点云分类与PointNet
作者: David Griffiths
创建日期: 2020/05/25
最后修改: 2024/01/09
描述: PointNet在ModelNet10分类中的实现。
点云分类
介绍
无序的3D点集（即点云）的分类、检测和分割是计算机视觉中的核心问题。此示例实现了开创性的点云深度学习论文PointNet (Qi et al., 2017)。有关PointNet的详细介绍，请参见这篇博客文章。
设置
如果使用colab，请首先通过!pip install trimesh安装trimesh。
import os
import glob
import trimesh
import numpy as np
from tensorflow import data as tf_data
from keras import ops
import keras
from keras import layers
from matplotlib import pyplot as plt
keras.utils.set_random_seed(seed=42)
加载数据集
我们使用ModelNet10模型数据集，这是ModelNet40数据集的较小10类版本。首先下载数据：
DATA_DIR = keras.utils.get_file(
"modelnet.zip",
"http://3dvision.princeton.edu/projects/2014/3DShapeNets/ModelNet10.zip",
extract=True,
)
DATA_DIR = os.path.join(os.path.dirname(DATA_DIR), "ModelNet10")
从 http://3dvision.princeton.edu/projects/2014/3DShapeNets/ModelNet10.zip 下载数据
0/473402300 ━━━━━━━━━━━━━━━━━━━━ 0s 0s/step
8192/473402300 ━━━━━━━━━━━━━━━━━━━━ 1:06:44 8us/step
40960/473402300 ━━━━━━━━━━━━━━━━━━━━ 26:17 3us/step
90112/473402300 ━━━━━━━━━━━━━━━━━━━━ 17:49 2us/step
188416/473402300 ━━━━━━━━━━━━━━━━━━━━ 11:20 1us/step
385024/473402300 ━━━━━━━━━━━━━━━━━━━━ 6:55 1us/step
786432/473402300 ━━━━━━━━━━━━━━━━━━━━ 4:03 1us/step
1581056/473402300 ━━━━━━━━━━━━━━━━━━━━ 2:21 0us/step
3170304/473402300 ━━━━━━━━━━━━━━━━━━━━ 1:20 0us/step
6004736/473402300 ━━━━━━━━━━━━━━━━━━━━ 47s 0us/step
8880128/473402300 ━━━━━━━━━━━━━━━━━━━━ 35s 0us/step
11902976/473402300 ━━━━━━━━━━━━━━━━━━━━ 28s 0us/step
14925824/473402300 ━━━━━━━━━━━━━━━━━━━━ 24s 0us/step
17915904/473402300 ━━━━━━━━━━━━━━━━━━━━ 22s 0us/step
21020672/473402300 ━━━━━━━━━━━━━━━━━━━━ 20s 0us/step
23977984/473402300 ━━━━━━━━━━━━━━━━━━━━ 18s 0us/step
26861568/473402300 ━━━━━━━━━━━━━━━━━━━━ 17s 0us/step
29958144/473402300 ━━━━━━━━━━━━━━━━━━━━ 16s 0us/step
33071104/473402300 ━━━━━━━━━━━━━━━━━━━━ 16s 0us/step
36175872/473402300 ━━━━━━━━━━━━━━━━━━━━ 15s 0us/step
39206912/473402300 ━━━━━━━━━━━━━━━━━━━━ 14s 0us/step
41902080/473402300 ━━━━━━━━━━━━━━━━━━━━ 14s 0us/step
45015040/473402300 ━━━━━━━━━━━━━━━━━━━━ 14s 0us/step
48021504/473402300 ━━━━━━━━━━━━━━━━━━━━ 13s 0us/step
51003392/473402300 ━━━━━━━━━━━━━━━━━━━━ 13s 0us/step
53960704/473402300 ━━━━━━━━━━━━━━━━━━━━ 13s 0us/step
56803328/473402300 ━━━━━━━━━━━━━━━━━━━━ 12s 0us/step
59834368/473402300 ━━━━━━━━━━━━━━━━━━━━ 12s 0us/step
62750720/473402300 ━━━━━━━━━━━━━━━━━━━━ 12s 0us/step
65839104/473402300 ━━━━━━━━━━━━━━━━━━━━ 12s 0us/step
68698112/473402300 ━━━━━━━━━━━━━━━━━━━━ 11s 0us/step
71385088/473402300 ━━━━━━━━━━━━━━━━━━━━ 11s 0us/step
74432512/473402300 ━━━━━━━━━━━━━━━━━━━━ 11s 0us/step
77365248/473402300 ━━━━━━━━━━━━━━━━━━━━ 11s 0us/step
80363520/473402300 ━━━━━━━━━━━━━━━━━━━━ 11s 0us/step
83156992/473402300 ━━━━━━━━━━━━━━━━━━━━ 11s 0us/step
86179840/473402300 ━━━━━━━━━━━━━━━━━━━━ 10s 0us/step
89300992/473402300 ━━━━━━━━━━━━━━━━━━━━ 10s 0us/step
92282880/473402300 ━━━━━━━━━━━━━━━━━━━━ 10s 0us/step
95371264/473402300 ━━━━━━━━━━━━━━━━━━━━ 10s 0us/step
98410496/473402300 ━━━━━━━━━━━━━━━━━━━━ 10s 0us/step
101130240/473402300 ━━━━━━━━━━━━━━━━━━━━ 10s 0us/step
104169472/473402300 ━━━━━━━━━━━━━━━━━━━━ 10s 0us/step
107192320/473402300 ━━━━━━━━━━━━━━━━━━━━ 9s 0us/step
110297088/473402300 ━━━━━━━━━━━━━━━━━━━━ 9s 0us/step
113344512/473402300 ━━━━━━━━━━━━━━━━━━━━ 9s 0us/step
116391936/473402300 ━━━━━━━━━━━━━━━━━━━━ 9s 0us/step
119513088/473402300 ━━━━━━━━━━━━━━━━━━━━ 9s 0us/step
122626048/473402300 ━━━━━━━━━━━━━━━━━━━━ 9s 0us/step
125313024/473402300 ━━━━━━━━━━━━━━━━━━━━ 9s 0us/step
128368640/473402300 ━━━━━━━━━━━━━━━━━━━━ 9s 0us/step
131432448/473402300 ━━━━━━━━━━━━━━━━━━━━ 8s 0us/step
134520832/473402300 ━━━━━━━━━━━━━━━━━━━━ 8s 0us/step
137560064/473402300 ━━━━━━━━━━━━━━━━━━━━ 8s 0us/step
140648448/473402300 ━━━━━━━━━━━━━━━━━━━━ 8s 0us/step
143720448/473402300 ━━━━━━━━━━━━━━━━━━━━ 8s 0us/step
146808832/473402300 ━━━━━━━━━━━━━━━━━━━━ 8s 0us/step
149864448/473402300 ━━━━━━━━━━━━━━━━━━━━ 8s 0us/step
152592384/473402300 ━━━━━━━━━━━━━━━━━━━━ 8s 0us/step
155623424/473402300 ━━━━━━━━━━━━━━━━━━━━ 8s 0us/step
158728192/473402300 ━━━━━━━━━━━━━━━━━━━━ 8s 0us/step
161783808/473402300 ━━━━━━━━━━━━━━━━━━━━ 7s 0us/step
164806656/473402300 ━━━━━━━━━━━━━━━━━━━━ 7s 0us/step
167895040/473402300 ━━━━━━━━━━━━━━━━━━━━ 7s 0us/step
170975232/473402300 ━━━━━━━━━━━━━━━━━━━━ 7s 0us/step
174071808/473402300 ━━━━━━━━━━━━━━━━━━━━ 7s 0us/step
177119232/473402300 ━━━━━━━━━━━━━━━━━━━━ 7s 0us/step
180166656/473402300 ━━━━━━━━━━━━━━━━━━━━ 7s 0us/step
182976512/473402300 ━━━━━━━━━━━━━━━━━━━━ 7s 0us/step
185884672/473402300 ━━━━━━━━━━━━━━━━━━━━ 7s 0us/step
188932096/473402300 ━━━━━━━━━━━━━━━━━━━━ 7s 0us/step
192028672/473402300 ━━━━━━━━━━━━━━━━━━━━ 7s 0us/step
195117056/473402300 ━━━━━━━━━━━━━━━━━━━━ 6s 0us/step
198189056/473402300 ━━━━━━━━━━━━━━━━━━━━ 6s 0us/step
201302016/473402300 ━━━━━━━━━━━━━━━━━━━━ 6s 0us/step
204406784/473402300 ━━━━━━━━━━━━━━━━━━━━ 6s 0us/step
207470592/473402300 ━━━━━━━━━━━━━━━━━━━━ 6s 0us/step
210575360/473402300 ━━━━━━━━━━━━━━━━━━━━ 6s 0us/step
213581824/473402300 ━━━━━━━━━━━━━━━━━━━━ 6s 0us/step
216268800/473402300 ━━━━━━━━━━━━━━━━━━━━ 6s 0us/step
218374144/473402300 ━━━━━━━━━━━━━━━━━━━━ 6s 0us/step
220569600/473402300 ━━━━━━━━━━━━━━━━━━━━ 6s 0us/step
222363648/473402300 ━━━━━━━━━━━━━━━━━━━━ 6s 0us/step
225345536/473402300 ━━━━━━━━━━━━━━━━━━━━ 6s 0us/step
228425728/473402300 ━━━━━━━━━━━━━━━━━━━━ 6s 0us/step
231473152/473402300 ━━━━━━━━━━━━━━━━━━━━ 5s 0us/step
234577920/473402300 ━━━━━━━━━━━━━━━━━━━━ 5s 0us/step
237690880/473402300 ━━━━━━━━━━━━━━━━━━━━ 5s 0us/step
240746496/473402300 ━━━━━━━━━━━━━━━━━━━━ 5s 0us/step
243834880/473402300 ━━━━━━━━━━━━━━━━━━━━ 5s 0us/step
246898688/473402300 ━━━━━━━━━━━━━━━━━━━━ 5s 0us/step
249954304/473402300 ━━━━━━━━━━━━━━━━━━━━ 5s 0us/step
252936192/473402300 ━━━━━━━━━━━━━━━━━━━━ 5s 0us/step
255672320/473402300 ━━━━━━━━━━━━━━━━━━━━ 5s 0us/step
258695168/473402300 ━━━━━━━━━━━━━━━━━━━━ 5s 0us/step
261734400/473402300 ━━━━━━━━━━━━━━━━━━━━ 5s 0us/step
264847360/473402300 ━━━━━━━━━━━━━━━━━━━━ 5s 0us/step
267919360/473402300 ━━━━━━━━━━━━━━━━━━━━ 4s 0us/step
271015936/473402300 ━━━━━━━━━━━━━━━━━━━━ 4s 0us/step
273768448/473402300 ━━━━━━━━━━━━━━━━━━━━ 4s 0us/step
276840448/473402300 ━━━━━━━━━━━━━━━━━━━━ 4s 0us/step
279625728/473402300 ━━━━━━━━━━━━━━━━━━━━ 4s 0us/step
282525696/473402300 ━━━━━━━━━━━━━━━━━━━━ 4s 0us/step
285581312/473402300 ━━━━━━━━━━━━━━━━━━━━ 4s 0us/step
288645120/473402300 ━━━━━━━━━━━━━━━━━━━━ 4s 0us/step
291733504/473402300 ━━━━━━━━━━━━━━━━━━━━ 4s 0us/step
294682624/473402300 ━━━━━━━━━━━━━━━━━━━━ 4s 0us/step
297795584/473402300 ━━━━━━━━━━━━━━━━━━━━ 4s 0us/step
300851200/473402300 ━━━━━━━━━━━━━━━━━━━━ 4s 0us/step
303955968/473402300 ━━━━━━━━━━━━━━━━━━━━ 4s 0us/step
306798592/473402300 ━━━━━━━━━━━━━━━━━━━━ 3s 0us/step
309846016/473402300 ━━━━━━━━━━━━━━━━━━━━ 3s 0us/step
312926208/473402300 ━━━━━━━━━━━━━━━━━━━━ 3s 0us/step
315990016/473402300 ━━━━━━━━━━━━━━━━━━━━ 3s 0us/step
319053824/473402300 ━━━━━━━━━━━━━━━━━━━━ 3s 0us/step
322134016/473402300 ━━━━━━━━━━━━━━━━━━━━ 3s 0us/step
325099520/473402300 ━━━━━━━━━━━━━━━━━━━━ 3s 0us/step
328187904/473402300 ━━━━━━━━━━━━━━━━━━━━ 3s 0us/step
331251712/473402300 ━━━━━━━━━━━━━━━━━━━━ 3s 0us/step
334364672/473402300 ━━━━━━━━━━━━━━━━━━━━ 3s 0us/step
337477632/473402300 ━━━━━━━━━━━━━━━━━━━━ 3s 0us/step
340598784/473402300 ━━━━━━━━━━━━━━━━━━━━ 3s 0us/step
343130112/473402300 ━━━━━━━━━━━━━━━━━━━━ 3s 0us/step
345554944/473402300 ━━━━━━━━━━━━━━━━━━━━ 3s 0us/step
347570176/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step
350224384/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step
352436224/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step
355393536/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step
357179392/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step
359858176/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step
362045440/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step
364281856/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step
364298240/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step
364306432/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step
364314624/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step
364322816/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step
364331008/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step
364339200/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step
364347392/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step
364355584/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step
364363776/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step
364371968/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step
364380160/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step
364396544/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step
364445696/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step
364601344/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step
365084672/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step
366510080/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step
369491968/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step
372400128/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step
375521280/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step
378535936/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step
381558784/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step
384475136/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step
387571712/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step
390463488/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step
393551872/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step
396632064/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step
399704064/473402300 ━━━━━━━━━━━━━━━━━━━━ 1s 0us/step
402767872/473402300 ━━━━━━━━━━━━━━━━━━━━ 1s 0us/step
405790720/473402300 ━━━━━━━━━━━━━━━━━━━━ 1s 0us/step
408854528/473402300 ━━━━━━━━━━━━━━━━━━━━ 1s 0us/step
411975680/473402300 ━━━━━━━━━━━━━━━━━━━━ 1s 0us/step
414982144/473402300 ━━━━━━━━━━━━━━━━━━━━ 1s 0us/step
418045952/473402300 ━━━━━━━━━━━━━━━━━━━━ 1s 0us/step
421167104/473402300 ━━━━━━━━━━━━━━━━━━━━ 1s 0us/step
423878656/473402300 ━━━━━━━━━━━━━━━━━━━━ 1s 0us/step
426999808/473402300 ━━━━━━━━━━━━━━━━━━━━ 1s 0us/step
430112768/473402300 ━━━━━━━━━━━━━━━━━━━━ 1s 0us/step
433053696/473402300 ━━━━━━━━━━━━━━━━━━━━ 1s 0us/step
436125696/473402300 ━━━━━━━━━━━━━━━━━━━━ 0s 0us/step
439189504/473402300 ━━━━━━━━━━━━━━━━━━━━ 0s 0us/step
442286080/473402300 ━━━━━━━━━━━━━━━━━━━━ 0s 0us/step
445063168/473402300 ━━━━━━━━━━━━━━━━━━━━ 0s 0us/step
448118784/473402300 ━━━━━━━━━━━━━━━━━━━━ 0s 0us/step
451166208/473402300 ━━━━━━━━━━━━━━━━━━━━ 0s 0us/step
454262784/473402300 ━━━━━━━━━━━━━━━━━━━━ 0s 0us/step
457293824/473402300 ━━━━━━━━━━━━━━━━━━━━ 0s 0us/step
460275712/473402300 ━━━━━━━━━━━━━━━━━━━━ 0s 0us/step
463011840/473402300 ━━━━━━━━━━━━━━━━━━━━ 0s 0us/step
466018304/473402300 ━━━━━━━━━━━━━━━━━━━━ 0s 0us/step
469057536/473402300 ━━━━━━━━━━━━━━━━━━━━ 0s 0us/step
472145920/473402300 ━━━━━━━━━━━━━━━━━━━━ 0s 0us/step
473402300/473402300 ━━━━━━━━━━━━━━━━━━━━ 12s 0us/step
我们可以使用 trimesh 包来读取和可视化 .off 网格文件。
mesh = trimesh.load(os.path.join(DATA_DIR, "chair/train/chair_0001.off")) # 加载网格文件
mesh.show() # 显示网格
To convert a mesh file to a point cloud we first need to sample points on the mesh
surface. .sample() performs a uniform random sampling. Here we sample at 2048 locations
and visualize in matplotlib.
points = mesh.sample(2048)
fig = plt.figure(figsize=(5, 5))
ax = fig.add_subplot(111, projection="3d")
ax.scatter(points[:, 0], points[:, 1], points[:, 2])
ax.set_axis_off()
plt.show()
To generate a tf.data.Dataset() we need to first parse through the ModelNet data
folders. Each mesh is loaded and sampled into a point cloud before being added to a
standard python list and converted to a numpy array. We also store the current
enumerate index value as the object label and use a dictionary to recall this later.
def parse_dataset(num_points=2048):
train_points = []
train_labels = []
test_points = []
test_labels = []
class_map = {}
folders = glob.glob(os.path.join(DATA_DIR, "[!README]*"))
for i, folder in enumerate(folders):
print("processing class: {}".format(os.path.basename(folder)))
# store folder name with ID so we can retrieve later
class_map[i] = folder.split("/")[-1]
# gather all files
train_files = glob.glob(os.path.join(folder, "train/*"))
test_files = glob.glob(os.path.join(folder, "test/*"))
for f in train_files:
train_points.append(trimesh.load(f).sample(num_points))
train_labels.append(i)
for f in test_files:
test_points.append(trimesh.load(f).sample(num_points))
test_labels.append(i)
return (
np.array(train_points),
np.array(test_points),
np.array(train_labels),
np.array(test_labels),
class_map,
)
Set the number of points to sample and batch size and parse the dataset. This can take ~5minutes to complete.
NUM_POINTS = 2048
NUM_CLASSES = 10
BATCH_SIZE = 32
train_points, test_points, train_labels, test_labels, CLASS_MAP = parse_dataset(
NUM_POINTS
)
processing class: bathtub
processing class: monitor
processing class: desk
processing class: dresser
processing class: toilet
processing class: bed
processing class: sofa
processing class: chair
processing class: night_stand
processing class: table
Our data can now be read into a tf.data.Dataset() object. We set the shuffle buffer
size to the entire size of the dataset as prior to this the data is ordered by class.
Data augmentation is important when working with point cloud data. We create a
augmentation function to jitter and shuffle the train dataset.
def augment(points, label):
# jitter points
points += keras.random.uniform(points.shape, -0.005, 0.005, dtype="float64")
# shuffle points
points = keras.random.shuffle(points)
return points, label
train_size = 0.8
dataset = tf_data.Dataset.from_tensor_slices((train_points, train_labels))
test_dataset = tf_data.Dataset.from_tensor_slices((test_points, test_labels))
train_dataset_size = int(len(dataset) * train_size)
dataset = dataset.shuffle(len(train_points)).map(augment)
test_dataset = test_dataset.shuffle(len(test_points)).batch(BATCH_SIZE)
train_dataset = dataset.take(train_dataset_size).batch(BATCH_SIZE)
validation_dataset = dataset.skip(train_dataset_size).batch(BATCH_SIZE)
Build a model
Each convolution and fully-connected layer (with exception for end layers) consists of Convolution / Dense -> Batch Normalization -> ReLU Activation.
def conv_bn(x, filters):
x = layers.Conv1D(filters, kernel_size=1, padding="valid")(x)
x = layers.BatchNormalization(momentum=0.0)(x)
return layers.Activation("relu")(x)
def dense_bn(x, filters):
x = layers.Dense(filters)(x)
x = layers.BatchNormalization(momentum=0.0)(x)
return layers.Activation("relu")(x)
PointNet consists of two core components. The primary MLP network, and the transformer net (T-net). The T-net aims to learn an affine transformation matrix by its own mini network. The T-net is used twice. The first time to transform the input features (n, 3) into a canonical representation. The second is an affine transformation for alignment in feature space (n, 3). As per the original paper we constrain the transformation to be close to an orthogonal matrix (i.e. ||X*X^T - I|| = 0).
class OrthogonalRegularizer(keras.regularizers.Regularizer):
def __init__(self, num_features, l2reg=0.001):
self.num_features = num_features
self.l2reg = l2reg
self.eye = ops.eye(num_features)
def __call__(self, x):
x = ops.reshape(x, (-1, self.num_features, self.num_features))
xxt = ops.tensordot(x, x, axes=(2, 2))
xxt = ops.reshape(xxt, (-1, self.num_features, self.num_features))
return ops.sum(self.l2reg * ops.square(xxt - self.eye))
We can then define a general function to build T-net layers.
def tnet(inputs, num_features):
# Initialise bias as the identity matrix
bias = keras.initializers.Constant(np.eye(num_features).flatten())
reg = OrthogonalRegularizer(num_features)
x = conv_bn(inputs, 32)
x = conv_bn(x, 64)
x = conv_bn(x, 512)
x = layers.GlobalMaxPooling1D()(x)
x = dense_bn(x, 256)
x = dense_bn(x, 128)
x = layers.Dense(
num_features * num_features,
kernel_initializer="zeros",
bias_initializer=bias,
activity_regularizer=reg,
)(x)
feat_T = layers.Reshape((num_features, num_features))(x)
# Apply affine transformation to input features
return layers.Dot(axes=(2, 1))([inputs, feat_T])
The main network can be then implemented in the same manner where the t-net mini models can be dropped in a layers in the graph. Here we replicate the network architecture published in the original paper but with half the number of weights at each layer as we are using the smaller 10 class ModelNet dataset.
inputs = keras.Input(shape=(NUM_POINTS, 3))
x = tnet(inputs, 3)
x = conv_bn(x, 32)
x = conv_bn(x, 32)
x = tnet(x, 32)
x = conv_bn(x, 32)
x = conv_bn(x, 64)
x = conv_bn(x, 512)
x = layers.GlobalMaxPooling1D()(x)
x = dense_bn(x, 256)
x = layers.Dropout(0.3)(x)
x = dense_bn(x, 128)
x = layers.Dropout(0.3)(x)
outputs = layers.Dense(NUM_CLASSES, activation="softmax")(x)
model = keras.Model(inputs=inputs, outputs=outputs, name="pointnet")
model.summary()
Model: "pointnet"
┏━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━┓ ┃ Layer (type) ┃ Output Shape ┃ Param # ┃ Connected to ┃ ┡━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━┩ │ input_layer │ (None, 2048, 3) │ 0 │ - │ │ (InputLayer) │ │ │ │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ conv1d (Conv1D) │ (None, 2048, 32) │ 128 │ input_layer[0][0] │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ batch_normalization │ (None, 2048, 32) │ 128 │ conv1d[0][0] │ │ (BatchNormalizatio… │ │ │ │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ activation │ (None, 2048, 32) │ 0 │ batch_normalization… │ │ (Activation) │ │ │ │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ conv1d_1 (Conv1D) │ (None, 2048, 64) │ 2,112 │ activation[0][0] │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ batch_normalizatio… │ (None, 2048, 64) │ 256 │ conv1d_1[0][0] │ │ (BatchNormalizatio… │ │ │ │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ activation_1 │ (None, 2048, 64) │ 0 │ batch_normalization… │ │ (Activation) │ │ │ │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ conv1d_2 (Conv1D) │ (None, 2048, 512) │ 33,280 │ activation_1[0][0] │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ batch_normalizatio… │ (None, 2048, 512) │ 2,048 │ conv1d_2[0][0] │ │ (BatchNormalizatio… │ │ │ │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ activation_2 │ (None, 2048, 512) │ 0 │ batch_normalization… │ │ (Activation) │ │ │ │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ global_max_pooling… │ (None, 512) │ 0 │ activation_2[0][0] │ │ (GlobalMaxPooling1… │ │ │ │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ dense (Dense) │ (None, 256) │ 131,328 │ global_max_pooling1… │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ batch_normalizatio… │ (None, 256) │ 1,024 │ dense[0][0] │ │ (BatchNormalizatio… │ │ │ │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ activation_3 │ (None, 256) │ 0 │ batch_normalization… │ │ (Activation) │ │ │ │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ dense_1 (Dense) │ (None, 128) │ 32,896 │ activation_3[0][0] │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ batch_normalizatio… │ (None, 128) │ 512 │ dense_1[0][0] │ │ (BatchNormalizatio… │ │ │ │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ activation_4 │ (None, 128) │ 0 │ batch_normalization… │ │ (Activation) │ │ │ │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ dense_2 (Dense) │ (None, 9) │ 1,161 │ activation_4[0][0] │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ reshape (Reshape) │ (None, 3, 3) │ 0 │ dense_2[0][0] │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ dot (Dot) │ (None, 2048, 3) │ 0 │ input_layer[0][0], │ │ │ │ │ reshape[0][0] │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ conv1d_3 (Conv1D) │ (None, 2048, 32) │ 128 │ dot[0][0] │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ batch_normalizatio… │ (None, 2048, 32) │ 128 │ conv1d_3[0][0] │ │ (BatchNormalizatio… │ │ │ │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ activation_5 │ (None, 2048, 32) │ 0 │ batch_normalization… │ │ (Activation) │ │ │ │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ conv1d_4 (Conv1D) │ (None, 2048, 32) │ 1,056 │ activation_5[0][0] │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ batch_normalizatio… │ (None, 2048, 32) │ 128 │ conv1d_4[0][0] │ │ (BatchNormalizatio… │ │ │ │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ activation_6 │ (None, 2048, 32) │ 0 │ batch_normalization… │ │ (Activation) │ │ │ │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ conv1d_5 (Conv1D) │ (None, 2048, 32) │ 1,056 │ activation_6[0][0] │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ batch_normalizatio… │ (None, 2048, 32) │ 128 │ conv1d_5[0][0] │ │ (BatchNormalizatio… │ │ │ │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ activation_7 │ (None, 2048, 32) │ 0 │ batch_normalization… │ │ (Activation) │ │ │ │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ conv1d_6 (Conv1D) │ (None, 2048, 64) │ 2,112 │ activation_7[0][0] │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ batch_normalizatio… │ (None, 2048, 64) │ 256 │ conv1d_6[0][0] │ │ (BatchNormalizatio… │ │ │ │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ activation_8 │ (None, 2048, 64) │ 0 │ batch_normalization… │ │ (Activation) │ │ │ │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ conv1d_7 (Conv1D) │ (None, 2048, 512) │ 33,280 │ activation_8[0][0] │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ batch_normalizatio… │ (None, 2048, 512) │ 2,048 │ conv1d_7[0][0] │ │ (BatchNormalizatio… │ │ │ │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ activation_9 │ (None, 2048, 512) │ 0 │ batch_normalization… │ │ (Activation) │ │ │ │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ global_max_pooling… │ (None, 512) │ 0 │ activation_9[0][0] │ │ (GlobalMaxPooling1… │ │ │ │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ dense_3 (Dense) │ (None, 256) │ 131,328 │ global_max_pooling1… │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ batch_normalizatio… │ (None, 256) │ 1,024 │ dense_3[0][0] │ │ (BatchNormalizatio… │ │ │ │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ activation_10 │ (None, 256) │ 0 │ batch_normalization… │ │ (Activation) │ │ │ │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ dense_4 (Dense) │ (None, 128) │ 32,896 │ activation_10[0][0] │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ batch_normalizatio… │ (None, 128) │ 512 │ dense_4[0][0] │ │ (BatchNormalizatio… │ │ │ │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ activation_11 │ (None, 128) │ 0 │ batch_normalization… │ │ (Activation) │ │ │ │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ dense_5 (Dense) │ (None, 1024) │ 132,096 │ activation_11[0][0] │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ reshape_1 (Reshape) │ (None, 32, 32) │ 0 │ dense_5[0][0] │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ dot_1 (Dot) │ (None, 2048, 32) │ 0 │ activation_6[0][0], │ │ │ │ │ reshape_1[0][0] │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ conv1d_8 (Conv1D) │ (None, 2048, 32) │ 1,056 │ dot_1[0][0] │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ batch_normalizatio… │ (None, 2048, 32) │ 128 │ conv1d_8[0][0] │ │ (BatchNormalizatio… │ │ │ │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ activation_12 │ (None, 2048, 32) │ 0 │ batch_normalization… │ │ (Activation) │ │ │ │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ conv1d_9 (Conv1D) │ (None, 2048, 64) │ 2,112 │ activation_12[0][0] │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ batch_normalizatio… │ (None, 2048, 64) │ 256 │ conv1d_9[0][0] │ │ (BatchNormalizatio… │ │ │ │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ activation_13 │ (None, 2048, 64) │ 0 │ batch_normalization… │ │ (Activation) │ │ │ │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ conv1d_10 (Conv1D) │ (None, 2048, 512) │ 33,280 │ activation_13[0][0] │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ batch_normalizatio… │ (None, 2048, 512) │ 2,048 │ conv1d_10[0][0] │ │ (BatchNormalizatio… │ │ │ │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ activation_14 │ (None, 2048, 512) │ 0 │ batch_normalization… │ │ (Activation) │ │ │ │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ global_max_pooling… │ (None, 512) │ 0 │ activation_14[0][0] │ │ (GlobalMaxPooling1… │ │ │ │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ dense_6 (Dense) │ (None, 256) │ 131,328 │ global_max_pooling1… │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ batch_normalizatio… │ (None, 256) │ 1,024 │ dense_6[0][0] │ │ (BatchNormalizatio… │ │ │ │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ activation_15 │ (None, 256) │ 0 │ batch_normalization… │ │ (Activation) │ │ │ │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ dropout (Dropout) │ (None, 256) │ 0 │ activation_15[0][0] │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ dense_7 (Dense) │ (None, 128) │ 32,896 │ dropout[0][0] │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ batch_normalizatio… │ (None, 128) │ 512 │ dense_7[0][0] │ │ (BatchNormalizatio… │ │ │ │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ activation_16 │ (None, 128) │ 0 │ batch_normalization… │ │ (Activation) │ │ │ │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ dropout_1 (Dropout) │ (None, 128) │ 0 │ activation_16[0][0] │ ├─────────────────────┼───────────────────┼─────────┼──────────────────────┤ │ dense_8 (Dense) │ (None, 10) │ 1,290 │ dropout_1[0][0] │ └─────────────────────┴───────────────────┴─────────┴──────────────────────┘
Total params: 748,979 (2.86 MB)
Trainable params: 742,899 (2.83 MB)
Non-trainable params: 6,080 (23.75 KB)
Train model
Once the model is defined it can be trained like any other standard classification model
using .compile() and .fit().
model.compile(
loss="sparse_categorical_crossentropy",
optimizer=keras.optimizers.Adam(learning_rate=0.001),
metrics=["sparse_categorical_accuracy"],
)
model.fit(train_dataset, epochs=20, validation_data=validation_dataset)
Epoch 1/20
1/100 [37m━━━━━━━━━━━━━━━━━━━━ 16:59 10s/step - loss: 70.7465 - sparse_categorical_accuracy: 0.2188
2/100 [37m━━━━━━━━━━━━━━━━━━━━ 2:06 1s/step - loss: 69.8872 - sparse_categorical_accuracy: 0.1953
3/100 [37m━━━━━━━━━━━━━━━━━━━━ 2:00 1s/step - loss: 69.4798 - sparse_categorical_accuracy: 0.1823
4/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:57 1s/step - loss: 68.7454 - sparse_categorical_accuracy: 0.1719
5/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:53 1s/step - loss: 67.8508 - sparse_categorical_accuracy: 0.1700
6/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:50 1s/step - loss: 67.0352 - sparse_categorical_accuracy: 0.1703
7/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:47 1s/step - loss: 66.3409 - sparse_categorical_accuracy: 0.1702
8/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:45 1s/step - loss: 65.5973 - sparse_categorical_accuracy: 0.1734
9/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:43 1s/step - loss: 64.8169 - sparse_categorical_accuracy: 0.1761
10/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:41 1s/step - loss: 64.0699 - sparse_categorical_accuracy: 0.1769
11/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:39 1s/step - loss: 63.3220 - sparse_categorical_accuracy: 0.1779
12/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:38 1s/step - loss: 62.6677 - sparse_categorical_accuracy: 0.1776
13/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:36 1s/step - loss: 62.0234 - sparse_categorical_accuracy: 0.1778
14/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:35 1s/step - loss: 61.4256 - sparse_categorical_accuracy: 0.1774
15/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:34 1s/step - loss: 60.8435 - sparse_categorical_accuracy: 0.1772
16/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:32 1s/step - loss: 60.2982 - sparse_categorical_accuracy: 0.1771
17/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:31 1s/step - loss: 59.7788 - sparse_categorical_accuracy: 0.1773
18/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:29 1s/step - loss: 59.2792 - sparse_categorical_accuracy: 0.1777
19/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:28 1s/step - loss: 58.7959 - sparse_categorical_accuracy: 0.1782
20/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:27 1s/step - loss: 58.3345 - sparse_categorical_accuracy: 0.1787
21/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:25 1s/step - loss: 57.8916 - sparse_categorical_accuracy: 0.1794
22/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:24 1s/step - loss: 57.4650 - sparse_categorical_accuracy: 0.1803
23/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:23 1s/step - loss: 57.0690 - sparse_categorical_accuracy: 0.1811
24/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:22 1s/step - loss: 56.6876 - sparse_categorical_accuracy: 0.1819
25/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:20 1s/step - loss: 56.3285 - sparse_categorical_accuracy: 0.1827
26/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:19 1s/step - loss: 55.9864 - sparse_categorical_accuracy: 0.1834
27/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:18 1s/step - loss: 55.6550 - sparse_categorical_accuracy: 0.1843
28/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:17 1s/step - loss: 55.3351 - sparse_categorical_accuracy: 0.1852
29/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:16 1s/step - loss: 55.0261 - sparse_categorical_accuracy: 0.1863
30/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:15 1s/step - loss: 54.7329 - sparse_categorical_accuracy: 0.1872
31/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:13 1s/step - loss: 54.4503 - sparse_categorical_accuracy: 0.1882
32/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:12 1s/step - loss: 54.1778 - sparse_categorical_accuracy: 0.1891
33/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:11 1s/step - loss: 53.9170 - sparse_categorical_accuracy: 0.1900
34/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:10 1s/step - loss: 53.6651 - sparse_categorical_accuracy: 0.1909
35/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:09 1s/step - loss: 53.4239 - sparse_categorical_accuracy: 0.1916
36/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:08 1s/step - loss: 53.1926 - sparse_categorical_accuracy: 0.1922
37/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:07 1s/step - loss: 52.9695 - sparse_categorical_accuracy: 0.1929
38/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:05 1s/step - loss: 52.7542 - sparse_categorical_accuracy: 0.1935
39/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:04 1s/step - loss: 52.5469 - sparse_categorical_accuracy: 0.1940
40/100 ━━━━━━━━[37m━━━━━━━━━━━━ 1:03 1s/step - loss: 52.3461 - sparse_categorical_accuracy: 0.1946
41/100 ━━━━━━━━[37m━━━━━━━━━━━━ 1:02 1s/step - loss: 52.1509 - sparse_categorical_accuracy: 0.1950
42/100 ━━━━━━━━[37m━━━━━━━━━━━━ 1:01 1s/step - loss: 51.9608 - sparse_categorical_accuracy: 0.1955
43/100 ━━━━━━━━[37m━━━━━━━━━━━━ 1:00 1s/step - loss: 51.7759 - sparse_categorical_accuracy: 0.1960
44/100 ━━━━━━━━[37m━━━━━━━━━━━━ 59s 1s/step - loss: 51.5960 - sparse_categorical_accuracy: 0.1966
45/100 ━━━━━━━━━[37m━━━━━━━━━━━ 58s 1s/step - loss: 51.4224 - sparse_categorical_accuracy: 0.1971
46/100 ━━━━━━━━━[37m━━━━━━━━━━━ 57s 1s/step - loss: 51.2539 - sparse_categorical_accuracy: 0.1976
47/100 ━━━━━━━━━[37m━━━━━━━━━━━ 56s 1s/step - loss: 51.0897 - sparse_categorical_accuracy: 0.1982
48/100 ━━━━━━━━━[37m━━━━━━━━━━━ 55s 1s/step - loss: 50.9300 - sparse_categorical_accuracy: 0.1987
49/100 ━━━━━━━━━[37m━━━━━━━━━━━ 54s 1s/step - loss: 50.7742 - sparse_categorical_accuracy: 0.1992
50/100 ━━━━━━━━━━[37m━━━━━━━━━━ 52s 1s/step - loss: 50.6223 - sparse_categorical_accuracy: 0.1997
51/100 ━━━━━━━━━━[37m━━━━━━━━━━ 51s 1s/step - loss: 50.4747 - sparse_categorical_accuracy: 0.2001
52/100 ━━━━━━━━━━[37m━━━━━━━━━━ 50s 1s/step - loss: 50.3312 - sparse_categorical_accuracy: 0.2006
53/100 ━━━━━━━━━━[37m━━━━━━━━━━ 49s 1s/step - loss: 50.1910 - sparse_categorical_accuracy: 0.2011
54/100 ━━━━━━━━━━[37m━━━━━━━━━━ 48s 1s/step - loss: 50.0539 - sparse_categorical_accuracy: 0.2017
55/100 ━━━━━━━━━━━[37m━━━━━━━━━ 47s 1s/step - loss: 49.9200 - sparse_categorical_accuracy: 0.2022
56/100 ━━━━━━━━━━━[37m━━━━━━━━━ 46s 1s/step - loss: 49.7896 - sparse_categorical_accuracy: 0.2027
57/100 ━━━━━━━━━━━[37m━━━━━━━━━ 45s 1s/step - loss: 49.6620 - sparse_categorical_accuracy: 0.2032
58/100 ━━━━━━━━━━━[37m━━━━━━━━━ 44s 1s/step - loss: 49.5372 - sparse_categorical_accuracy: 0.2037
59/100 ━━━━━━━━━━━[37m━━━━━━━━━ 43s 1s/step - loss: 49.4152 - sparse_categorical_accuracy: 0.2041
60/100 ━━━━━━━━━━━━[37m━━━━━━━━ 42s 1s/step - loss: 49.2957 - sparse_categorical_accuracy: 0.2046
61/100 ━━━━━━━━━━━━[37m━━━━━━━━ 41s 1s/step - loss: 49.1790 - sparse_categorical_accuracy: 0.2050
62/100 ━━━━━━━━━━━━[37m━━━━━━━━ 40s 1s/step - loss: 49.0646 - sparse_categorical_accuracy: 0.2054
63/100 ━━━━━━━━━━━━[37m━━━━━━━━ 39s 1s/step - loss: 48.9525 - sparse_categorical_accuracy: 0.2058
64/100 ━━━━━━━━━━━━[37m━━━━━━━━ 37s 1s/step - loss: 48.8427 - sparse_categorical_accuracy: 0.2062
65/100 ━━━━━━━━━━━━━[37m━━━━━━━ 36s 1s/step - loss: 48.7353 - sparse_categorical_accuracy: 0.2065
66/100 ━━━━━━━━━━━━━[37m━━━━━━━ 35s 1s/step - loss: 48.6299 - sparse_categorical_accuracy: 0.2069
67/100 ━━━━━━━━━━━━━[37m━━━━━━━ 34s 1s/step - loss: 48.5266 - sparse_categorical_accuracy: 0.2072
68/100 ━━━━━━━━━━━━━[37m━━━━━━━ 33s 1s/step - loss: 48.4277 - sparse_categorical_accuracy: 0.2075
69/100 ━━━━━━━━━━━━━[37m━━━━━━━ 32s 1s/step - loss: 48.3308 - sparse_categorical_accuracy: 0.2078
70/100 ━━━━━━━━━━━━━━[37m━━━━━━ 31s 1s/step - loss: 48.2357 - sparse_categorical_accuracy: 0.2081
71/100 ━━━━━━━━━━━━━━[37m━━━━━━ 30s 1s/step - loss: 48.1423 - sparse_categorical_accuracy: 0.2084
72/100 ━━━━━━━━━━━━━━[37m━━━━━━ 29s 1s/step - loss: 48.0505 - sparse_categorical_accuracy: 0.2087
73/100 ━━━━━━━━━━━━━━[37m━━━━━━ 28s 1s/step - loss: 47.9604 - sparse_categorical_accuracy: 0.2090
74/100 ━━━━━━━━━━━━━━[37m━━━━━━ 27s 1s/step - loss: 47.8719 - sparse_categorical_accuracy: 0.2093
75/100 ━━━━━━━━━━━━━━━[37m━━━━━ 26s 1s/step - loss: 47.7852 - sparse_categorical_accuracy: 0.2096
76/100 ━━━━━━━━━━━━━━━[37m━━━━━ 25s 1s/step - loss: 47.7000 - sparse_categorical_accuracy: 0.2098
77/100 ━━━━━━━━━━━━━━━[37m━━━━━ 24s 1s/step - loss: 47.6164 - sparse_categorical_accuracy: 0.2101
78/100 ━━━━━━━━━━━━━━━[37m━━━━━ 23s 1s/step - loss: 47.5342 - sparse_categorical_accuracy: 0.2104
79/100 ━━━━━━━━━━━━━━━[37m━━━━━ 22s 1s/step - loss: 47.4536 - sparse_categorical_accuracy: 0.2106
80/100 ━━━━━━━━━━━━━━━━[37m━━━━ 21s 1s/step - loss: 47.3744 - sparse_categorical_accuracy: 0.2109
81/100 ━━━━━━━━━━━━━━━━[37m━━━━ 19s 1s/step - loss: 47.2967 - sparse_categorical_accuracy: 0.2112
82/100 ━━━━━━━━━━━━━━━━[37m━━━━ 18s 1s/step - loss: 47.2202 - sparse_categorical_accuracy: 0.2114
83/100 ━━━━━━━━━━━━━━━━[37m━━━━ 17s 1s/step - loss: 47.1450 - sparse_categorical_accuracy: 0.2117
84/100 ━━━━━━━━━━━━━━━━[37m━━━━ 16s 1s/step - loss: 47.0711 - sparse_categorical_accuracy: 0.2119
85/100 ━━━━━━━━━━━━━━━━━[37m━━━ 15s 1s/step - loss: 46.9984 - sparse_categorical_accuracy: 0.2122
86/100 ━━━━━━━━━━━━━━━━━[37m━━━ 14s 1s/step - loss: 46.9270 - sparse_categorical_accuracy: 0.2124
87/100 ━━━━━━━━━━━━━━━━━[37m━━━ 13s 1s/step - loss: 46.8568 - sparse_categorical_accuracy: 0.2126
88/100 ━━━━━━━━━━━━━━━━━[37m━━━ 12s 1s/step - loss: 46.7877 - sparse_categorical_accuracy: 0.2129
89/100 ━━━━━━━━━━━━━━━━━[37m━━━ 11s 1s/step - loss: 46.7196 - sparse_categorical_accuracy: 0.2131
90/100 ━━━━━━━━━━━━━━━━━━[37m━━ 10s 1s/step - loss: 46.6525 - sparse_categorical_accuracy: 0.2133
91/100 ━━━━━━━━━━━━━━━━━━[37m━━ 9s 1s/step - loss: 46.5865 - sparse_categorical_accuracy: 0.2135
92/100 ━━━━━━━━━━━━━━━━━━[37m━━ 8s 1s/step - loss: 46.5215 - sparse_categorical_accuracy: 0.2137
93/100 ━━━━━━━━━━━━━━━━━━[37m━━ 7s 1s/step - loss: 46.4574 - sparse_categorical_accuracy: 0.2139
94/100 ━━━━━━━━━━━━━━━━━━[37m━━ 6s 1s/step - loss: 46.3946 - sparse_categorical_accuracy: 0.2141
95/100 ━━━━━━━━━━━━━━━━━━━[37m━ 5s 1s/step - loss: 46.3327 - sparse_categorical_accuracy: 0.2143
96/100 ━━━━━━━━━━━━━━━━━━━[37m━ 4s 1s/step - loss: 46.2717 - sparse_categorical_accuracy: 0.2145
97/100 ━━━━━━━━━━━━━━━━━━━[37m━ 3s 1s/step - loss: 46.2115 - sparse_categorical_accuracy: 0.2147
98/100 ━━━━━━━━━━━━━━━━━━━[37m━ 2s 1s/step - loss: 46.1522 - sparse_categorical_accuracy: 0.2149
99/100 ━━━━━━━━━━━━━━━━━━━[37m━ 1s 1s/step - loss: 46.0937 - sparse_categorical_accuracy: 0.2151
100/100 ━━━━━━━━━━━━━━━━━━━━ 0s 1s/step - loss: 46.0345 - sparse_categorical_accuracy: 0.2154
100/100 ━━━━━━━━━━━━━━━━━━━━ 119s 1s/step - loss: 45.9764 - sparse_categorical_accuracy: 0.2156 - val_loss: 4122951.0000 - val_sparse_categorical_accuracy: 0.3154
Epoch 2/20
1/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:44 1s/step - loss: 36.7920 - sparse_categorical_accuracy: 0.2500
2/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:42 1s/step - loss: 36.8501 - sparse_categorical_accuracy: 0.2188
3/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:39 1s/step - loss: 36.8194 - sparse_categorical_accuracy: 0.2049
4/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:37 1s/step - loss: 36.7948 - sparse_categorical_accuracy: 0.1947
5/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:35 1s/step - loss: 36.7802 - sparse_categorical_accuracy: 0.1907
6/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:34 1s/step - loss: 36.7761 - sparse_categorical_accuracy: 0.1911
7/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:33 1s/step - loss: 36.7720 - sparse_categorical_accuracy: 0.1937
8/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:33 1s/step - loss: 36.7660 - sparse_categorical_accuracy: 0.1964
9/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:32 1s/step - loss: 36.7617 - sparse_categorical_accuracy: 0.1977
10/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:30 1s/step - loss: 36.7567 - sparse_categorical_accuracy: 0.1992
11/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:30 1s/step - loss: 36.7558 - sparse_categorical_accuracy: 0.2007
12/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:29 1s/step - loss: 36.7534 - sparse_categorical_accuracy: 0.2022
13/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:28 1s/step - loss: 36.7539 - sparse_categorical_accuracy: 0.2033
14/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:27 1s/step - loss: 36.7521 - sparse_categorical_accuracy: 0.2049
15/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:26 1s/step - loss: 36.7500 - sparse_categorical_accuracy: 0.2064
16/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:25 1s/step - loss: 36.7464 - sparse_categorical_accuracy: 0.2087
17/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:25 1s/step - loss: 36.7410 - sparse_categorical_accuracy: 0.2116
18/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:24 1s/step - loss: 36.7356 - sparse_categorical_accuracy: 0.2138
19/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:23 1s/step - loss: 36.7314 - sparse_categorical_accuracy: 0.2157
20/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:21 1s/step - loss: 36.7275 - sparse_categorical_accuracy: 0.2178
21/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:20 1s/step - loss: 36.7235 - sparse_categorical_accuracy: 0.2196
22/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:19 1s/step - loss: 36.7189 - sparse_categorical_accuracy: 0.2218
23/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:18 1s/step - loss: 36.7141 - sparse_categorical_accuracy: 0.2241
24/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:17 1s/step - loss: 36.7087 - sparse_categorical_accuracy: 0.2262
25/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:16 1s/step - loss: 36.7027 - sparse_categorical_accuracy: 0.2283
26/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:15 1s/step - loss: 36.6970 - sparse_categorical_accuracy: 0.2303
27/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:14 1s/step - loss: 36.6911 - sparse_categorical_accuracy: 0.2325
28/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:13 1s/step - loss: 36.6862 - sparse_categorical_accuracy: 0.2342
29/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:12 1s/step - loss: 36.6818 - sparse_categorical_accuracy: 0.2357
30/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:11 1s/step - loss: 36.6766 - sparse_categorical_accuracy: 0.2372
31/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:10 1s/step - loss: 36.6717 - sparse_categorical_accuracy: 0.2387
32/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:09 1s/step - loss: 36.6670 - sparse_categorical_accuracy: 0.2403
33/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:08 1s/step - loss: 36.6629 - sparse_categorical_accuracy: 0.2418
34/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:07 1s/step - loss: 36.6591 - sparse_categorical_accuracy: 0.2431
35/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:06 1s/step - loss: 36.6551 - sparse_categorical_accuracy: 0.2444
36/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:05 1s/step - loss: 36.6513 - sparse_categorical_accuracy: 0.2456
37/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:04 1s/step - loss: 36.6478 - sparse_categorical_accuracy: 0.2467
38/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:03 1s/step - loss: 36.6441 - sparse_categorical_accuracy: 0.2477
39/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:02 1s/step - loss: 36.6405 - sparse_categorical_accuracy: 0.2487
40/100 ━━━━━━━━[37m━━━━━━━━━━━━ 1:01 1s/step - loss: 36.6368 - sparse_categorical_accuracy: 0.2497
41/100 ━━━━━━━━[37m━━━━━━━━━━━━ 1:00 1s/step - loss: 36.6331 - sparse_categorical_accuracy: 0.2507
42/100 ━━━━━━━━[37m━━━━━━━━━━━━ 59s 1s/step - loss: 36.6330 - sparse_categorical_accuracy: 0.2515
43/100 ━━━━━━━━[37m━━━━━━━━━━━━ 58s 1s/step - loss: 36.6330 - sparse_categorical_accuracy: 0.2523
44/100 ━━━━━━━━[37m━━━━━━━━━━━━ 57s 1s/step - loss: 36.6331 - sparse_categorical_accuracy: 0.2531
45/100 ━━━━━━━━━[37m━━━━━━━━━━━ 56s 1s/step - loss: 36.6330 - sparse_categorical_accuracy: 0.2538
46/100 ━━━━━━━━━[37m━━━━━━━━━━━ 55s 1s/step - loss: 36.6330 - sparse_categorical_accuracy: 0.2546
47/100 ━━━━━━━━━[37m━━━━━━━━━━━ 54s 1s/step - loss: 36.6330 - sparse_categorical_accuracy: 0.2554
48/100 ━━━━━━━━━[37m━━━━━━━━━━━ 53s 1s/step - loss: 36.6330 - sparse_categorical_accuracy: 0.2561
49/100 ━━━━━━━━━[37m━━━━━━━━━━━ 52s 1s/step - loss: 36.6331 - sparse_categorical_accuracy: 0.2568
50/100 ━━━━━━━━━━[37m━━━━━━━━━━ 51s 1s/step - loss: 36.6331 - sparse_categorical_accuracy: 0.2575
51/100 ━━━━━━━━━━[37m━━━━━━━━━━ 50s 1s/step - loss: 36.6332 - sparse_categorical_accuracy: 0.2582
52/100 ━━━━━━━━━━[37m━━━━━━━━━━ 49s 1s/step - loss: 36.6332 - sparse_categorical_accuracy: 0.2588
53/100 ━━━━━━━━━━[37m━━━━━━━━━━ 48s 1s/step - loss: 36.6331 - sparse_categorical_accuracy: 0.2594
54/100 ━━━━━━━━━━[37m━━━━━━━━━━ 47s 1s/step - loss: 36.6330 - sparse_categorical_accuracy: 0.2600
55/100 ━━━━━━━━━━━[37m━━━━━━━━━ 46s 1s/step - loss: 36.6329 - sparse_categorical_accuracy: 0.2606
56/100 ━━━━━━━━━━━[37m━━━━━━━━━ 45s 1s/step - loss: 36.6331 - sparse_categorical_accuracy: 0.2612
57/100 ━━━━━━━━━━━[37m━━━━━━━━━ 44s 1s/step - loss: 36.6332 - sparse_categorical_accuracy: 0.2618
58/100 ━━━━━━━━━━━[37m━━━━━━━━━ 43s 1s/step - loss: 36.6332 - sparse_categorical_accuracy: 0.2624
59/100 ━━━━━━━━━━━[37m━━━━━━━━━ 42s 1s/step - loss: 36.6331 - sparse_categorical_accuracy: 0.2630
60/100 ━━━━━━━━━━━━[37m━━━━━━━━ 41s 1s/step - loss: 36.6331 - sparse_categorical_accuracy: 0.2636
61/100 ━━━━━━━━━━━━[37m━━━━━━━━ 40s 1s/step - loss: 36.6330 - sparse_categorical_accuracy: 0.2641
62/100 ━━━━━━━━━━━━[37m━━━━━━━━ 39s 1s/step - loss: 36.6330 - sparse_categorical_accuracy: 0.2646
63/100 ━━━━━━━━━━━━[37m━━━━━━━━ 38s 1s/step - loss: 36.6329 - sparse_categorical_accuracy: 0.2652
64/100 ━━━━━━━━━━━━[37m━━━━━━━━ 37s 1s/step - loss: 36.6329 - sparse_categorical_accuracy: 0.2657
65/100 ━━━━━━━━━━━━━[37m━━━━━━━ 36s 1s/step - loss: 36.6330 - sparse_categorical_accuracy: 0.2662
66/100 ━━━━━━━━━━━━━[37m━━━━━━━ 35s 1s/step - loss: 36.6332 - sparse_categorical_accuracy: 0.2667
67/100 ━━━━━━━━━━━━━[37m━━━━━━━ 34s 1s/step - loss: 36.6336 - sparse_categorical_accuracy: 0.2671
68/100 ━━━━━━━━━━━━━[37m━━━━━━━ 33s 1s/step - loss: 36.6340 - sparse_categorical_accuracy: 0.2674
69/100 ━━━━━━━━━━━━━[37m━━━━━━━ 32s 1s/step - loss: 36.6346 - sparse_categorical_accuracy: 0.2678
70/100 ━━━━━━━━━━━━━━[37m━━━━━━ 30s 1s/step - loss: 36.6352 - sparse_categorical_accuracy: 0.2682
71/100 ━━━━━━━━━━━━━━[37m━━━━━━ 29s 1s/step - loss: 36.6359 - sparse_categorical_accuracy: 0.2685
72/100 ━━━━━━━━━━━━━━[37m━━━━━━ 28s 1s/step - loss: 36.6365 - sparse_categorical_accuracy: 0.2688
73/100 ━━━━━━━━━━━━━━[37m━━━━━━ 27s 1s/step - loss: 36.6371 - sparse_categorical_accuracy: 0.2690
74/100 ━━━━━━━━━━━━━━[37m━━━━━━ 26s 1s/step - loss: 36.6377 - sparse_categorical_accuracy: 0.2693
75/100 ━━━━━━━━━━━━━━━[37m━━━━━ 25s 1s/step - loss: 36.6384 - sparse_categorical_accuracy: 0.2696
76/100 ━━━━━━━━━━━━━━━[37m━━━━━ 24s 1s/step - loss: 36.6389 - sparse_categorical_accuracy: 0.2698
77/100 ━━━━━━━━━━━━━━━[37m━━━━━ 23s 1s/step - loss: 36.6394 - sparse_categorical_accuracy: 0.2700
78/100 ━━━━━━━━━━━━━━━[37m━━━━━ 22s 1s/step - loss: 36.6398 - sparse_categorical_accuracy: 0.2703
79/100 ━━━━━━━━━━━━━━━[37m━━━━━ 21s 1s/step - loss: 36.6401 - sparse_categorical_accuracy: 0.2706
80/100 ━━━━━━━━━━━━━━━━[37m━━━━ 20s 1s/step - loss: 36.6406 - sparse_categorical_accuracy: 0.2708
81/100 ━━━━━━━━━━━━━━━━[37m━━━━ 19s 1s/step - loss: 36.6411 - sparse_categorical_accuracy: 0.2710
82/100 ━━━━━━━━━━━━━━━━[37m━━━━ 18s 1s/step - loss: 36.6415 - sparse_categorical_accuracy: 0.2712
83/100 ━━━━━━━━━━━━━━━━[37m━━━━ 17s 1s/step - loss: 36.6419 - sparse_categorical_accuracy: 0.2714
84/100 ━━━━━━━━━━━━━━━━[37m━━━━ 16s 1s/step - loss: 36.6423 - sparse_categorical_accuracy: 0.2716
85/100 ━━━━━━━━━━━━━━━━━[37m━━━ 15s 1s/step - loss: 36.6426 - sparse_categorical_accuracy: 0.2718
86/100 ━━━━━━━━━━━━━━━━━[37m━━━ 14s 1s/step - loss: 36.6429 - sparse_categorical_accuracy: 0.2720
87/100 ━━━━━━━━━━━━━━━━━[37m━━━ 13s 1s/step - loss: 36.6431 - sparse_categorical_accuracy: 0.2723
88/100 ━━━━━━━━━━━━━━━━━[37m━━━ 12s 1s/step - loss: 36.6432 - sparse_categorical_accuracy: 0.2725
89/100 ━━━━━━━━━━━━━━━━━[37m━━━ 11s 1s/step - loss: 36.6433 - sparse_categorical_accuracy: 0.2727
90/100 ━━━━━━━━━━━━━━━━━━[37m━━ 10s 1s/step - loss: 36.6434 - sparse_categorical_accuracy: 0.2730
91/100 ━━━━━━━━━━━━━━━━━━[37m━━ 9s 1s/step - loss: 36.6435 - sparse_categorical_accuracy: 0.2732
92/100 ━━━━━━━━━━━━━━━━━━[37m━━ 8s 1s/step - loss: 36.6435 - sparse_categorical_accuracy: 0.2734
93/100 ━━━━━━━━━━━━━━━━━━[37m━━ 7s 1s/step - loss: 36.6434 - sparse_categorical_accuracy: 0.2736
94/100 ━━━━━━━━━━━━━━━━━━[37m━━ 6s 1s/step - loss: 36.6432 - sparse_categorical_accuracy: 0.2738
95/100 ━━━━━━━━━━━━━━━━━━━[37m━ 5s 1s/step - loss: 36.6430 - sparse_categorical_accuracy: 0.2740
96/100 ━━━━━━━━━━━━━━━━━━━[37m━ 4s 1s/step - loss: 36.6427 - sparse_categorical_accuracy: 0.2742
97/100 ━━━━━━━━━━━━━━━━━━━[37m━ 3s 1s/step - loss: 36.6424 - sparse_categorical_accuracy: 0.2744
98/100 ━━━━━━━━━━━━━━━━━━━[37m━ 2s 1s/step - loss: 36.6421 - sparse_categorical_accuracy: 0.2746
99/100 ━━━━━━━━━━━━━━━━━━━[37m━ 1s 1s/step - loss: 36.6418 - sparse_categorical_accuracy: 0.2748
100/100 ━━━━━━━━━━━━━━━━━━━━ 0s 1s/step - loss: 36.6402 - sparse_categorical_accuracy: 0.2749
100/100 ━━━━━━━━━━━━━━━━━━━━ 108s 1s/step - loss: 36.6386 - sparse_categorical_accuracy: 0.2751 - val_loss: 20961250112658389073920.0000 - val_sparse_categorical_accuracy: 0.3191
Epoch 3/20
1/100 [37m━━━━━━━━━━━━━━━━━━━━ 57:33 35s/step - loss: 35.9745 - sparse_categorical_accuracy: 0.3438
2/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:39 1s/step - loss: 36.1432 - sparse_categorical_accuracy: 0.3359
3/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:38 1s/step - loss: 36.1628 - sparse_categorical_accuracy: 0.3420
4/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:39 1s/step - loss: 36.1912 - sparse_categorical_accuracy: 0.3424
5/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:38 1s/step - loss: 36.2222 - sparse_categorical_accuracy: 0.3390
6/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:37 1s/step - loss: 36.2318 - sparse_categorical_accuracy: 0.3345
7/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:36 1s/step - loss: 36.2484 - sparse_categorical_accuracy: 0.3301
8/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:35 1s/step - loss: 36.2639 - sparse_categorical_accuracy: 0.3284
9/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:33 1s/step - loss: 36.2697 - sparse_categorical_accuracy: 0.3282
10/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:33 1s/step - loss: 36.2697 - sparse_categorical_accuracy: 0.3304
11/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:32 1s/step - loss: 36.2697 - sparse_categorical_accuracy: 0.3316
12/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:30 1s/step - loss: 36.2714 - sparse_categorical_accuracy: 0.3319
13/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:29 1s/step - loss: 36.2731 - sparse_categorical_accuracy: 0.3319
14/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:28 1s/step - loss: 36.2716 - sparse_categorical_accuracy: 0.3325
15/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:27 1s/step - loss: 36.2714 - sparse_categorical_accuracy: 0.3327
16/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:26 1s/step - loss: 36.2703 - sparse_categorical_accuracy: 0.3325
17/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:25 1s/step - loss: 36.2685 - sparse_categorical_accuracy: 0.3322
18/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:24 1s/step - loss: 36.2665 - sparse_categorical_accuracy: 0.3322
19/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:23 1s/step - loss: 36.2672 - sparse_categorical_accuracy: 0.3320
20/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:22 1s/step - loss: 36.2689 - sparse_categorical_accuracy: 0.3316
21/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:22 1s/step - loss: 36.2700 - sparse_categorical_accuracy: 0.3311
22/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:21 1s/step - loss: 36.2712 - sparse_categorical_accuracy: 0.3307
23/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:20 1s/step - loss: 36.2732 - sparse_categorical_accuracy: 0.3301
24/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:19 1s/step - loss: 36.2753 - sparse_categorical_accuracy: 0.3293
25/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:18 1s/step - loss: 36.2772 - sparse_categorical_accuracy: 0.3284
26/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:16 1s/step - loss: 36.2789 - sparse_categorical_accuracy: 0.3275
27/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:15 1s/step - loss: 36.2803 - sparse_categorical_accuracy: 0.3266
28/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:14 1s/step - loss: 36.2832 - sparse_categorical_accuracy: 0.3258
29/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:13 1s/step - loss: 36.2886 - sparse_categorical_accuracy: 0.3251
30/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:12 1s/step - loss: 36.2944 - sparse_categorical_accuracy: 0.3245
31/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:11 1s/step - loss: 36.3001 - sparse_categorical_accuracy: 0.3237
32/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:10 1s/step - loss: 36.3053 - sparse_categorical_accuracy: 0.3231
33/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:09 1s/step - loss: 36.3102 - sparse_categorical_accuracy: 0.3226
34/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:08 1s/step - loss: 36.3150 - sparse_categorical_accuracy: 0.3221
35/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:07 1s/step - loss: 36.3196 - sparse_categorical_accuracy: 0.3216
36/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:06 1s/step - loss: 36.3239 - sparse_categorical_accuracy: 0.3212
37/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:05 1s/step - loss: 36.3281 - sparse_categorical_accuracy: 0.3209
38/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:04 1s/step - loss: 36.3322 - sparse_categorical_accuracy: 0.3204
39/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:03 1s/step - loss: 36.3358 - sparse_categorical_accuracy: 0.3201
40/100 ━━━━━━━━[37m━━━━━━━━━━━━ 1:02 1s/step - loss: 36.3392 - sparse_categorical_accuracy: 0.3199
41/100 ━━━━━━━━[37m━━━━━━━━━━━━ 1:01 1s/step - loss: 36.3423 - sparse_categorical_accuracy: 0.3196
42/100 ━━━━━━━━[37m━━━━━━━━━━━━ 1:00 1s/step - loss: 36.3453 - sparse_categorical_accuracy: 0.3195
43/100 ━━━━━━━━[37m━━━━━━━━━━━━ 58s 1s/step - loss: 36.3482 - sparse_categorical_accuracy: 0.3193
44/100 ━━━━━━━━[37m━━━━━━━━━━━━ 57s 1s/step - loss: 36.3509 - sparse_categorical_accuracy: 0.3193
45/100 ━━━━━━━━━[37m━━━━━━━━━━━ 56s 1s/step - loss: 36.3534 - sparse_categorical_accuracy: 0.3192
46/100 ━━━━━━━━━[37m━━━━━━━━━━━ 55s 1s/step - loss: 36.3557 - sparse_categorical_accuracy: 0.3191
47/100 ━━━━━━━━━[37m━━━━━━━━━━━ 54s 1s/step - loss: 36.3577 - sparse_categorical_accuracy: 0.3191
48/100 ━━━━━━━━━[37m━━━━━━━━━━━ 53s 1s/step - loss: 36.3597 - sparse_categorical_accuracy: 0.3190
49/100 ━━━━━━━━━[37m━━━━━━━━━━━ 52s 1s/step - loss: 36.3617 - sparse_categorical_accuracy: 0.3188
50/100 ━━━━━━━━━━[37m━━━━━━━━━━ 51s 1s/step - loss: 36.3636 - sparse_categorical_accuracy: 0.3186
51/100 ━━━━━━━━━━[37m━━━━━━━━━━ 50s 1s/step - loss: 36.3654 - sparse_categorical_accuracy: 0.3183
52/100 ━━━━━━━━━━[37m━━━━━━━━━━ 49s 1s/step - loss: 36.3671 - sparse_categorical_accuracy: 0.3181
53/100 ━━━━━━━━━━[37m━━━━━━━━━━ 48s 1s/step - loss: 36.3687 - sparse_categorical_accuracy: 0.3179
54/100 ━━━━━━━━━━[37m━━━━━━━━━━ 47s 1s/step - loss: 36.3705 - sparse_categorical_accuracy: 0.3177
55/100 ━━━━━━━━━━━[37m━━━━━━━━━ 46s 1s/step - loss: 36.3723 - sparse_categorical_accuracy: 0.3175
56/100 ━━━━━━━━━━━[37m━━━━━━━━━ 45s 1s/step - loss: 36.3744 - sparse_categorical_accuracy: 0.3173
57/100 ━━━━━━━━━━━[37m━━━━━━━━━ 44s 1s/step - loss: 36.3764 - sparse_categorical_accuracy: 0.3171
58/100 ━━━━━━━━━━━[37m━━━━━━━━━ 43s 1s/step - loss: 36.3784 - sparse_categorical_accuracy: 0.3170
59/100 ━━━━━━━━━━━[37m━━━━━━━━━ 42s 1s/step - loss: 36.3805 - sparse_categorical_accuracy: 0.3168
60/100 ━━━━━━━━━━━━[37m━━━━━━━━ 41s 1s/step - loss: 36.3824 - sparse_categorical_accuracy: 0.3167
61/100 ━━━━━━━━━━━━[37m━━━━━━━━ 40s 1s/step - loss: 36.3843 - sparse_categorical_accuracy: 0.3166
62/100 ━━━━━━━━━━━━[37m━━━━━━━━ 39s 1s/step - loss: 36.3862 - sparse_categorical_accuracy: 0.3165
63/100 ━━━━━━━━━━━━[37m━━━━━━━━ 38s 1s/step - loss: 36.3879 - sparse_categorical_accuracy: 0.3164
64/100 ━━━━━━━━━━━━[37m━━━━━━━━ 37s 1s/step - loss: 36.3893 - sparse_categorical_accuracy: 0.3163
65/100 ━━━━━━━━━━━━━[37m━━━━━━━ 36s 1s/step - loss: 36.3907 - sparse_categorical_accuracy: 0.3163
66/100 ━━━━━━━━━━━━━[37m━━━━━━━ 35s 1s/step - loss: 36.3921 - sparse_categorical_accuracy: 0.3162
67/100 ━━━━━━━━━━━━━[37m━━━━━━━ 34s 1s/step - loss: 36.3933 - sparse_categorical_accuracy: 0.3162
68/100 ━━━━━━━━━━━━━[37m━━━━━━━ 33s 1s/step - loss: 36.3944 - sparse_categorical_accuracy: 0.3161
69/100 ━━━━━━━━━━━━━[37m━━━━━━━ 32s 1s/step - loss: 36.3953 - sparse_categorical_accuracy: 0.3161
70/100 ━━━━━━━━━━━━━━[37m━━━━━━ 31s 1s/step - loss: 36.3962 - sparse_categorical_accuracy: 0.3160
71/100 ━━━━━━━━━━━━━━[37m━━━━━━ 30s 1s/step - loss: 36.3971 - sparse_categorical_accuracy: 0.3160
72/100 ━━━━━━━━━━━━━━[37m━━━━━━ 29s 1s/step - loss: 36.3978 - sparse_categorical_accuracy: 0.3159
73/100 ━━━━━━━━━━━━━━[37m━━━━━━ 27s 1s/step - loss: 36.3986 - sparse_categorical_accuracy: 0.3159
74/100 ━━━━━━━━━━━━━━[37m━━━━━━ 26s 1s/step - loss: 36.3994 - sparse_categorical_accuracy: 0.3158
75/100 ━━━━━━━━━━━━━━━[37m━━━━━ 25s 1s/step - loss: 36.4003 - sparse_categorical_accuracy: 0.3157
76/100 ━━━━━━━━━━━━━━━[37m━━━━━ 24s 1s/step - loss: 36.4011 - sparse_categorical_accuracy: 0.3157
77/100 ━━━━━━━━━━━━━━━[37m━━━━━ 23s 1s/step - loss: 36.4019 - sparse_categorical_accuracy: 0.3156
78/100 ━━━━━━━━━━━━━━━[37m━━━━━ 22s 1s/step - loss: 36.4026 - sparse_categorical_accuracy: 0.3156
79/100 ━━━━━━━━━━━━━━━[37m━━━━━ 21s 1s/step - loss: 36.4032 - sparse_categorical_accuracy: 0.3155
80/100 ━━━━━━━━━━━━━━━━[37m━━━━ 20s 1s/step - loss: 36.4038 - sparse_categorical_accuracy: 0.3155
81/100 ━━━━━━━━━━━━━━━━[37m━━━━ 19s 1s/step - loss: 36.4045 - sparse_categorical_accuracy: 0.3155
82/100 ━━━━━━━━━━━━━━━━[37m━━━━ 18s 1s/step - loss: 36.4051 - sparse_categorical_accuracy: 0.3154
83/100 ━━━━━━━━━━━━━━━━[37m━━━━ 17s 1s/step - loss: 36.4058 - sparse_categorical_accuracy: 0.3154
84/100 ━━━━━━━━━━━━━━━━[37m━━━━ 16s 1s/step - loss: 36.4066 - sparse_categorical_accuracy: 0.3154
85/100 ━━━━━━━━━━━━━━━━━[37m━━━ 15s 1s/step - loss: 36.4072 - sparse_categorical_accuracy: 0.3154
86/100 ━━━━━━━━━━━━━━━━━[37m━━━ 14s 1s/step - loss: 36.4079 - sparse_categorical_accuracy: 0.3154
87/100 ━━━━━━━━━━━━━━━━━[37m━━━ 13s 1s/step - loss: 36.4085 - sparse_categorical_accuracy: 0.3154
88/100 ━━━━━━━━━━━━━━━━━[37m━━━ 12s 1s/step - loss: 36.4091 - sparse_categorical_accuracy: 0.3154
89/100 ━━━━━━━━━━━━━━━━━[37m━━━ 11s 1s/step - loss: 36.4097 - sparse_categorical_accuracy: 0.3154
90/100 ━━━━━━━━━━━━━━━━━━[37m━━ 10s 1s/step - loss: 36.4104 - sparse_categorical_accuracy: 0.3154
91/100 ━━━━━━━━━━━━━━━━━━[37m━━ 9s 1s/step - loss: 36.4110 - sparse_categorical_accuracy: 0.3154
92/100 ━━━━━━━━━━━━━━━━━━[37m━━ 8s 1s/step - loss: 36.4117 - sparse_categorical_accuracy: 0.3153
93/100 ━━━━━━━━━━━━━━━━━━[37m━━ 7s 1s/step - loss: 36.4123 - sparse_categorical_accuracy: 0.3153
94/100 ━━━━━━━━━━━━━━━━━━[37m━━ 6s 1s/step - loss: 36.4129 - sparse_categorical_accuracy: 0.3152
95/100 ━━━━━━━━━━━━━━━━━━━[37m━ 5s 1s/step - loss: 36.4135 - sparse_categorical_accuracy: 0.3152
96/100 ━━━━━━━━━━━━━━━━━━━[37m━ 4s 1s/step - loss: 36.4142 - sparse_categorical_accuracy: 0.3152
97/100 ━━━━━━━━━━━━━━━━━━━[37m━ 3s 1s/step - loss: 36.4150 - sparse_categorical_accuracy: 0.3151
98/100 ━━━━━━━━━━━━━━━━━━━[37m━ 2s 1s/step - loss: 36.4157 - sparse_categorical_accuracy: 0.3151
99/100 ━━━━━━━━━━━━━━━━━━━[37m━ 1s 1s/step - loss: 36.4164 - sparse_categorical_accuracy: 0.3151
100/100 ━━━━━━━━━━━━━━━━━━━━ 0s 1s/step - loss: 36.4156 - sparse_categorical_accuracy: 0.3150
100/100 ━━━━━━━━━━━━━━━━━━━━ 142s 1s/step - loss: 36.4148 - sparse_categorical_accuracy: 0.3150 - val_loss: 14661139300352.0000 - val_sparse_categorical_accuracy: 0.2240
Epoch 4/20
1/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:40 1s/step - loss: 36.7380 - sparse_categorical_accuracy: 0.5312
2/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:40 1s/step - loss: 36.7969 - sparse_categorical_accuracy: 0.4844
3/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:38 1s/step - loss: 36.7860 - sparse_categorical_accuracy: 0.4653
4/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:36 1s/step - loss: 36.7852 - sparse_categorical_accuracy: 0.4447
5/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:35 1s/step - loss: 36.7560 - sparse_categorical_accuracy: 0.4370
6/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:35 1s/step - loss: 36.7412 - sparse_categorical_accuracy: 0.4293
7/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:34 1s/step - loss: 36.7300 - sparse_categorical_accuracy: 0.4221
8/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:33 1s/step - loss: 36.7233 - sparse_categorical_accuracy: 0.4148
9/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:32 1s/step - loss: 36.7190 - sparse_categorical_accuracy: 0.4073
10/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:31 1s/step - loss: 36.7201 - sparse_categorical_accuracy: 0.3990
11/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:30 1s/step - loss: 36.7176 - sparse_categorical_accuracy: 0.3925
12/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:30 1s/step - loss: 36.7097 - sparse_categorical_accuracy: 0.3882
13/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:29 1s/step - loss: 36.7017 - sparse_categorical_accuracy: 0.3850
14/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:28 1s/step - loss: 36.6936 - sparse_categorical_accuracy: 0.3819
15/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:27 1s/step - loss: 36.6858 - sparse_categorical_accuracy: 0.3786
16/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:26 1s/step - loss: 36.6785 - sparse_categorical_accuracy: 0.3752
17/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:26 1s/step - loss: 36.6711 - sparse_categorical_accuracy: 0.3723
18/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:24 1s/step - loss: 36.6637 - sparse_categorical_accuracy: 0.3695
19/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:23 1s/step - loss: 36.6692 - sparse_categorical_accuracy: 0.3668
20/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:22 1s/step - loss: 36.6728 - sparse_categorical_accuracy: 0.3647
21/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:21 1s/step - loss: 36.6748 - sparse_categorical_accuracy: 0.3631
22/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:20 1s/step - loss: 36.6766 - sparse_categorical_accuracy: 0.3616
23/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:19 1s/step - loss: 36.6783 - sparse_categorical_accuracy: 0.3601
24/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:18 1s/step - loss: 36.6799 - sparse_categorical_accuracy: 0.3588
25/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:17 1s/step - loss: 36.6818 - sparse_categorical_accuracy: 0.3576
26/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:16 1s/step - loss: 36.6836 - sparse_categorical_accuracy: 0.3565
27/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:15 1s/step - loss: 36.6852 - sparse_categorical_accuracy: 0.3555
28/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:14 1s/step - loss: 36.6879 - sparse_categorical_accuracy: 0.3545
29/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:13 1s/step - loss: 36.6908 - sparse_categorical_accuracy: 0.3535
30/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:12 1s/step - loss: 36.6939 - sparse_categorical_accuracy: 0.3525
31/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:11 1s/step - loss: 36.6971 - sparse_categorical_accuracy: 0.3515
32/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:10 1s/step - loss: 36.7002 - sparse_categorical_accuracy: 0.3506
33/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:09 1s/step - loss: 36.7032 - sparse_categorical_accuracy: 0.3498
34/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:08 1s/step - loss: 36.7059 - sparse_categorical_accuracy: 0.3492
35/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:07 1s/step - loss: 36.7085 - sparse_categorical_accuracy: 0.3487
36/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:06 1s/step - loss: 36.7110 - sparse_categorical_accuracy: 0.3481
37/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:05 1s/step - loss: 36.7138 - sparse_categorical_accuracy: 0.3476
38/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:04 1s/step - loss: 36.7167 - sparse_categorical_accuracy: 0.3472
39/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:03 1s/step - loss: 36.7196 - sparse_categorical_accuracy: 0.3468
40/100 ━━━━━━━━[37m━━━━━━━━━━━━ 1:02 1s/step - loss: 36.7225 - sparse_categorical_accuracy: 0.3463
41/100 ━━━━━━━━[37m━━━━━━━━━━━━ 1:01 1s/step - loss: 36.7254 - sparse_categorical_accuracy: 0.3459
42/100 ━━━━━━━━[37m━━━━━━━━━━━━ 1:00 1s/step - loss: 36.7283 - sparse_categorical_accuracy: 0.3455
43/100 ━━━━━━━━[37m━━━━━━━━━━━━ 59s 1s/step - loss: 36.7311 - sparse_categorical_accuracy: 0.3450
44/100 ━━━━━━━━[37m━━━━━━━━━━━━ 58s 1s/step - loss: 36.7339 - sparse_categorical_accuracy: 0.3446
45/100 ━━━━━━━━━[37m━━━━━━━━━━━ 57s 1s/step - loss: 36.7364 - sparse_categorical_accuracy: 0.3441
46/100 ━━━━━━━━━[37m━━━━━━━━━━━ 56s 1s/step - loss: 36.7387 - sparse_categorical_accuracy: 0.3437
47/100 ━━━━━━━━━[37m━━━━━━━━━━━ 55s 1s/step - loss: 36.7410 - sparse_categorical_accuracy: 0.3432
48/100 ━━━━━━━━━[37m━━━━━━━━━━━ 54s 1s/step - loss: 36.7433 - sparse_categorical_accuracy: 0.3428
49/100 ━━━━━━━━━[37m━━━━━━━━━━━ 53s 1s/step - loss: 36.7454 - sparse_categorical_accuracy: 0.3424
50/100 ━━━━━━━━━━[37m━━━━━━━━━━ 51s 1s/step - loss: 36.7475 - sparse_categorical_accuracy: 0.3420
51/100 ━━━━━━━━━━[37m━━━━━━━━━━ 50s 1s/step - loss: 36.7496 - sparse_categorical_accuracy: 0.3416
52/100 ━━━━━━━━━━[37m━━━━━━━━━━ 49s 1s/step - loss: 36.7515 - sparse_categorical_accuracy: 0.3413
53/100 ━━━━━━━━━━[37m━━━━━━━━━━ 48s 1s/step - loss: 36.7532 - sparse_categorical_accuracy: 0.3410
54/100 ━━━━━━━━━━[37m━━━━━━━━━━ 47s 1s/step - loss: 36.7547 - sparse_categorical_accuracy: 0.3407
55/100 ━━━━━━━━━━━[37m━━━━━━━━━ 46s 1s/step - loss: 36.7561 - sparse_categorical_accuracy: 0.3404
56/100 ━━━━━━━━━━━[37m━━━━━━━━━ 45s 1s/step - loss: 36.7575 - sparse_categorical_accuracy: 0.3401
57/100 ━━━━━━━━━━━[37m━━━━━━━━━ 44s 1s/step - loss: 36.7590 - sparse_categorical_accuracy: 0.3398
58/100 ━━━━━━━━━━━[37m━━━━━━━━━ 43s 1s/step - loss: 36.7603 - sparse_categorical_accuracy: 0.3396
59/100 ━━━━━━━━━━━[37m━━━━━━━━━ 42s 1s/step - loss: 36.7617 - sparse_categorical_accuracy: 0.3393
60/100 ━━━━━━━━━━━━[37m━━━━━━━━ 41s 1s/step - loss: 36.7629 - sparse_categorical_accuracy: 0.3390
61/100 ━━━━━━━━━━━━[37m━━━━━━━━ 40s 1s/step - loss: 36.7641 - sparse_categorical_accuracy: 0.3387
62/100 ━━━━━━━━━━━━[37m━━━━━━━━ 39s 1s/step - loss: 36.7653 - sparse_categorical_accuracy: 0.3383
63/100 ━━━━━━━━━━━━[37m━━━━━━━━ 38s 1s/step - loss: 36.7665 - sparse_categorical_accuracy: 0.3380
64/100 ━━━━━━━━━━━━[37m━━━━━━━━ 37s 1s/step - loss: 36.7676 - sparse_categorical_accuracy: 0.3376
65/100 ━━━━━━━━━━━━━[37m━━━━━━━ 36s 1s/step - loss: 36.7687 - sparse_categorical_accuracy: 0.3373
66/100 ━━━━━━━━━━━━━[37m━━━━━━━ 35s 1s/step - loss: 36.7696 - sparse_categorical_accuracy: 0.3369
67/100 ━━━━━━━━━━━━━[37m━━━━━━━ 34s 1s/step - loss: 36.7705 - sparse_categorical_accuracy: 0.3366
68/100 ━━━━━━━━━━━━━[37m━━━━━━━ 33s 1s/step - loss: 36.7713 - sparse_categorical_accuracy: 0.3363
69/100 ━━━━━━━━━━━━━[37m━━━━━━━ 32s 1s/step - loss: 36.7720 - sparse_categorical_accuracy: 0.3360
70/100 ━━━━━━━━━━━━━━[37m━━━━━━ 31s 1s/step - loss: 36.7725 - sparse_categorical_accuracy: 0.3357
71/100 ━━━━━━━━━━━━━━[37m━━━━━━ 30s 1s/step - loss: 36.7730 - sparse_categorical_accuracy: 0.3354
72/100 ━━━━━━━━━━━━━━[37m━━━━━━ 29s 1s/step - loss: 36.7734 - sparse_categorical_accuracy: 0.3352
73/100 ━━━━━━━━━━━━━━[37m━━━━━━ 28s 1s/step - loss: 36.7736 - sparse_categorical_accuracy: 0.3350
74/100 ━━━━━━━━━━━━━━[37m━━━━━━ 27s 1s/step - loss: 36.7739 - sparse_categorical_accuracy: 0.3348
75/100 ━━━━━━━━━━━━━━━[37m━━━━━ 26s 1s/step - loss: 36.7742 - sparse_categorical_accuracy: 0.3345
76/100 ━━━━━━━━━━━━━━━[37m━━━━━ 25s 1s/step - loss: 36.7744 - sparse_categorical_accuracy: 0.3343
77/100 ━━━━━━━━━━━━━━━[37m━━━━━ 24s 1s/step - loss: 36.7746 - sparse_categorical_accuracy: 0.3340
78/100 ━━━━━━━━━━━━━━━[37m━━━━━ 23s 1s/step - loss: 36.7747 - sparse_categorical_accuracy: 0.3338
79/100 ━━━━━━━━━━━━━━━[37m━━━━━ 22s 1s/step - loss: 36.7747 - sparse_categorical_accuracy: 0.3335
80/100 ━━━━━━━━━━━━━━━━[37m━━━━ 20s 1s/step - loss: 36.7747 - sparse_categorical_accuracy: 0.3333
81/100 ━━━━━━━━━━━━━━━━[37m━━━━ 19s 1s/step - loss: 36.7746 - sparse_categorical_accuracy: 0.3330
82/100 ━━━━━━━━━━━━━━━━[37m━━━━ 18s 1s/step - loss: 36.7745 - sparse_categorical_accuracy: 0.3328
83/100 ━━━━━━━━━━━━━━━━[37m━━━━ 17s 1s/step - loss: 36.7743 - sparse_categorical_accuracy: 0.3325
84/100 ━━━━━━━━━━━━━━━━[37m━━━━ 16s 1s/step - loss: 36.7741 - sparse_categorical_accuracy: 0.3322
85/100 ━━━━━━━━━━━━━━━━━[37m━━━ 15s 1s/step - loss: 36.7739 - sparse_categorical_accuracy: 0.3320
86/100 ━━━━━━━━━━━━━━━━━[37m━━━ 14s 1s/step - loss: 36.7737 - sparse_categorical_accuracy: 0.3317
87/100 ━━━━━━━━━━━━━━━━━[37m━━━ 13s 1s/step - loss: 36.7735 - sparse_categorical_accuracy: 0.3315
88/100 ━━━━━━━━━━━━━━━━━[37m━━━ 12s 1s/step - loss: 36.7732 - sparse_categorical_accuracy: 0.3312
89/100 ━━━━━━━━━━━━━━━━━[37m━━━ 11s 1s/step - loss: 36.7729 - sparse_categorical_accuracy: 0.3310
90/100 ━━━━━━━━━━━━━━━━━━[37m━━ 10s 1s/step - loss: 36.7727 - sparse_categorical_accuracy: 0.3307
91/100 ━━━━━━━━━━━━━━━━━━[37m━━ 9s 1s/step - loss: 36.7724 - sparse_categorical_accuracy: 0.3305
92/100 ━━━━━━━━━━━━━━━━━━[37m━━ 8s 1s/step - loss: 36.7721 - sparse_categorical_accuracy: 0.3303
93/100 ━━━━━━━━━━━━━━━━━━[37m━━ 7s 1s/step - loss: 36.7718 - sparse_categorical_accuracy: 0.3300
94/100 ━━━━━━━━━━━━━━━━━━[37m━━ 6s 1s/step - loss: 36.7714 - sparse_categorical_accuracy: 0.3298
95/100 ━━━━━━━━━━━━━━━━━━━[37m━ 5s 1s/step - loss: 36.7711 - sparse_categorical_accuracy: 0.3296
96/100 ━━━━━━━━━━━━━━━━━━━[37m━ 4s 1s/step - loss: 36.7707 - sparse_categorical_accuracy: 0.3294
97/100 ━━━━━━━━━━━━━━━━━━━[37m━ 3s 1s/step - loss: 36.7704 - sparse_categorical_accuracy: 0.3293
98/100 ━━━━━━━━━━━━━━━━━━━[37m━ 2s 1s/step - loss: 36.7701 - sparse_categorical_accuracy: 0.3291
99/100 ━━━━━━━━━━━━━━━━━━━[37m━ 1s 1s/step - loss: 36.7697 - sparse_categorical_accuracy: 0.3289
100/100 ━━━━━━━━━━━━━━━━━━━━ 0s 1s/step - loss: 36.7677 - sparse_categorical_accuracy: 0.3288
100/100 ━━━━━━━━━━━━━━━━━━━━ 110s 1s/step - loss: 36.7658 - sparse_categorical_accuracy: 0.3286 - val_loss: 2640681721921536.0000 - val_sparse_categorical_accuracy: 0.3542
Epoch 5/20
1/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:43 1s/step - loss: 36.6004 - sparse_categorical_accuracy: 0.2188
2/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:42 1s/step - loss: 36.5184 - sparse_categorical_accuracy: 0.2734
3/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:43 1s/step - loss: 36.4827 - sparse_categorical_accuracy: 0.2969
4/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:42 1s/step - loss: 36.4396 - sparse_categorical_accuracy: 0.3086
5/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:42 1s/step - loss: 36.4243 - sparse_categorical_accuracy: 0.3131
6/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:40 1s/step - loss: 36.4060 - sparse_categorical_accuracy: 0.3165
7/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:38 1s/step - loss: 36.4471 - sparse_categorical_accuracy: 0.3178
8/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:37 1s/step - loss: 36.4807 - sparse_categorical_accuracy: 0.3177
9/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:36 1s/step - loss: 36.5028 - sparse_categorical_accuracy: 0.3163
10/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:35 1s/step - loss: 36.5155 - sparse_categorical_accuracy: 0.3162
11/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:34 1s/step - loss: 36.5232 - sparse_categorical_accuracy: 0.3151
12/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:33 1s/step - loss: 36.5263 - sparse_categorical_accuracy: 0.3147
13/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:32 1s/step - loss: 36.5277 - sparse_categorical_accuracy: 0.3145
14/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:32 1s/step - loss: 36.5289 - sparse_categorical_accuracy: 0.3139
15/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:31 1s/step - loss: 36.5328 - sparse_categorical_accuracy: 0.3130
16/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:30 1s/step - loss: 36.5365 - sparse_categorical_accuracy: 0.3120
17/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:29 1s/step - loss: 36.5411 - sparse_categorical_accuracy: 0.3116
18/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:28 1s/step - loss: 36.5457 - sparse_categorical_accuracy: 0.3119
19/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:27 1s/step - loss: 36.5504 - sparse_categorical_accuracy: 0.3127
20/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:26 1s/step - loss: 36.5570 - sparse_categorical_accuracy: 0.3130
21/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:25 1s/step - loss: 36.5644 - sparse_categorical_accuracy: 0.3134
22/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:23 1s/step - loss: 36.5724 - sparse_categorical_accuracy: 0.3134
23/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:22 1s/step - loss: 36.5828 - sparse_categorical_accuracy: 0.3136
24/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:21 1s/step - loss: 36.6011 - sparse_categorical_accuracy: 0.3138
25/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:20 1s/step - loss: 36.6181 - sparse_categorical_accuracy: 0.3137
26/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:19 1s/step - loss: 36.6334 - sparse_categorical_accuracy: 0.3140
27/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:18 1s/step - loss: 36.6477 - sparse_categorical_accuracy: 0.3142
28/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:17 1s/step - loss: 36.6605 - sparse_categorical_accuracy: 0.3147
29/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:16 1s/step - loss: 36.6723 - sparse_categorical_accuracy: 0.3149
30/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:15 1s/step - loss: 36.6831 - sparse_categorical_accuracy: 0.3153
31/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:14 1s/step - loss: 36.6929 - sparse_categorical_accuracy: 0.3157
32/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:13 1s/step - loss: 36.7023 - sparse_categorical_accuracy: 0.3160
33/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:12 1s/step - loss: 36.7110 - sparse_categorical_accuracy: 0.3161
34/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:11 1s/step - loss: 36.7188 - sparse_categorical_accuracy: 0.3161
35/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:10 1s/step - loss: 36.7264 - sparse_categorical_accuracy: 0.3161
36/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:09 1s/step - loss: 36.7333 - sparse_categorical_accuracy: 0.3160
37/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:08 1s/step - loss: 36.7404 - sparse_categorical_accuracy: 0.3160
38/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:07 1s/step - loss: 36.7483 - sparse_categorical_accuracy: 0.3158
39/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:06 1s/step - loss: 36.7558 - sparse_categorical_accuracy: 0.3156
40/100 ━━━━━━━━[37m━━━━━━━━━━━━ 1:05 1s/step - loss: 36.7629 - sparse_categorical_accuracy: 0.3155
41/100 ━━━━━━━━[37m━━━━━━━━━━━━ 1:04 1s/step - loss: 36.7698 - sparse_categorical_accuracy: 0.3153
42/100 ━━━━━━━━[37m━━━━━━━━━━━━ 1:03 1s/step - loss: 36.7760 - sparse_categorical_accuracy: 0.3151
43/100 ━━━━━━━━[37m━━━━━━━━━━━━ 1:01 1s/step - loss: 36.7818 - sparse_categorical_accuracy: 0.3150
44/100 ━━━━━━━━[37m━━━━━━━━━━━━ 1:00 1s/step - loss: 36.7870 - sparse_categorical_accuracy: 0.3149
45/100 ━━━━━━━━━[37m━━━━━━━━━━━ 59s 1s/step - loss: 36.7922 - sparse_categorical_accuracy: 0.3147
46/100 ━━━━━━━━━[37m━━━━━━━━━━━ 58s 1s/step - loss: 36.7971 - sparse_categorical_accuracy: 0.3145
47/100 ━━━━━━━━━[37m━━━━━━━━━━━ 57s 1s/step - loss: 36.8016 - sparse_categorical_accuracy: 0.3144
48/100 ━━━━━━━━━[37m━━━━━━━━━━━ 56s 1s/step - loss: 36.8057 - sparse_categorical_accuracy: 0.3143
49/100 ━━━━━━━━━[37m━━━━━━━━━━━ 55s 1s/step - loss: 36.8098 - sparse_categorical_accuracy: 0.3142
50/100 ━━━━━━━━━━[37m━━━━━━━━━━ 54s 1s/step - loss: 36.8136 - sparse_categorical_accuracy: 0.3141
51/100 ━━━━━━━━━━[37m━━━━━━━━━━ 53s 1s/step - loss: 36.8172 - sparse_categorical_accuracy: 0.3141
52/100 ━━━━━━━━━━[37m━━━━━━━━━━ 52s 1s/step - loss: 36.8203 - sparse_categorical_accuracy: 0.3141
53/100 ━━━━━━━━━━[37m━━━━━━━━━━ 50s 1s/step - loss: 36.8234 - sparse_categorical_accuracy: 0.3141
54/100 ━━━━━━━━━━[37m━━━━━━━━━━ 49s 1s/step - loss: 36.8262 - sparse_categorical_accuracy: 0.3141
55/100 ━━━━━━━━━━━[37m━━━━━━━━━ 48s 1s/step - loss: 36.8288 - sparse_categorical_accuracy: 0.3140
56/100 ━━━━━━━━━━━[37m━━━━━━━━━ 47s 1s/step - loss: 36.8313 - sparse_categorical_accuracy: 0.3140
57/100 ━━━━━━━━━━━[37m━━━━━━━━━ 46s 1s/step - loss: 36.8338 - sparse_categorical_accuracy: 0.3139
58/100 ━━━━━━━━━━━[37m━━━━━━━━━ 45s 1s/step - loss: 36.8362 - sparse_categorical_accuracy: 0.3139
59/100 ━━━━━━━━━━━[37m━━━━━━━━━ 44s 1s/step - loss: 36.8383 - sparse_categorical_accuracy: 0.3139
60/100 ━━━━━━━━━━━━[37m━━━━━━━━ 43s 1s/step - loss: 36.8402 - sparse_categorical_accuracy: 0.3138
61/100 ━━━━━━━━━━━━[37m━━━━━━━━ 42s 1s/step - loss: 36.8420 - sparse_categorical_accuracy: 0.3137
62/100 ━━━━━━━━━━━━[37m━━━━━━━━ 41s 1s/step - loss: 36.8436 - sparse_categorical_accuracy: 0.3137
63/100 ━━━━━━━━━━━━[37m━━━━━━━━ 40s 1s/step - loss: 36.8450 - sparse_categorical_accuracy: 0.3136
64/100 ━━━━━━━━━━━━[37m━━━━━━━━ 38s 1s/step - loss: 36.8501 - sparse_categorical_accuracy: 0.3135
65/100 ━━━━━━━━━━━━━[37m━━━━━━━ 37s 1s/step - loss: 36.8548 - sparse_categorical_accuracy: 0.3134
66/100 ━━━━━━━━━━━━━[37m━━━━━━━ 36s 1s/step - loss: 36.8594 - sparse_categorical_accuracy: 0.3133
67/100 ━━━━━━━━━━━━━[37m━━━━━━━ 35s 1s/step - loss: 36.8637 - sparse_categorical_accuracy: 0.3132
68/100 ━━━━━━━━━━━━━[37m━━━━━━━ 34s 1s/step - loss: 36.8679 - sparse_categorical_accuracy: 0.3132
69/100 ━━━━━━━━━━━━━[37m━━━━━━━ 33s 1s/step - loss: 36.8722 - sparse_categorical_accuracy: 0.3131
70/100 ━━━━━━━━━━━━━━[37m━━━━━━ 32s 1s/step - loss: 36.8765 - sparse_categorical_accuracy: 0.3130
71/100 ━━━━━━━━━━━━━━[37m━━━━━━ 31s 1s/step - loss: 36.8808 - sparse_categorical_accuracy: 0.3129
72/100 ━━━━━━━━━━━━━━[37m━━━━━━ 30s 1s/step - loss: 36.8851 - sparse_categorical_accuracy: 0.3128
73/100 ━━━━━━━━━━━━━━[37m━━━━━━ 29s 1s/step - loss: 36.8893 - sparse_categorical_accuracy: 0.3127
74/100 ━━━━━━━━━━━━━━[37m━━━━━━ 28s 1s/step - loss: 36.8934 - sparse_categorical_accuracy: 0.3126
75/100 ━━━━━━━━━━━━━━━[37m━━━━━ 26s 1s/step - loss: 36.8974 - sparse_categorical_accuracy: 0.3125
76/100 ━━━━━━━━━━━━━━━[37m━━━━━ 25s 1s/step - loss: 36.9016 - sparse_categorical_accuracy: 0.3124
77/100 ━━━━━━━━━━━━━━━[37m━━━━━ 24s 1s/step - loss: 36.9056 - sparse_categorical_accuracy: 0.3123
78/100 ━━━━━━━━━━━━━━━[37m━━━━━ 23s 1s/step - loss: 36.9097 - sparse_categorical_accuracy: 0.3122
79/100 ━━━━━━━━━━━━━━━[37m━━━━━ 22s 1s/step - loss: 36.9137 - sparse_categorical_accuracy: 0.3121
80/100 ━━━━━━━━━━━━━━━━[37m━━━━ 21s 1s/step - loss: 36.9180 - sparse_categorical_accuracy: 0.3120
81/100 ━━━━━━━━━━━━━━━━[37m━━━━ 20s 1s/step - loss: 36.9223 - sparse_categorical_accuracy: 0.3119
82/100 ━━━━━━━━━━━━━━━━[37m━━━━ 19s 1s/step - loss: 36.9265 - sparse_categorical_accuracy: 0.3118
83/100 ━━━━━━━━━━━━━━━━[37m━━━━ 18s 1s/step - loss: 36.9306 - sparse_categorical_accuracy: 0.3117
84/100 ━━━━━━━━━━━━━━━━[37m━━━━ 17s 1s/step - loss: 36.9348 - sparse_categorical_accuracy: 0.3116
85/100 ━━━━━━━━━━━━━━━━━[37m━━━ 16s 1s/step - loss: 36.9389 - sparse_categorical_accuracy: 0.3115
86/100 ━━━━━━━━━━━━━━━━━[37m━━━ 15s 1s/step - loss: 36.9430 - sparse_categorical_accuracy: 0.3114
87/100 ━━━━━━━━━━━━━━━━━[37m━━━ 13s 1s/step - loss: 36.9471 - sparse_categorical_accuracy: 0.3113
88/100 ━━━━━━━━━━━━━━━━━[37m━━━ 12s 1s/step - loss: 36.9511 - sparse_categorical_accuracy: 0.3112
89/100 ━━━━━━━━━━━━━━━━━[37m━━━ 11s 1s/step - loss: 36.9550 - sparse_categorical_accuracy: 0.3112
90/100 ━━━━━━━━━━━━━━━━━━[37m━━ 10s 1s/step - loss: 36.9589 - sparse_categorical_accuracy: 0.3111
91/100 ━━━━━━━━━━━━━━━━━━[37m━━ 9s 1s/step - loss: 36.9626 - sparse_categorical_accuracy: 0.3110
92/100 ━━━━━━━━━━━━━━━━━━[37m━━ 8s 1s/step - loss: 36.9663 - sparse_categorical_accuracy: 0.3109
93/100 ━━━━━━━━━━━━━━━━━━[37m━━ 7s 1s/step - loss: 36.9700 - sparse_categorical_accuracy: 0.3108
94/100 ━━━━━━━━━━━━━━━━━━[37m━━ 6s 1s/step - loss: 36.9734 - sparse_categorical_accuracy: 0.3107
95/100 ━━━━━━━━━━━━━━━━━━━[37m━ 5s 1s/step - loss: 36.9768 - sparse_categorical_accuracy: 0.3106
96/100 ━━━━━━━━━━━━━━━━━━━[37m━ 4s 1s/step - loss: 36.9801 - sparse_categorical_accuracy: 0.3105
97/100 ━━━━━━━━━━━━━━━━━━━[37m━ 3s 1s/step - loss: 36.9834 - sparse_categorical_accuracy: 0.3104
98/100 ━━━━━━━━━━━━━━━━━━━[37m━ 2s 1s/step - loss: 36.9866 - sparse_categorical_accuracy: 0.3103
99/100 ━━━━━━━━━━━━━━━━━━━[37m━ 1s 1s/step - loss: 36.9898 - sparse_categorical_accuracy: 0.3102
100/100 ━━━━━━━━━━━━━━━━━━━━ 0s 1s/step - loss: 36.9913 - sparse_categorical_accuracy: 0.3101
100/100 ━━━━━━━━━━━━━━━━━━━━ 112s 1s/step - loss: 36.9928 - sparse_categorical_accuracy: 0.3100 - val_loss: 2087371157504536015273984.0000 - val_sparse_categorical_accuracy: 0.3004
Epoch 6/20
1/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:43 1s/step - loss: 37.1168 - sparse_categorical_accuracy: 0.1875
2/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:48 1s/step - loss: 37.1688 - sparse_categorical_accuracy: 0.1719
3/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:46 1s/step - loss: 37.1452 - sparse_categorical_accuracy: 0.1944
4/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:44 1s/step - loss: 37.0992 - sparse_categorical_accuracy: 0.2220
5/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:43 1s/step - loss: 37.0764 - sparse_categorical_accuracy: 0.2376
6/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:43 1s/step - loss: 37.0523 - sparse_categorical_accuracy: 0.2492
7/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:42 1s/step - loss: 37.0250 - sparse_categorical_accuracy: 0.2602
8/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:40 1s/step - loss: 36.9997 - sparse_categorical_accuracy: 0.2692
9/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:38 1s/step - loss: 36.9775 - sparse_categorical_accuracy: 0.2755
10/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:37 1s/step - loss: 36.9576 - sparse_categorical_accuracy: 0.2805
11/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:35 1s/step - loss: 36.9399 - sparse_categorical_accuracy: 0.2849
12/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:34 1s/step - loss: 36.9274 - sparse_categorical_accuracy: 0.2881
13/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:33 1s/step - loss: 36.9169 - sparse_categorical_accuracy: 0.2911
14/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:31 1s/step - loss: 36.9084 - sparse_categorical_accuracy: 0.2931
15/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:30 1s/step - loss: 36.8988 - sparse_categorical_accuracy: 0.2952
16/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:29 1s/step - loss: 36.8877 - sparse_categorical_accuracy: 0.2976
17/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:28 1s/step - loss: 36.8768 - sparse_categorical_accuracy: 0.3001
18/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:26 1s/step - loss: 36.8669 - sparse_categorical_accuracy: 0.3020
19/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:25 1s/step - loss: 36.8565 - sparse_categorical_accuracy: 0.3036
20/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:25 1s/step - loss: 36.8455 - sparse_categorical_accuracy: 0.3054
21/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:23 1s/step - loss: 36.8350 - sparse_categorical_accuracy: 0.3068
22/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:22 1s/step - loss: 36.8242 - sparse_categorical_accuracy: 0.3080
23/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:21 1s/step - loss: 36.8151 - sparse_categorical_accuracy: 0.3088
24/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:20 1s/step - loss: 36.8065 - sparse_categorical_accuracy: 0.3096
25/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:19 1s/step - loss: 36.7989 - sparse_categorical_accuracy: 0.3102
26/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:18 1s/step - loss: 36.7921 - sparse_categorical_accuracy: 0.3105
27/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:17 1s/step - loss: 36.7860 - sparse_categorical_accuracy: 0.3107
28/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:16 1s/step - loss: 36.7804 - sparse_categorical_accuracy: 0.3107
29/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:15 1s/step - loss: 36.7753 - sparse_categorical_accuracy: 0.3109
30/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:14 1s/step - loss: 36.7707 - sparse_categorical_accuracy: 0.3113
31/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:13 1s/step - loss: 36.7666 - sparse_categorical_accuracy: 0.3118
32/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:12 1s/step - loss: 36.7625 - sparse_categorical_accuracy: 0.3123
33/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:11 1s/step - loss: 36.7581 - sparse_categorical_accuracy: 0.3129
34/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:10 1s/step - loss: 36.7541 - sparse_categorical_accuracy: 0.3132
35/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:08 1s/step - loss: 36.7502 - sparse_categorical_accuracy: 0.3134
36/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:07 1s/step - loss: 36.7466 - sparse_categorical_accuracy: 0.3136
37/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:06 1s/step - loss: 36.7429 - sparse_categorical_accuracy: 0.3138
38/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:05 1s/step - loss: 36.7391 - sparse_categorical_accuracy: 0.3140
39/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:04 1s/step - loss: 36.7354 - sparse_categorical_accuracy: 0.3141
40/100 ━━━━━━━━[37m━━━━━━━━━━━━ 1:03 1s/step - loss: 36.7317 - sparse_categorical_accuracy: 0.3141
41/100 ━━━━━━━━[37m━━━━━━━━━━━━ 1:02 1s/step - loss: 36.7280 - sparse_categorical_accuracy: 0.3141
42/100 ━━━━━━━━[37m━━━━━━━━━━━━ 1:01 1s/step - loss: 36.7242 - sparse_categorical_accuracy: 0.3142
43/100 ━━━━━━━━[37m━━━━━━━━━━━━ 1:00 1s/step - loss: 36.7205 - sparse_categorical_accuracy: 0.3142
44/100 ━━━━━━━━[37m━━━━━━━━━━━━ 59s 1s/step - loss: 36.7167 - sparse_categorical_accuracy: 0.3143
45/100 ━━━━━━━━━[37m━━━━━━━━━━━ 58s 1s/step - loss: 36.7129 - sparse_categorical_accuracy: 0.3144
46/100 ━━━━━━━━━[37m━━━━━━━━━━━ 56s 1s/step - loss: 36.7114 - sparse_categorical_accuracy: 0.3145
47/100 ━━━━━━━━━[37m━━━━━━━━━━━ 55s 1s/step - loss: 36.7097 - sparse_categorical_accuracy: 0.3146
48/100 ━━━━━━━━━[37m━━━━━━━━━━━ 54s 1s/step - loss: 36.7081 - sparse_categorical_accuracy: 0.3147
49/100 ━━━━━━━━━[37m━━━━━━━━━━━ 53s 1s/step - loss: 36.7067 - sparse_categorical_accuracy: 0.3148
50/100 ━━━━━━━━━━[37m━━━━━━━━━━ 52s 1s/step - loss: 36.7053 - sparse_categorical_accuracy: 0.3149
51/100 ━━━━━━━━━━[37m━━━━━━━━━━ 51s 1s/step - loss: 36.7043 - sparse_categorical_accuracy: 0.3150
52/100 ━━━━━━━━━━[37m━━━━━━━━━━ 50s 1s/step - loss: 36.7035 - sparse_categorical_accuracy: 0.3151
53/100 ━━━━━━━━━━[37m━━━━━━━━━━ 49s 1s/step - loss: 36.7027 - sparse_categorical_accuracy: 0.3152
54/100 ━━━━━━━━━━[37m━━━━━━━━━━ 48s 1s/step - loss: 36.7020 - sparse_categorical_accuracy: 0.3153
55/100 ━━━━━━━━━━━[37m━━━━━━━━━ 47s 1s/step - loss: 36.7013 - sparse_categorical_accuracy: 0.3153
56/100 ━━━━━━━━━━━[37m━━━━━━━━━ 46s 1s/step - loss: 36.7005 - sparse_categorical_accuracy: 0.3154
57/100 ━━━━━━━━━━━[37m━━━━━━━━━ 44s 1s/step - loss: 36.6997 - sparse_categorical_accuracy: 0.3155
58/100 ━━━━━━━━━━━[37m━━━━━━━━━ 43s 1s/step - loss: 36.6991 - sparse_categorical_accuracy: 0.3155
59/100 ━━━━━━━━━━━[37m━━━━━━━━━ 42s 1s/step - loss: 36.6983 - sparse_categorical_accuracy: 0.3156
60/100 ━━━━━━━━━━━━[37m━━━━━━━━ 41s 1s/step - loss: 36.6977 - sparse_categorical_accuracy: 0.3156
61/100 ━━━━━━━━━━━━[37m━━━━━━━━ 40s 1s/step - loss: 36.6974 - sparse_categorical_accuracy: 0.3156
62/100 ━━━━━━━━━━━━[37m━━━━━━━━ 39s 1s/step - loss: 36.6971 - sparse_categorical_accuracy: 0.3156
63/100 ━━━━━━━━━━━━[37m━━━━━━━━ 38s 1s/step - loss: 36.6968 - sparse_categorical_accuracy: 0.3156
64/100 ━━━━━━━━━━━━[37m━━━━━━━━ 37s 1s/step - loss: 36.6963 - sparse_categorical_accuracy: 0.3157
65/100 ━━━━━━━━━━━━━[37m━━━━━━━ 36s 1s/step - loss: 36.6959 - sparse_categorical_accuracy: 0.3157
66/100 ━━━━━━━━━━━━━[37m━━━━━━━ 35s 1s/step - loss: 36.6954 - sparse_categorical_accuracy: 0.3158
67/100 ━━━━━━━━━━━━━[37m━━━━━━━ 34s 1s/step - loss: 36.6949 - sparse_categorical_accuracy: 0.3159
68/100 ━━━━━━━━━━━━━[37m━━━━━━━ 33s 1s/step - loss: 36.6944 - sparse_categorical_accuracy: 0.3160
69/100 ━━━━━━━━━━━━━[37m━━━━━━━ 32s 1s/step - loss: 36.6939 - sparse_categorical_accuracy: 0.3161
70/100 ━━━━━━━━━━━━━━[37m━━━━━━ 31s 1s/step - loss: 36.6933 - sparse_categorical_accuracy: 0.3162
71/100 ━━━━━━━━━━━━━━[37m━━━━━━ 30s 1s/step - loss: 36.6927 - sparse_categorical_accuracy: 0.3163
72/100 ━━━━━━━━━━━━━━[37m━━━━━━ 28s 1s/step - loss: 36.6921 - sparse_categorical_accuracy: 0.3164
73/100 ━━━━━━━━━━━━━━[37m━━━━━━ 27s 1s/step - loss: 36.6914 - sparse_categorical_accuracy: 0.3165
74/100 ━━━━━━━━━━━━━━[37m━━━━━━ 26s 1s/step - loss: 36.6907 - sparse_categorical_accuracy: 0.3166
75/100 ━━━━━━━━━━━━━━━[37m━━━━━ 25s 1s/step - loss: 36.6901 - sparse_categorical_accuracy: 0.3166
76/100 ━━━━━━━━━━━━━━━[37m━━━━━ 24s 1s/step - loss: 36.6897 - sparse_categorical_accuracy: 0.3167
77/100 ━━━━━━━━━━━━━━━[37m━━━━━ 23s 1s/step - loss: 36.6892 - sparse_categorical_accuracy: 0.3167
78/100 ━━━━━━━━━━━━━━━[37m━━━━━ 22s 1s/step - loss: 36.6887 - sparse_categorical_accuracy: 0.3168
79/100 ━━━━━━━━━━━━━━━[37m━━━━━ 21s 1s/step - loss: 36.6882 - sparse_categorical_accuracy: 0.3169
80/100 ━━━━━━━━━━━━━━━━[37m━━━━ 20s 1s/step - loss: 36.6878 - sparse_categorical_accuracy: 0.3170
81/100 ━━━━━━━━━━━━━━━━[37m━━━━ 19s 1s/step - loss: 36.6872 - sparse_categorical_accuracy: 0.3171
82/100 ━━━━━━━━━━━━━━━━[37m━━━━ 18s 1s/step - loss: 36.6867 - sparse_categorical_accuracy: 0.3172
83/100 ━━━━━━━━━━━━━━━━[37m━━━━ 17s 1s/step - loss: 36.6862 - sparse_categorical_accuracy: 0.3173
84/100 ━━━━━━━━━━━━━━━━[37m━━━━ 16s 1s/step - loss: 36.6858 - sparse_categorical_accuracy: 0.3173
85/100 ━━━━━━━━━━━━━━━━━[37m━━━ 15s 1s/step - loss: 36.6853 - sparse_categorical_accuracy: 0.3174
86/100 ━━━━━━━━━━━━━━━━━[37m━━━ 14s 1s/step - loss: 36.6847 - sparse_categorical_accuracy: 0.3175
87/100 ━━━━━━━━━━━━━━━━━[37m━━━ 13s 1s/step - loss: 36.6842 - sparse_categorical_accuracy: 0.3175
88/100 ━━━━━━━━━━━━━━━━━[37m━━━ 12s 1s/step - loss: 36.6835 - sparse_categorical_accuracy: 0.3176
89/100 ━━━━━━━━━━━━━━━━━[37m━━━ 11s 1s/step - loss: 36.6829 - sparse_categorical_accuracy: 0.3176
90/100 ━━━━━━━━━━━━━━━━━━[37m━━ 10s 1s/step - loss: 36.6823 - sparse_categorical_accuracy: 0.3177
91/100 ━━━━━━━━━━━━━━━━━━[37m━━ 9s 1s/step - loss: 36.6817 - sparse_categorical_accuracy: 0.3177
92/100 ━━━━━━━━━━━━━━━━━━[37m━━ 8s 1s/step - loss: 36.6810 - sparse_categorical_accuracy: 0.3177
93/100 ━━━━━━━━━━━━━━━━━━[37m━━ 7s 1s/step - loss: 36.6804 - sparse_categorical_accuracy: 0.3177
94/100 ━━━━━━━━━━━━━━━━━━[37m━━ 6s 1s/step - loss: 36.6802 - sparse_categorical_accuracy: 0.3178
95/100 ━━━━━━━━━━━━━━━━━━━[37m━ 5s 1s/step - loss: 36.6800 - sparse_categorical_accuracy: 0.3178
96/100 ━━━━━━━━━━━━━━━━━━━[37m━ 4s 1s/step - loss: 36.6798 - sparse_categorical_accuracy: 0.3179
97/100 ━━━━━━━━━━━━━━━━━━━[37m━ 3s 1s/step - loss: 36.6797 - sparse_categorical_accuracy: 0.3179
98/100 ━━━━━━━━━━━━━━━━━━━[37m━ 2s 1s/step - loss: 36.6795 - sparse_categorical_accuracy: 0.3180
99/100 ━━━━━━━━━━━━━━━━━━━[37m━ 1s 1s/step - loss: 36.6792 - sparse_categorical_accuracy: 0.3180
100/100 ━━━━━━━━━━━━━━━━━━━━ 0s 1s/step - loss: 36.6775 - sparse_categorical_accuracy: 0.3181
100/100 ━━━━━━━━━━━━━━━━━━━━ 108s 1s/step - loss: 36.6758 - sparse_categorical_accuracy: 0.3182 - val_loss: 598952362161209344.0000 - val_sparse_categorical_accuracy: 0.4180
Epoch 7/20
1/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:46 1s/step - loss: 36.5799 - sparse_categorical_accuracy: 0.2188
2/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:45 1s/step - loss: 39.4707 - sparse_categorical_accuracy: 0.2422
3/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:44 1s/step - loss: 39.7202 - sparse_categorical_accuracy: 0.2622
4/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:41 1s/step - loss: 39.6028 - sparse_categorical_accuracy: 0.2826
5/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:39 1s/step - loss: 39.4266 - sparse_categorical_accuracy: 0.2923
6/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:37 1s/step - loss: 39.2664 - sparse_categorical_accuracy: 0.3000
7/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:35 1s/step - loss: 39.1370 - sparse_categorical_accuracy: 0.3050
8/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:34 1s/step - loss: 39.0332 - sparse_categorical_accuracy: 0.3064
9/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:34 1s/step - loss: 38.9412 - sparse_categorical_accuracy: 0.3090
10/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:33 1s/step - loss: 38.8614 - sparse_categorical_accuracy: 0.3115
11/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:32 1s/step - loss: 38.7961 - sparse_categorical_accuracy: 0.3127
12/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:31 1s/step - loss: 38.7323 - sparse_categorical_accuracy: 0.3144
13/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:30 1s/step - loss: 38.6772 - sparse_categorical_accuracy: 0.3161
14/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:29 1s/step - loss: 38.6311 - sparse_categorical_accuracy: 0.3166
15/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:28 1s/step - loss: 38.5887 - sparse_categorical_accuracy: 0.3172
16/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:27 1s/step - loss: 38.5600 - sparse_categorical_accuracy: 0.3173
17/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:26 1s/step - loss: 38.5358 - sparse_categorical_accuracy: 0.3172
18/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:25 1s/step - loss: 38.5143 - sparse_categorical_accuracy: 0.3170
19/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:24 1s/step - loss: 38.4937 - sparse_categorical_accuracy: 0.3166
20/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:23 1s/step - loss: 38.4737 - sparse_categorical_accuracy: 0.3164
21/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:22 1s/step - loss: 38.4543 - sparse_categorical_accuracy: 0.3164
22/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:20 1s/step - loss: 38.4364 - sparse_categorical_accuracy: 0.3163
23/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:19 1s/step - loss: 38.4201 - sparse_categorical_accuracy: 0.3161
24/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:18 1s/step - loss: 38.4052 - sparse_categorical_accuracy: 0.3162
25/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:17 1s/step - loss: 38.3898 - sparse_categorical_accuracy: 0.3165
26/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:16 1s/step - loss: 38.3748 - sparse_categorical_accuracy: 0.3167
27/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:15 1s/step - loss: 38.3601 - sparse_categorical_accuracy: 0.3167
28/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:14 1s/step - loss: 38.3457 - sparse_categorical_accuracy: 0.3167
29/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:13 1s/step - loss: 38.3315 - sparse_categorical_accuracy: 0.3168
30/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:12 1s/step - loss: 38.3167 - sparse_categorical_accuracy: 0.3172
31/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:11 1s/step - loss: 38.3021 - sparse_categorical_accuracy: 0.3175
32/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:10 1s/step - loss: 38.2873 - sparse_categorical_accuracy: 0.3179
33/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:09 1s/step - loss: 38.2722 - sparse_categorical_accuracy: 0.3184
34/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:08 1s/step - loss: 38.2571 - sparse_categorical_accuracy: 0.3189
35/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:07 1s/step - loss: 38.2425 - sparse_categorical_accuracy: 0.3193
36/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:06 1s/step - loss: 38.2277 - sparse_categorical_accuracy: 0.3197
37/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:05 1s/step - loss: 38.2132 - sparse_categorical_accuracy: 0.3199
38/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:04 1s/step - loss: 38.1989 - sparse_categorical_accuracy: 0.3201
39/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:02 1s/step - loss: 38.1846 - sparse_categorical_accuracy: 0.3204
40/100 ━━━━━━━━[37m━━━━━━━━━━━━ 1:01 1s/step - loss: 38.1707 - sparse_categorical_accuracy: 0.3206
41/100 ━━━━━━━━[37m━━━━━━━━━━━━ 1:00 1s/step - loss: 38.1595 - sparse_categorical_accuracy: 0.3209
42/100 ━━━━━━━━[37m━━━━━━━━━━━━ 59s 1s/step - loss: 38.1484 - sparse_categorical_accuracy: 0.3211
43/100 ━━━━━━━━[37m━━━━━━━━━━━━ 58s 1s/step - loss: 38.1373 - sparse_categorical_accuracy: 0.3213
44/100 ━━━━━━━━[37m━━━━━━━━━━━━ 57s 1s/step - loss: 38.1262 - sparse_categorical_accuracy: 0.3214
45/100 ━━━━━━━━━[37m━━━━━━━━━━━ 56s 1s/step - loss: 38.1152 - sparse_categorical_accuracy: 0.3215
46/100 ━━━━━━━━━[37m━━━━━━━━━━━ 55s 1s/step - loss: 38.1040 - sparse_categorical_accuracy: 0.3216
47/100 ━━━━━━━━━[37m━━━━━━━━━━━ 54s 1s/step - loss: 38.0932 - sparse_categorical_accuracy: 0.3216
48/100 ━━━━━━━━━[37m━━━━━━━━━━━ 53s 1s/step - loss: 38.0824 - sparse_categorical_accuracy: 0.3216
49/100 ━━━━━━━━━[37m━━━━━━━━━━━ 52s 1s/step - loss: 38.0716 - sparse_categorical_accuracy: 0.3216
50/100 ━━━━━━━━━━[37m━━━━━━━━━━ 51s 1s/step - loss: 38.0609 - sparse_categorical_accuracy: 0.3216
51/100 ━━━━━━━━━━[37m━━━━━━━━━━ 50s 1s/step - loss: 38.0535 - sparse_categorical_accuracy: 0.3216
52/100 ━━━━━━━━━━[37m━━━━━━━━━━ 49s 1s/step - loss: 38.0460 - sparse_categorical_accuracy: 0.3217
53/100 ━━━━━━━━━━[37m━━━━━━━━━━ 48s 1s/step - loss: 38.0384 - sparse_categorical_accuracy: 0.3217
54/100 ━━━━━━━━━━[37m━━━━━━━━━━ 47s 1s/step - loss: 38.0309 - sparse_categorical_accuracy: 0.3217
55/100 ━━━━━━━━━━━[37m━━━━━━━━━ 46s 1s/step - loss: 38.0235 - sparse_categorical_accuracy: 0.3218
56/100 ━━━━━━━━━━━[37m━━━━━━━━━ 45s 1s/step - loss: 38.0162 - sparse_categorical_accuracy: 0.3218
57/100 ━━━━━━━━━━━[37m━━━━━━━━━ 44s 1s/step - loss: 38.0092 - sparse_categorical_accuracy: 0.3217
58/100 ━━━━━━━━━━━[37m━━━━━━━━━ 43s 1s/step - loss: 38.0029 - sparse_categorical_accuracy: 0.3217
59/100 ━━━━━━━━━━━[37m━━━━━━━━━ 42s 1s/step - loss: 37.9967 - sparse_categorical_accuracy: 0.3216
60/100 ━━━━━━━━━━━━[37m━━━━━━━━ 41s 1s/step - loss: 37.9907 - sparse_categorical_accuracy: 0.3215
61/100 ━━━━━━━━━━━━[37m━━━━━━━━ 40s 1s/step - loss: 37.9848 - sparse_categorical_accuracy: 0.3215
62/100 ━━━━━━━━━━━━[37m━━━━━━━━ 39s 1s/step - loss: 37.9791 - sparse_categorical_accuracy: 0.3214
63/100 ━━━━━━━━━━━━[37m━━━━━━━━ 38s 1s/step - loss: 37.9734 - sparse_categorical_accuracy: 0.3214
64/100 ━━━━━━━━━━━━[37m━━━━━━━━ 36s 1s/step - loss: 37.9678 - sparse_categorical_accuracy: 0.3213
65/100 ━━━━━━━━━━━━━[37m━━━━━━━ 35s 1s/step - loss: 37.9623 - sparse_categorical_accuracy: 0.3212
66/100 ━━━━━━━━━━━━━[37m━━━━━━━ 34s 1s/step - loss: 37.9570 - sparse_categorical_accuracy: 0.3211
67/100 ━━━━━━━━━━━━━[37m━━━━━━━ 33s 1s/step - loss: 37.9519 - sparse_categorical_accuracy: 0.3211
68/100 ━━━━━━━━━━━━━[37m━━━━━━━ 32s 1s/step - loss: 37.9469 - sparse_categorical_accuracy: 0.3210
69/100 ━━━━━━━━━━━━━[37m━━━━━━━ 31s 1s/step - loss: 37.9424 - sparse_categorical_accuracy: 0.3209
70/100 ━━━━━━━━━━━━━━[37m━━━━━━ 30s 1s/step - loss: 37.9380 - sparse_categorical_accuracy: 0.3208
71/100 ━━━━━━━━━━━━━━[37m━━━━━━ 29s 1s/step - loss: 37.9341 - sparse_categorical_accuracy: 0.3208
72/100 ━━━━━━━━━━━━━━[37m━━━━━━ 28s 1s/step - loss: 37.9304 - sparse_categorical_accuracy: 0.3207
73/100 ━━━━━━━━━━━━━━[37m━━━━━━ 27s 1s/step - loss: 37.9269 - sparse_categorical_accuracy: 0.3206
74/100 ━━━━━━━━━━━━━━[37m━━━━━━ 26s 1s/step - loss: 37.9234 - sparse_categorical_accuracy: 0.3206
75/100 ━━━━━━━━━━━━━━━[37m━━━━━ 25s 1s/step - loss: 37.9199 - sparse_categorical_accuracy: 0.3205
76/100 ━━━━━━━━━━━━━━━[37m━━━━━ 24s 1s/step - loss: 37.9165 - sparse_categorical_accuracy: 0.3204
77/100 ━━━━━━━━━━━━━━━[37m━━━━━ 23s 1s/step - loss: 37.9135 - sparse_categorical_accuracy: 0.3203
78/100 ━━━━━━━━━━━━━━━[37m━━━━━ 22s 1s/step - loss: 37.9104 - sparse_categorical_accuracy: 0.3202
79/100 ━━━━━━━━━━━━━━━[37m━━━━━ 21s 1s/step - loss: 37.9071 - sparse_categorical_accuracy: 0.3202
80/100 ━━━━━━━━━━━━━━━━[37m━━━━ 20s 1s/step - loss: 37.9039 - sparse_categorical_accuracy: 0.3201
81/100 ━━━━━━━━━━━━━━━━[37m━━━━ 19s 1s/step - loss: 37.9007 - sparse_categorical_accuracy: 0.3201
82/100 ━━━━━━━━━━━━━━━━[37m━━━━ 18s 1s/step - loss: 37.8974 - sparse_categorical_accuracy: 0.3200
83/100 ━━━━━━━━━━━━━━━━[37m━━━━ 17s 1s/step - loss: 37.8941 - sparse_categorical_accuracy: 0.3200
84/100 ━━━━━━━━━━━━━━━━[37m━━━━ 16s 1s/step - loss: 37.8908 - sparse_categorical_accuracy: 0.3200
85/100 ━━━━━━━━━━━━━━━━━[37m━━━ 15s 1s/step - loss: 37.8875 - sparse_categorical_accuracy: 0.3199
86/100 ━━━━━━━━━━━━━━━━━[37m━━━ 14s 1s/step - loss: 37.8840 - sparse_categorical_accuracy: 0.3199
87/100 ━━━━━━━━━━━━━━━━━[37m━━━ 13s 1s/step - loss: 37.8806 - sparse_categorical_accuracy: 0.3199
88/100 ━━━━━━━━━━━━━━━━━[37m━━━ 12s 1s/step - loss: 37.8770 - sparse_categorical_accuracy: 0.3198
89/100 ━━━━━━━━━━━━━━━━━[37m━━━ 11s 1s/step - loss: 37.8734 - sparse_categorical_accuracy: 0.3198
90/100 ━━━━━━━━━━━━━━━━━━[37m━━ 10s 1s/step - loss: 37.8697 - sparse_categorical_accuracy: 0.3197
91/100 ━━━━━━━━━━━━━━━━━━[37m━━ 9s 1s/step - loss: 37.8660 - sparse_categorical_accuracy: 0.3197
92/100 ━━━━━━━━━━━━━━━━━━[37m━━ 8s 1s/step - loss: 37.8622 - sparse_categorical_accuracy: 0.3196
93/100 ━━━━━━━━━━━━━━━━━━[37m━━ 7s 1s/step - loss: 37.8583 - sparse_categorical_accuracy: 0.3195
94/100 ━━━━━━━━━━━━━━━━━━[37m━━ 6s 1s/step - loss: 37.8545 - sparse_categorical_accuracy: 0.3195
95/100 ━━━━━━━━━━━━━━━━━━━[37m━ 5s 1s/step - loss: 37.8505 - sparse_categorical_accuracy: 0.3194
96/100 ━━━━━━━━━━━━━━━━━━━[37m━ 4s 1s/step - loss: 37.8465 - sparse_categorical_accuracy: 0.3194
97/100 ━━━━━━━━━━━━━━━━━━━[37m━ 3s 1s/step - loss: 37.8424 - sparse_categorical_accuracy: 0.3193
98/100 ━━━━━━━━━━━━━━━━━━━[37m━ 2s 1s/step - loss: 37.8384 - sparse_categorical_accuracy: 0.3193
99/100 ━━━━━━━━━━━━━━━━━━━[37m━ 1s 1s/step - loss: 37.8342 - sparse_categorical_accuracy: 0.3192
100/100 ━━━━━━━━━━━━━━━━━━━━ 0s 1s/step - loss: 37.8286 - sparse_categorical_accuracy: 0.3192
100/100 ━━━━━━━━━━━━━━━━━━━━ 107s 1s/step - loss: 37.8231 - sparse_categorical_accuracy: 0.3192 - val_loss: 1330149064704.0000 - val_sparse_categorical_accuracy: 0.3367
Epoch 8/20
1/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:42 1s/step - loss: 36.6512 - sparse_categorical_accuracy: 0.2500
2/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:44 1s/step - loss: 36.6798 - sparse_categorical_accuracy: 0.2734
3/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:40 1s/step - loss: 36.6432 - sparse_categorical_accuracy: 0.2899
4/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:40 1s/step - loss: 36.5739 - sparse_categorical_accuracy: 0.3132
5/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:39 1s/step - loss: 36.5407 - sparse_categorical_accuracy: 0.3268
6/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:37 1s/step - loss: 36.5485 - sparse_categorical_accuracy: 0.3331
7/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:36 1s/step - loss: 36.5576 - sparse_categorical_accuracy: 0.3371
8/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:35 1s/step - loss: 36.5698 - sparse_categorical_accuracy: 0.3385
9/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:34 1s/step - loss: 36.5745 - sparse_categorical_accuracy: 0.3394
10/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:33 1s/step - loss: 36.5792 - sparse_categorical_accuracy: 0.3389
11/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:32 1s/step - loss: 36.5810 - sparse_categorical_accuracy: 0.3376
12/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:30 1s/step - loss: 36.5798 - sparse_categorical_accuracy: 0.3361
13/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:29 1s/step - loss: 36.5791 - sparse_categorical_accuracy: 0.3352
14/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:28 1s/step - loss: 36.5762 - sparse_categorical_accuracy: 0.3354
15/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:28 1s/step - loss: 36.5728 - sparse_categorical_accuracy: 0.3355
16/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:26 1s/step - loss: 36.5684 - sparse_categorical_accuracy: 0.3359
17/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:25 1s/step - loss: 36.5666 - sparse_categorical_accuracy: 0.3356
18/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:24 1s/step - loss: 36.5648 - sparse_categorical_accuracy: 0.3348
19/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:23 1s/step - loss: 36.5629 - sparse_categorical_accuracy: 0.3337
20/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:22 1s/step - loss: 36.5608 - sparse_categorical_accuracy: 0.3327
21/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:21 1s/step - loss: 36.5580 - sparse_categorical_accuracy: 0.3321
22/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:20 1s/step - loss: 36.5553 - sparse_categorical_accuracy: 0.3314
23/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:19 1s/step - loss: 36.5536 - sparse_categorical_accuracy: 0.3305
24/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:18 1s/step - loss: 36.5524 - sparse_categorical_accuracy: 0.3294
25/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:17 1s/step - loss: 36.5546 - sparse_categorical_accuracy: 0.3286
26/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:16 1s/step - loss: 36.5562 - sparse_categorical_accuracy: 0.3276
27/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:15 1s/step - loss: 36.5576 - sparse_categorical_accuracy: 0.3267
28/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:14 1s/step - loss: 36.5586 - sparse_categorical_accuracy: 0.3258
29/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:13 1s/step - loss: 36.5592 - sparse_categorical_accuracy: 0.3251
30/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:11 1s/step - loss: 36.5596 - sparse_categorical_accuracy: 0.3245
31/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:10 1s/step - loss: 36.5592 - sparse_categorical_accuracy: 0.3241
32/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:09 1s/step - loss: 36.5586 - sparse_categorical_accuracy: 0.3238
33/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:08 1s/step - loss: 36.5576 - sparse_categorical_accuracy: 0.3236
34/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:07 1s/step - loss: 36.5560 - sparse_categorical_accuracy: 0.3234
35/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:06 1s/step - loss: 36.5542 - sparse_categorical_accuracy: 0.3233
36/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:05 1s/step - loss: 36.5522 - sparse_categorical_accuracy: 0.3231
37/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:04 1s/step - loss: 36.5500 - sparse_categorical_accuracy: 0.3231
38/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:03 1s/step - loss: 36.5481 - sparse_categorical_accuracy: 0.3230
39/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:02 1s/step - loss: 36.5463 - sparse_categorical_accuracy: 0.3228
40/100 ━━━━━━━━[37m━━━━━━━━━━━━ 1:01 1s/step - loss: 36.5443 - sparse_categorical_accuracy: 0.3227
41/100 ━━━━━━━━[37m━━━━━━━━━━━━ 1:00 1s/step - loss: 36.5423 - sparse_categorical_accuracy: 0.3225
42/100 ━━━━━━━━[37m━━━━━━━━━━━━ 59s 1s/step - loss: 36.5402 - sparse_categorical_accuracy: 0.3223
43/100 ━━━━━━━━[37m━━━━━━━━━━━━ 58s 1s/step - loss: 36.5381 - sparse_categorical_accuracy: 0.3220
44/100 ━━━━━━━━[37m━━━━━━━━━━━━ 57s 1s/step - loss: 36.5362 - sparse_categorical_accuracy: 0.3218
45/100 ━━━━━━━━━[37m━━━━━━━━━━━ 56s 1s/step - loss: 36.5354 - sparse_categorical_accuracy: 0.3215
46/100 ━━━━━━━━━[37m━━━━━━━━━━━ 55s 1s/step - loss: 36.5343 - sparse_categorical_accuracy: 0.3212
47/100 ━━━━━━━━━[37m━━━━━━━━━━━ 54s 1s/step - loss: 36.5330 - sparse_categorical_accuracy: 0.3209
48/100 ━━━━━━━━━[37m━━━━━━━━━━━ 53s 1s/step - loss: 36.5316 - sparse_categorical_accuracy: 0.3207
49/100 ━━━━━━━━━[37m━━━━━━━━━━━ 52s 1s/step - loss: 36.5302 - sparse_categorical_accuracy: 0.3205
50/100 ━━━━━━━━━━[37m━━━━━━━━━━ 51s 1s/step - loss: 36.5287 - sparse_categorical_accuracy: 0.3204
51/100 ━━━━━━━━━━[37m━━━━━━━━━━ 50s 1s/step - loss: 36.5272 - sparse_categorical_accuracy: 0.3203
52/100 ━━━━━━━━━━[37m━━━━━━━━━━ 49s 1s/step - loss: 36.5257 - sparse_categorical_accuracy: 0.3202
53/100 ━━━━━━━━━━[37m━━━━━━━━━━ 48s 1s/step - loss: 36.5242 - sparse_categorical_accuracy: 0.3201
54/100 ━━━━━━━━━━[37m━━━━━━━━━━ 46s 1s/step - loss: 36.5229 - sparse_categorical_accuracy: 0.3200
55/100 ━━━━━━━━━━━[37m━━━━━━━━━ 45s 1s/step - loss: 36.5216 - sparse_categorical_accuracy: 0.3199
56/100 ━━━━━━━━━━━[37m━━━━━━━━━ 44s 1s/step - loss: 36.5203 - sparse_categorical_accuracy: 0.3197
57/100 ━━━━━━━━━━━[37m━━━━━━━━━ 43s 1s/step - loss: 36.5188 - sparse_categorical_accuracy: 0.3196
58/100 ━━━━━━━━━━━[37m━━━━━━━━━ 42s 1s/step - loss: 36.5173 - sparse_categorical_accuracy: 0.3195
59/100 ━━━━━━━━━━━[37m━━━━━━━━━ 41s 1s/step - loss: 36.5157 - sparse_categorical_accuracy: 0.3194
60/100 ━━━━━━━━━━━━[37m━━━━━━━━ 40s 1s/step - loss: 36.5140 - sparse_categorical_accuracy: 0.3193
61/100 ━━━━━━━━━━━━[37m━━━━━━━━ 39s 1s/step - loss: 36.5122 - sparse_categorical_accuracy: 0.3192
62/100 ━━━━━━━━━━━━[37m━━━━━━━━ 38s 1s/step - loss: 36.5105 - sparse_categorical_accuracy: 0.3192
63/100 ━━━━━━━━━━━━[37m━━━━━━━━ 37s 1s/step - loss: 36.5086 - sparse_categorical_accuracy: 0.3191
64/100 ━━━━━━━━━━━━[37m━━━━━━━━ 36s 1s/step - loss: 36.5067 - sparse_categorical_accuracy: 0.3191
65/100 ━━━━━━━━━━━━━[37m━━━━━━━ 35s 1s/step - loss: 36.5048 - sparse_categorical_accuracy: 0.3191
66/100 ━━━━━━━━━━━━━[37m━━━━━━━ 34s 1s/step - loss: 36.5030 - sparse_categorical_accuracy: 0.3191
67/100 ━━━━━━━━━━━━━[37m━━━━━━━ 33s 1s/step - loss: 36.5011 - sparse_categorical_accuracy: 0.3191
68/100 ━━━━━━━━━━━━━[37m━━━━━━━ 32s 1s/step - loss: 36.4993 - sparse_categorical_accuracy: 0.3191
69/100 ━━━━━━━━━━━━━[37m━━━━━━━ 31s 1s/step - loss: 36.4974 - sparse_categorical_accuracy: 0.3191
70/100 ━━━━━━━━━━━━━━[37m━━━━━━ 30s 1s/step - loss: 36.4955 - sparse_categorical_accuracy: 0.3192
71/100 ━━━━━━━━━━━━━━[37m━━━━━━ 29s 1s/step - loss: 36.4937 - sparse_categorical_accuracy: 0.3192
72/100 ━━━━━━━━━━━━━━[37m━━━━━━ 28s 1s/step - loss: 36.4919 - sparse_categorical_accuracy: 0.3193
73/100 ━━━━━━━━━━━━━━[37m━━━━━━ 27s 1s/step - loss: 36.4902 - sparse_categorical_accuracy: 0.3194
74/100 ━━━━━━━━━━━━━━[37m━━━━━━ 26s 1s/step - loss: 36.4886 - sparse_categorical_accuracy: 0.3194
75/100 ━━━━━━━━━━━━━━━[37m━━━━━ 25s 1s/step - loss: 36.4871 - sparse_categorical_accuracy: 0.3194
76/100 ━━━━━━━━━━━━━━━[37m━━━━━ 24s 1s/step - loss: 36.4858 - sparse_categorical_accuracy: 0.3194
77/100 ━━━━━━━━━━━━━━━[37m━━━━━ 23s 1s/step - loss: 36.4845 - sparse_categorical_accuracy: 0.3195
78/100 ━━━━━━━━━━━━━━━[37m━━━━━ 22s 1s/step - loss: 36.4834 - sparse_categorical_accuracy: 0.3195
79/100 ━━━━━━━━━━━━━━━[37m━━━━━ 21s 1s/step - loss: 36.4824 - sparse_categorical_accuracy: 0.3195
80/100 ━━━━━━━━━━━━━━━━[37m━━━━ 20s 1s/step - loss: 36.4813 - sparse_categorical_accuracy: 0.3195
81/100 ━━━━━━━━━━━━━━━━[37m━━━━ 19s 1s/step - loss: 36.4804 - sparse_categorical_accuracy: 0.3195
82/100 ━━━━━━━━━━━━━━━━[37m━━━━ 18s 1s/step - loss: 36.4794 - sparse_categorical_accuracy: 0.3195
83/100 ━━━━━━━━━━━━━━━━[37m━━━━ 17s 1s/step - loss: 36.4785 - sparse_categorical_accuracy: 0.3195
84/100 ━━━━━━━━━━━━━━━━[37m━━━━ 16s 1s/step - loss: 36.4776 - sparse_categorical_accuracy: 0.3195
85/100 ━━━━━━━━━━━━━━━━━[37m━━━ 15s 1s/step - loss: 36.4767 - sparse_categorical_accuracy: 0.3196
86/100 ━━━━━━━━━━━━━━━━━[37m━━━ 14s 1s/step - loss: 36.4759 - sparse_categorical_accuracy: 0.3196
87/100 ━━━━━━━━━━━━━━━━━[37m━━━ 13s 1s/step - loss: 36.4750 - sparse_categorical_accuracy: 0.3196
88/100 ━━━━━━━━━━━━━━━━━[37m━━━ 12s 1s/step - loss: 36.4742 - sparse_categorical_accuracy: 0.3196
89/100 ━━━━━━━━━━━━━━━━━[37m━━━ 11s 1s/step - loss: 36.4735 - sparse_categorical_accuracy: 0.3196
90/100 ━━━━━━━━━━━━━━━━━━[37m━━ 10s 1s/step - loss: 36.4727 - sparse_categorical_accuracy: 0.3197
91/100 ━━━━━━━━━━━━━━━━━━[37m━━ 9s 1s/step - loss: 36.4719 - sparse_categorical_accuracy: 0.3197
92/100 ━━━━━━━━━━━━━━━━━━[37m━━ 8s 1s/step - loss: 36.4711 - sparse_categorical_accuracy: 0.3197
93/100 ━━━━━━━━━━━━━━━━━━[37m━━ 7s 1s/step - loss: 36.4702 - sparse_categorical_accuracy: 0.3198
94/100 ━━━━━━━━━━━━━━━━━━[37m━━ 6s 1s/step - loss: 36.4693 - sparse_categorical_accuracy: 0.3198
95/100 ━━━━━━━━━━━━━━━━━━━[37m━ 5s 1s/step - loss: 36.4686 - sparse_categorical_accuracy: 0.3198
96/100 ━━━━━━━━━━━━━━━━━━━[37m━ 4s 1s/step - loss: 36.4678 - sparse_categorical_accuracy: 0.3198
97/100 ━━━━━━━━━━━━━━━━━━━[37m━ 3s 1s/step - loss: 36.4670 - sparse_categorical_accuracy: 0.3198
98/100 ━━━━━━━━━━━━━━━━━━━[37m━ 2s 1s/step - loss: 36.4663 - sparse_categorical_accuracy: 0.3198
99/100 ━━━━━━━━━━━━━━━━━━━[37m━ 1s 1s/step - loss: 36.4656 - sparse_categorical_accuracy: 0.3198
100/100 ━━━━━━━━━━━━━━━━━━━━ 0s 1s/step - loss: 36.4633 - sparse_categorical_accuracy: 0.3198
100/100 ━━━━━━━━━━━━━━━━━━━━ 107s 1s/step - loss: 36.4611 - sparse_categorical_accuracy: 0.3198 - val_loss: 55461990629376.0000 - val_sparse_categorical_accuracy: 0.3805
Epoch 9/20
1/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:48 1s/step - loss: 36.1902 - sparse_categorical_accuracy: 0.4062
2/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:42 1s/step - loss: 36.1628 - sparse_categorical_accuracy: 0.3594
3/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:42 1s/step - loss: 36.1877 - sparse_categorical_accuracy: 0.3438
4/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:40 1s/step - loss: 36.2174 - sparse_categorical_accuracy: 0.3320
5/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:38 1s/step - loss: 36.2312 - sparse_categorical_accuracy: 0.3294
6/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:37 1s/step - loss: 36.2290 - sparse_categorical_accuracy: 0.3309
7/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:36 1s/step - loss: 36.2177 - sparse_categorical_accuracy: 0.3321
8/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:35 1s/step - loss: 36.2049 - sparse_categorical_accuracy: 0.3331
9/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:34 1s/step - loss: 36.2052 - sparse_categorical_accuracy: 0.3319
10/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:32 1s/step - loss: 36.2082 - sparse_categorical_accuracy: 0.3309
11/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:32 1s/step - loss: 36.2106 - sparse_categorical_accuracy: 0.3298
12/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:31 1s/step - loss: 36.2138 - sparse_categorical_accuracy: 0.3292
13/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:29 1s/step - loss: 36.2142 - sparse_categorical_accuracy: 0.3288
14/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:28 1s/step - loss: 36.2186 - sparse_categorical_accuracy: 0.3282
15/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:27 1s/step - loss: 36.2206 - sparse_categorical_accuracy: 0.3278
16/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:26 1s/step - loss: 36.2294 - sparse_categorical_accuracy: 0.3283
17/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:25 1s/step - loss: 36.2382 - sparse_categorical_accuracy: 0.3287
18/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:24 1s/step - loss: 36.2450 - sparse_categorical_accuracy: 0.3294
19/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:23 1s/step - loss: 36.2496 - sparse_categorical_accuracy: 0.3303
20/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:22 1s/step - loss: 36.2549 - sparse_categorical_accuracy: 0.3309
21/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:21 1s/step - loss: 36.2586 - sparse_categorical_accuracy: 0.3315
22/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:20 1s/step - loss: 36.2609 - sparse_categorical_accuracy: 0.3324
23/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:19 1s/step - loss: 36.2630 - sparse_categorical_accuracy: 0.3330
24/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:18 1s/step - loss: 36.2647 - sparse_categorical_accuracy: 0.3333
25/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:17 1s/step - loss: 36.2664 - sparse_categorical_accuracy: 0.3339
26/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:16 1s/step - loss: 36.2682 - sparse_categorical_accuracy: 0.3343
27/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:15 1s/step - loss: 36.2697 - sparse_categorical_accuracy: 0.3344
28/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:14 1s/step - loss: 36.2714 - sparse_categorical_accuracy: 0.3345
29/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:13 1s/step - loss: 36.2728 - sparse_categorical_accuracy: 0.3344
30/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:12 1s/step - loss: 36.2743 - sparse_categorical_accuracy: 0.3343
31/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:11 1s/step - loss: 36.2755 - sparse_categorical_accuracy: 0.3340
32/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:10 1s/step - loss: 36.2773 - sparse_categorical_accuracy: 0.3338
33/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:09 1s/step - loss: 36.2785 - sparse_categorical_accuracy: 0.3337
34/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:08 1s/step - loss: 36.2792 - sparse_categorical_accuracy: 0.3336
35/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:06 1s/step - loss: 36.2797 - sparse_categorical_accuracy: 0.3336
36/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:05 1s/step - loss: 36.2802 - sparse_categorical_accuracy: 0.3336
37/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:04 1s/step - loss: 36.2807 - sparse_categorical_accuracy: 0.3336
38/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:03 1s/step - loss: 36.2810 - sparse_categorical_accuracy: 0.3336
39/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:02 1s/step - loss: 36.2810 - sparse_categorical_accuracy: 0.3336
40/100 ━━━━━━━━[37m━━━━━━━━━━━━ 1:01 1s/step - loss: 36.2809 - sparse_categorical_accuracy: 0.3336
41/100 ━━━━━━━━[37m━━━━━━━━━━━━ 1:00 1s/step - loss: 36.2809 - sparse_categorical_accuracy: 0.3336
42/100 ━━━━━━━━[37m━━━━━━━━━━━━ 59s 1s/step - loss: 36.2820 - sparse_categorical_accuracy: 0.3336
43/100 ━━━━━━━━[37m━━━━━━━━━━━━ 58s 1s/step - loss: 36.2831 - sparse_categorical_accuracy: 0.3337
44/100 ━━━━━━━━[37m━━━━━━━━━━━━ 57s 1s/step - loss: 36.2839 - sparse_categorical_accuracy: 0.3337
45/100 ━━━━━━━━━[37m━━━━━━━━━━━ 56s 1s/step - loss: 36.2848 - sparse_categorical_accuracy: 0.3337
46/100 ━━━━━━━━━[37m━━━━━━━━━━━ 55s 1s/step - loss: 36.2857 - sparse_categorical_accuracy: 0.3336
47/100 ━━━━━━━━━[37m━━━━━━━━━━━ 54s 1s/step - loss: 36.2874 - sparse_categorical_accuracy: 0.3335
48/100 ━━━━━━━━━[37m━━━━━━━━━━━ 53s 1s/step - loss: 36.2893 - sparse_categorical_accuracy: 0.3335
49/100 ━━━━━━━━━[37m━━━━━━━━━━━ 52s 1s/step - loss: 36.2912 - sparse_categorical_accuracy: 0.3334
50/100 ━━━━━━━━━━[37m━━━━━━━━━━ 51s 1s/step - loss: 36.2930 - sparse_categorical_accuracy: 0.3333
51/100 ━━━━━━━━━━[37m━━━━━━━━━━ 50s 1s/step - loss: 36.2946 - sparse_categorical_accuracy: 0.3334
52/100 ━━━━━━━━━━[37m━━━━━━━━━━ 49s 1s/step - loss: 36.2961 - sparse_categorical_accuracy: 0.3334
53/100 ━━━━━━━━━━[37m━━━━━━━━━━ 48s 1s/step - loss: 36.2975 - sparse_categorical_accuracy: 0.3334
54/100 ━━━━━━━━━━[37m━━━━━━━━━━ 47s 1s/step - loss: 36.2989 - sparse_categorical_accuracy: 0.3334
55/100 ━━━━━━━━━━━[37m━━━━━━━━━ 46s 1s/step - loss: 36.3000 - sparse_categorical_accuracy: 0.3335
56/100 ━━━━━━━━━━━[37m━━━━━━━━━ 45s 1s/step - loss: 36.3012 - sparse_categorical_accuracy: 0.3336
57/100 ━━━━━━━━━━━[37m━━━━━━━━━ 44s 1s/step - loss: 36.3021 - sparse_categorical_accuracy: 0.3336
58/100 ━━━━━━━━━━━[37m━━━━━━━━━ 43s 1s/step - loss: 36.3031 - sparse_categorical_accuracy: 0.3336
59/100 ━━━━━━━━━━━[37m━━━━━━━━━ 42s 1s/step - loss: 36.3040 - sparse_categorical_accuracy: 0.3336
60/100 ━━━━━━━━━━━━[37m━━━━━━━━ 41s 1s/step - loss: 36.3048 - sparse_categorical_accuracy: 0.3336
61/100 ━━━━━━━━━━━━[37m━━━━━━━━ 40s 1s/step - loss: 36.3055 - sparse_categorical_accuracy: 0.3336
62/100 ━━━━━━━━━━━━[37m━━━━━━━━ 39s 1s/step - loss: 36.3060 - sparse_categorical_accuracy: 0.3336
63/100 ━━━━━━━━━━━━[37m━━━━━━━━ 38s 1s/step - loss: 36.3065 - sparse_categorical_accuracy: 0.3337
64/100 ━━━━━━━━━━━━[37m━━━━━━━━ 37s 1s/step - loss: 36.3070 - sparse_categorical_accuracy: 0.3337
65/100 ━━━━━━━━━━━━━[37m━━━━━━━ 36s 1s/step - loss: 36.3075 - sparse_categorical_accuracy: 0.3338
66/100 ━━━━━━━━━━━━━[37m━━━━━━━ 35s 1s/step - loss: 36.3080 - sparse_categorical_accuracy: 0.3338
67/100 ━━━━━━━━━━━━━[37m━━━━━━━ 33s 1s/step - loss: 36.3088 - sparse_categorical_accuracy: 0.3338
68/100 ━━━━━━━━━━━━━[37m━━━━━━━ 32s 1s/step - loss: 36.3095 - sparse_categorical_accuracy: 0.3339
69/100 ━━━━━━━━━━━━━[37m━━━━━━━ 31s 1s/step - loss: 36.3101 - sparse_categorical_accuracy: 0.3339
70/100 ━━━━━━━━━━━━━━[37m━━━━━━ 30s 1s/step - loss: 36.3108 - sparse_categorical_accuracy: 0.3340
71/100 ━━━━━━━━━━━━━━[37m━━━━━━ 29s 1s/step - loss: 36.3115 - sparse_categorical_accuracy: 0.3341
72/100 ━━━━━━━━━━━━━━[37m━━━━━━ 28s 1s/step - loss: 36.3121 - sparse_categorical_accuracy: 0.3342
73/100 ━━━━━━━━━━━━━━[37m━━━━━━ 27s 1s/step - loss: 36.3127 - sparse_categorical_accuracy: 0.3342
74/100 ━━━━━━━━━━━━━━[37m━━━━━━ 26s 1s/step - loss: 36.3133 - sparse_categorical_accuracy: 0.3343
75/100 ━━━━━━━━━━━━━━━[37m━━━━━ 25s 1s/step - loss: 36.3142 - sparse_categorical_accuracy: 0.3344
76/100 ━━━━━━━━━━━━━━━[37m━━━━━ 24s 1s/step - loss: 36.3150 - sparse_categorical_accuracy: 0.3345
77/100 ━━━━━━━━━━━━━━━[37m━━━━━ 23s 1s/step - loss: 36.3158 - sparse_categorical_accuracy: 0.3345
78/100 ━━━━━━━━━━━━━━━[37m━━━━━ 22s 1s/step - loss: 36.3166 - sparse_categorical_accuracy: 0.3346
79/100 ━━━━━━━━━━━━━━━[37m━━━━━ 21s 1s/step - loss: 36.3174 - sparse_categorical_accuracy: 0.3347
80/100 ━━━━━━━━━━━━━━━━[37m━━━━ 20s 1s/step - loss: 36.3180 - sparse_categorical_accuracy: 0.3348
81/100 ━━━━━━━━━━━━━━━━[37m━━━━ 19s 1s/step - loss: 36.3186 - sparse_categorical_accuracy: 0.3350
82/100 ━━━━━━━━━━━━━━━━[37m━━━━ 18s 1s/step - loss: 36.3191 - sparse_categorical_accuracy: 0.3352
83/100 ━━━━━━━━━━━━━━━━[37m━━━━ 17s 1s/step - loss: 36.3194 - sparse_categorical_accuracy: 0.3353
84/100 ━━━━━━━━━━━━━━━━[37m━━━━ 16s 1s/step - loss: 36.3198 - sparse_categorical_accuracy: 0.3355
85/100 ━━━━━━━━━━━━━━━━━[37m━━━ 15s 1s/step - loss: 36.3201 - sparse_categorical_accuracy: 0.3357
86/100 ━━━━━━━━━━━━━━━━━[37m━━━ 14s 1s/step - loss: 36.3204 - sparse_categorical_accuracy: 0.3358
87/100 ━━━━━━━━━━━━━━━━━[37m━━━ 13s 1s/step - loss: 36.3207 - sparse_categorical_accuracy: 0.3359
88/100 ━━━━━━━━━━━━━━━━━[37m━━━ 12s 1s/step - loss: 36.3210 - sparse_categorical_accuracy: 0.3360
89/100 ━━━━━━━━━━━━━━━━━[37m━━━ 11s 1s/step - loss: 36.3215 - sparse_categorical_accuracy: 0.3361
90/100 ━━━━━━━━━━━━━━━━━━[37m━━ 10s 1s/step - loss: 36.3218 - sparse_categorical_accuracy: 0.3362
91/100 ━━━━━━━━━━━━━━━━━━[37m━━ 9s 1s/step - loss: 36.3222 - sparse_categorical_accuracy: 0.3363
92/100 ━━━━━━━━━━━━━━━━━━[37m━━ 8s 1s/step - loss: 36.3225 - sparse_categorical_accuracy: 0.3364
93/100 ━━━━━━━━━━━━━━━━━━[37m━━ 7s 1s/step - loss: 36.3228 - sparse_categorical_accuracy: 0.3365
94/100 ━━━━━━━━━━━━━━━━━━[37m━━ 6s 1s/step - loss: 36.3230 - sparse_categorical_accuracy: 0.3365
95/100 ━━━━━━━━━━━━━━━━━━━[37m━ 5s 1s/step - loss: 36.3232 - sparse_categorical_accuracy: 0.3366
96/100 ━━━━━━━━━━━━━━━━━━━[37m━ 4s 1s/step - loss: 36.3234 - sparse_categorical_accuracy: 0.3367
97/100 ━━━━━━━━━━━━━━━━━━━[37m━ 3s 1s/step - loss: 36.3235 - sparse_categorical_accuracy: 0.3368
98/100 ━━━━━━━━━━━━━━━━━━━[37m━ 2s 1s/step - loss: 36.3236 - sparse_categorical_accuracy: 0.3368
99/100 ━━━━━━━━━━━━━━━━━━━[37m━ 1s 1s/step - loss: 36.3236 - sparse_categorical_accuracy: 0.3369
100/100 ━━━━━━━━━━━━━━━━━━━━ 0s 1s/step - loss: 36.3222 - sparse_categorical_accuracy: 0.3370
100/100 ━━━━━━━━━━━━━━━━━━━━ 107s 1s/step - loss: 36.3207 - sparse_categorical_accuracy: 0.3371 - val_loss: 79361986265088.0000 - val_sparse_categorical_accuracy: 0.3680
Epoch 10/20
1/100 [37m━━━━━━━━━━━━━━━━━━━━ 58:50 36s/step - loss: 36.7173 - sparse_categorical_accuracy: 0.4062
2/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:42 1s/step - loss: 36.4852 - sparse_categorical_accuracy: 0.3906
3/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:38 1s/step - loss: 36.3769 - sparse_categorical_accuracy: 0.3819
4/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:38 1s/step - loss: 36.3024 - sparse_categorical_accuracy: 0.3822
5/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:36 1s/step - loss: 36.2685 - sparse_categorical_accuracy: 0.3845
6/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:35 1s/step - loss: 36.2423 - sparse_categorical_accuracy: 0.3855
7/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:34 1s/step - loss: 36.2239 - sparse_categorical_accuracy: 0.3840
8/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:33 1s/step - loss: 36.2047 - sparse_categorical_accuracy: 0.3843
9/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:32 1s/step - loss: 36.1833 - sparse_categorical_accuracy: 0.3837
10/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:31 1s/step - loss: 36.1658 - sparse_categorical_accuracy: 0.3825
11/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:29 1s/step - loss: 36.1490 - sparse_categorical_accuracy: 0.3816
12/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:28 1s/step - loss: 36.1342 - sparse_categorical_accuracy: 0.3804
13/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:27 1s/step - loss: 36.1258 - sparse_categorical_accuracy: 0.3792
14/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:26 1s/step - loss: 36.1192 - sparse_categorical_accuracy: 0.3783
15/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:26 1s/step - loss: 36.1131 - sparse_categorical_accuracy: 0.3771
16/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:25 1s/step - loss: 36.1093 - sparse_categorical_accuracy: 0.3756
17/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:24 1s/step - loss: 36.1054 - sparse_categorical_accuracy: 0.3740
18/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:23 1s/step - loss: 36.1022 - sparse_categorical_accuracy: 0.3727
19/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:22 1s/step - loss: 36.1001 - sparse_categorical_accuracy: 0.3713
20/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:21 1s/step - loss: 36.0968 - sparse_categorical_accuracy: 0.3706
21/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:20 1s/step - loss: 36.0938 - sparse_categorical_accuracy: 0.3700
22/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:19 1s/step - loss: 36.0911 - sparse_categorical_accuracy: 0.3692
23/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:18 1s/step - loss: 36.0882 - sparse_categorical_accuracy: 0.3684
24/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:16 1s/step - loss: 36.0863 - sparse_categorical_accuracy: 0.3673
25/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:16 1s/step - loss: 36.0843 - sparse_categorical_accuracy: 0.3664
26/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:15 1s/step - loss: 36.0827 - sparse_categorical_accuracy: 0.3657
27/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:14 1s/step - loss: 36.0816 - sparse_categorical_accuracy: 0.3648
28/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:13 1s/step - loss: 36.0803 - sparse_categorical_accuracy: 0.3640
29/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:11 1s/step - loss: 36.0787 - sparse_categorical_accuracy: 0.3633
30/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:10 1s/step - loss: 36.0772 - sparse_categorical_accuracy: 0.3627
31/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:09 1s/step - loss: 36.0758 - sparse_categorical_accuracy: 0.3622
32/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:08 1s/step - loss: 36.0746 - sparse_categorical_accuracy: 0.3617
33/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:08 1s/step - loss: 36.0738 - sparse_categorical_accuracy: 0.3611
34/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:06 1s/step - loss: 36.0728 - sparse_categorical_accuracy: 0.3605
35/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:06 1s/step - loss: 36.0722 - sparse_categorical_accuracy: 0.3600
36/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:05 1s/step - loss: 36.0717 - sparse_categorical_accuracy: 0.3595
37/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:04 1s/step - loss: 36.0716 - sparse_categorical_accuracy: 0.3590
38/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:03 1s/step - loss: 36.0718 - sparse_categorical_accuracy: 0.3585
39/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:02 1s/step - loss: 36.0723 - sparse_categorical_accuracy: 0.3580
40/100 ━━━━━━━━[37m━━━━━━━━━━━━ 1:01 1s/step - loss: 36.0727 - sparse_categorical_accuracy: 0.3574
41/100 ━━━━━━━━[37m━━━━━━━━━━━━ 59s 1s/step - loss: 36.0730 - sparse_categorical_accuracy: 0.3568
42/100 ━━━━━━━━[37m━━━━━━━━━━━━ 59s 1s/step - loss: 36.0735 - sparse_categorical_accuracy: 0.3562
43/100 ━━━━━━━━[37m━━━━━━━━━━━━ 58s 1s/step - loss: 36.0742 - sparse_categorical_accuracy: 0.3557
44/100 ━━━━━━━━[37m━━━━━━━━━━━━ 57s 1s/step - loss: 36.0748 - sparse_categorical_accuracy: 0.3552
45/100 ━━━━━━━━━[37m━━━━━━━━━━━ 56s 1s/step - loss: 36.0752 - sparse_categorical_accuracy: 0.3548
46/100 ━━━━━━━━━[37m━━━━━━━━━━━ 55s 1s/step - loss: 36.0757 - sparse_categorical_accuracy: 0.3544
47/100 ━━━━━━━━━[37m━━━━━━━━━━━ 53s 1s/step - loss: 36.0761 - sparse_categorical_accuracy: 0.3540
48/100 ━━━━━━━━━[37m━━━━━━━━━━━ 52s 1s/step - loss: 36.0769 - sparse_categorical_accuracy: 0.3536
49/100 ━━━━━━━━━[37m━━━━━━━━━━━ 52s 1s/step - loss: 36.0776 - sparse_categorical_accuracy: 0.3532
50/100 ━━━━━━━━━━[37m━━━━━━━━━━ 51s 1s/step - loss: 36.0782 - sparse_categorical_accuracy: 0.3529
51/100 ━━━━━━━━━━[37m━━━━━━━━━━ 49s 1s/step - loss: 36.0788 - sparse_categorical_accuracy: 0.3527
52/100 ━━━━━━━━━━[37m━━━━━━━━━━ 49s 1s/step - loss: 36.0793 - sparse_categorical_accuracy: 0.3525
53/100 ━━━━━━━━━━[37m━━━━━━━━━━ 47s 1s/step - loss: 36.0799 - sparse_categorical_accuracy: 0.3523
54/100 ━━━━━━━━━━[37m━━━━━━━━━━ 46s 1s/step - loss: 36.0804 - sparse_categorical_accuracy: 0.3521
55/100 ━━━━━━━━━━━[37m━━━━━━━━━ 46s 1s/step - loss: 36.0808 - sparse_categorical_accuracy: 0.3520
56/100 ━━━━━━━━━━━[37m━━━━━━━━━ 45s 1s/step - loss: 36.0812 - sparse_categorical_accuracy: 0.3519
57/100 ━━━━━━━━━━━[37m━━━━━━━━━ 44s 1s/step - loss: 36.0816 - sparse_categorical_accuracy: 0.3518
58/100 ━━━━━━━━━━━[37m━━━━━━━━━ 43s 1s/step - loss: 36.0819 - sparse_categorical_accuracy: 0.3517
59/100 ━━━━━━━━━━━[37m━━━━━━━━━ 42s 1s/step - loss: 36.0821 - sparse_categorical_accuracy: 0.3516
60/100 ━━━━━━━━━━━━[37m━━━━━━━━ 40s 1s/step - loss: 36.0823 - sparse_categorical_accuracy: 0.3515
61/100 ━━━━━━━━━━━━[37m━━━━━━━━ 39s 1s/step - loss: 36.0826 - sparse_categorical_accuracy: 0.3514
62/100 ━━━━━━━━━━━━[37m━━━━━━━━ 38s 1s/step - loss: 36.0829 - sparse_categorical_accuracy: 0.3513
63/100 ━━━━━━━━━━━━[37m━━━━━━━━ 37s 1s/step - loss: 36.0832 - sparse_categorical_accuracy: 0.3512
64/100 ━━━━━━━━━━━━[37m━━━━━━━━ 36s 1s/step - loss: 36.0835 - sparse_categorical_accuracy: 0.3511
65/100 ━━━━━━━━━━━━━[37m━━━━━━━ 35s 1s/step - loss: 36.0838 - sparse_categorical_accuracy: 0.3510
66/100 ━━━━━━━━━━━━━[37m━━━━━━━ 34s 1s/step - loss: 36.0841 - sparse_categorical_accuracy: 0.3508
67/100 ━━━━━━━━━━━━━[37m━━━━━━━ 33s 1s/step - loss: 36.0846 - sparse_categorical_accuracy: 0.3507
68/100 ━━━━━━━━━━━━━[37m━━━━━━━ 32s 1s/step - loss: 36.0851 - sparse_categorical_accuracy: 0.3505
69/100 ━━━━━━━━━━━━━[37m━━━━━━━ 31s 1s/step - loss: 36.0856 - sparse_categorical_accuracy: 0.3503
70/100 ━━━━━━━━━━━━━━[37m━━━━━━ 30s 1s/step - loss: 36.0861 - sparse_categorical_accuracy: 0.3501
71/100 ━━━━━━━━━━━━━━[37m━━━━━━ 29s 1s/step - loss: 36.0867 - sparse_categorical_accuracy: 0.3499
72/100 ━━━━━━━━━━━━━━[37m━━━━━━ 28s 1s/step - loss: 36.0872 - sparse_categorical_accuracy: 0.3497
73/100 ━━━━━━━━━━━━━━[37m━━━━━━ 27s 1s/step - loss: 36.0878 - sparse_categorical_accuracy: 0.3495
74/100 ━━━━━━━━━━━━━━[37m━━━━━━ 26s 1s/step - loss: 36.0883 - sparse_categorical_accuracy: 0.3494
75/100 ━━━━━━━━━━━━━━━[37m━━━━━ 25s 1s/step - loss: 36.0888 - sparse_categorical_accuracy: 0.3492
76/100 ━━━━━━━━━━━━━━━[37m━━━━━ 24s 1s/step - loss: 36.0894 - sparse_categorical_accuracy: 0.3490
77/100 ━━━━━━━━━━━━━━━[37m━━━━━ 23s 1s/step - loss: 36.0899 - sparse_categorical_accuracy: 0.3488
78/100 ━━━━━━━━━━━━━━━[37m━━━━━ 22s 1s/step - loss: 36.0903 - sparse_categorical_accuracy: 0.3487
79/100 ━━━━━━━━━━━━━━━[37m━━━━━ 21s 1s/step - loss: 36.0906 - sparse_categorical_accuracy: 0.3485
80/100 ━━━━━━━━━━━━━━━━[37m━━━━ 20s 1s/step - loss: 36.0911 - sparse_categorical_accuracy: 0.3484
81/100 ━━━━━━━━━━━━━━━━[37m━━━━ 19s 1s/step - loss: 36.0914 - sparse_categorical_accuracy: 0.3483
82/100 ━━━━━━━━━━━━━━━━[37m━━━━ 18s 1s/step - loss: 36.0917 - sparse_categorical_accuracy: 0.3482
83/100 ━━━━━━━━━━━━━━━━[37m━━━━ 17s 1s/step - loss: 36.0920 - sparse_categorical_accuracy: 0.3481
84/100 ━━━━━━━━━━━━━━━━[37m━━━━ 16s 1s/step - loss: 36.0922 - sparse_categorical_accuracy: 0.3480
85/100 ━━━━━━━━━━━━━━━━━[37m━━━ 15s 1s/step - loss: 36.0925 - sparse_categorical_accuracy: 0.3479
86/100 ━━━━━━━━━━━━━━━━━[37m━━━ 14s 1s/step - loss: 36.0928 - sparse_categorical_accuracy: 0.3478
87/100 ━━━━━━━━━━━━━━━━━[37m━━━ 13s 1s/step - loss: 36.0930 - sparse_categorical_accuracy: 0.3478
88/100 ━━━━━━━━━━━━━━━━━[37m━━━ 12s 1s/step - loss: 36.0932 - sparse_categorical_accuracy: 0.3477
89/100 ━━━━━━━━━━━━━━━━━[37m━━━ 11s 1s/step - loss: 36.0935 - sparse_categorical_accuracy: 0.3476
90/100 ━━━━━━━━━━━━━━━━━━[37m━━ 10s 1s/step - loss: 36.0937 - sparse_categorical_accuracy: 0.3476
91/100 ━━━━━━━━━━━━━━━━━━[37m━━ 9s 1s/step - loss: 36.0939 - sparse_categorical_accuracy: 0.3476
92/100 ━━━━━━━━━━━━━━━━━━[37m━━ 8s 1s/step - loss: 36.0941 - sparse_categorical_accuracy: 0.3475
93/100 ━━━━━━━━━━━━━━━━━━[37m━━ 7s 1s/step - loss: 36.0943 - sparse_categorical_accuracy: 0.3475
94/100 ━━━━━━━━━━━━━━━━━━[37m━━ 6s 1s/step - loss: 36.0944 - sparse_categorical_accuracy: 0.3475
95/100 ━━━━━━━━━━━━━━━━━━━[37m━ 5s 1s/step - loss: 36.0947 - sparse_categorical_accuracy: 0.3474
96/100 ━━━━━━━━━━━━━━━━━━━[37m━ 4s 1s/step - loss: 36.0950 - sparse_categorical_accuracy: 0.3474
97/100 ━━━━━━━━━━━━━━━━━━━[37m━ 3s 1s/step - loss: 36.0955 - sparse_categorical_accuracy: 0.3474
98/100 ━━━━━━━━━━━━━━━━━━━[37m━ 2s 1s/step - loss: 36.0961 - sparse_categorical_accuracy: 0.3474
99/100 ━━━━━━━━━━━━━━━━━━━[37m━ 1s 1s/step - loss: 36.0966 - sparse_categorical_accuracy: 0.3475
100/100 ━━━━━━━━━━━━━━━━━━━━ 0s 1s/step - loss: 36.0956 - sparse_categorical_accuracy: 0.3475
100/100 ━━━━━━━━━━━━━━━━━━━━ 142s 1s/step - loss: 36.0947 - sparse_categorical_accuracy: 0.3475 - val_loss: 14927241216.0000 - val_sparse_categorical_accuracy: 0.3054
Epoch 11/20
1/100 [37m━━━━━━━━━━━━━━━━━━━━ 58:42 36s/step - loss: 36.1768 - sparse_categorical_accuracy: 0.3438
2/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:38 1s/step - loss: 36.3035 - sparse_categorical_accuracy: 0.3125
3/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:39 1s/step - loss: 36.3690 - sparse_categorical_accuracy: 0.3090
4/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:39 1s/step - loss: 36.4012 - sparse_categorical_accuracy: 0.3138
5/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:37 1s/step - loss: 36.4168 - sparse_categorical_accuracy: 0.3198
6/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:35 1s/step - loss: 36.4449 - sparse_categorical_accuracy: 0.3247
7/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:34 1s/step - loss: 36.4684 - sparse_categorical_accuracy: 0.3287
8/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:33 1s/step - loss: 36.4986 - sparse_categorical_accuracy: 0.3305
9/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:31 1s/step - loss: 36.5271 - sparse_categorical_accuracy: 0.3328
10/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:30 1s/step - loss: 36.5636 - sparse_categorical_accuracy: 0.3336
11/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:29 1s/step - loss: 36.6122 - sparse_categorical_accuracy: 0.3342
12/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:28 1s/step - loss: 36.6884 - sparse_categorical_accuracy: 0.3348
13/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:27 1s/step - loss: 36.7833 - sparse_categorical_accuracy: 0.3353
14/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:26 1s/step - loss: 36.8994 - sparse_categorical_accuracy: 0.3350
15/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:26 1s/step - loss: 37.0178 - sparse_categorical_accuracy: 0.3349
16/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:25 1s/step - loss: 37.1292 - sparse_categorical_accuracy: 0.3337
17/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:24 1s/step - loss: 37.2272 - sparse_categorical_accuracy: 0.3332
18/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:23 1s/step - loss: 37.3126 - sparse_categorical_accuracy: 0.3323
19/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:22 1s/step - loss: 37.3916 - sparse_categorical_accuracy: 0.3314
20/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:21 1s/step - loss: 37.4582 - sparse_categorical_accuracy: 0.3308
21/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:20 1s/step - loss: 37.5152 - sparse_categorical_accuracy: 0.3302
22/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:19 1s/step - loss: 37.5639 - sparse_categorical_accuracy: 0.3298
23/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:18 1s/step - loss: 37.6056 - sparse_categorical_accuracy: 0.3292
24/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:17 1s/step - loss: 37.6425 - sparse_categorical_accuracy: 0.3286
25/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:16 1s/step - loss: 37.6735 - sparse_categorical_accuracy: 0.3283
26/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:15 1s/step - loss: 37.6993 - sparse_categorical_accuracy: 0.3281
27/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:14 1s/step - loss: 37.7214 - sparse_categorical_accuracy: 0.3280
28/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:13 1s/step - loss: 37.7406 - sparse_categorical_accuracy: 0.3277
29/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:12 1s/step - loss: 37.7565 - sparse_categorical_accuracy: 0.3274
30/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:11 1s/step - loss: 37.7714 - sparse_categorical_accuracy: 0.3272
31/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:10 1s/step - loss: 37.7842 - sparse_categorical_accuracy: 0.3268
32/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:09 1s/step - loss: 37.7953 - sparse_categorical_accuracy: 0.3264
33/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:08 1s/step - loss: 37.8040 - sparse_categorical_accuracy: 0.3260
34/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:07 1s/step - loss: 37.8219 - sparse_categorical_accuracy: 0.3258
35/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:06 1s/step - loss: 37.8379 - sparse_categorical_accuracy: 0.3256
36/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:05 1s/step - loss: 37.8525 - sparse_categorical_accuracy: 0.3254
37/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:04 1s/step - loss: 37.8659 - sparse_categorical_accuracy: 0.3253
38/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:03 1s/step - loss: 37.8796 - sparse_categorical_accuracy: 0.3250
39/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:02 1s/step - loss: 37.8931 - sparse_categorical_accuracy: 0.3247
40/100 ━━━━━━━━[37m━━━━━━━━━━━━ 1:01 1s/step - loss: 37.9096 - sparse_categorical_accuracy: 0.3244
41/100 ━━━━━━━━[37m━━━━━━━━━━━━ 1:00 1s/step - loss: 37.9253 - sparse_categorical_accuracy: 0.3241
42/100 ━━━━━━━━[37m━━━━━━━━━━━━ 59s 1s/step - loss: 37.9405 - sparse_categorical_accuracy: 0.3238
43/100 ━━━━━━━━[37m━━━━━━━━━━━━ 57s 1s/step - loss: 37.9553 - sparse_categorical_accuracy: 0.3236
44/100 ━━━━━━━━[37m━━━━━━━━━━━━ 56s 1s/step - loss: 37.9707 - sparse_categorical_accuracy: 0.3235
45/100 ━━━━━━━━━[37m━━━━━━━━━━━ 55s 1s/step - loss: 37.9869 - sparse_categorical_accuracy: 0.3232
46/100 ━━━━━━━━━[37m━━━━━━━━━━━ 54s 1s/step - loss: 38.0034 - sparse_categorical_accuracy: 0.3231
47/100 ━━━━━━━━━[37m━━━━━━━━━━━ 53s 1s/step - loss: 38.0206 - sparse_categorical_accuracy: 0.3229
48/100 ━━━━━━━━━[37m━━━━━━━━━━━ 52s 1s/step - loss: 38.0382 - sparse_categorical_accuracy: 0.3227
49/100 ━━━━━━━━━[37m━━━━━━━━━━━ 51s 1s/step - loss: 38.0558 - sparse_categorical_accuracy: 0.3226
50/100 ━━━━━━━━━━[37m━━━━━━━━━━ 50s 1s/step - loss: 38.0737 - sparse_categorical_accuracy: 0.3224
51/100 ━━━━━━━━━━[37m━━━━━━━━━━ 49s 1s/step - loss: 38.0920 - sparse_categorical_accuracy: 0.3222
52/100 ━━━━━━━━━━[37m━━━━━━━━━━ 48s 1s/step - loss: 38.1100 - sparse_categorical_accuracy: 0.3221
53/100 ━━━━━━━━━━[37m━━━━━━━━━━ 47s 1s/step - loss: 38.1299 - sparse_categorical_accuracy: 0.3220
54/100 ━━━━━━━━━━[37m━━━━━━━━━━ 46s 1s/step - loss: 38.1498 - sparse_categorical_accuracy: 0.3220
55/100 ━━━━━━━━━━━[37m━━━━━━━━━ 45s 1s/step - loss: 38.1689 - sparse_categorical_accuracy: 0.3219
56/100 ━━━━━━━━━━━[37m━━━━━━━━━ 44s 1s/step - loss: 38.1871 - sparse_categorical_accuracy: 0.3218
57/100 ━━━━━━━━━━━[37m━━━━━━━━━ 43s 1s/step - loss: 38.2045 - sparse_categorical_accuracy: 0.3217
58/100 ━━━━━━━━━━━[37m━━━━━━━━━ 42s 1s/step - loss: 38.2213 - sparse_categorical_accuracy: 0.3216
59/100 ━━━━━━━━━━━[37m━━━━━━━━━ 41s 1s/step - loss: 38.2376 - sparse_categorical_accuracy: 0.3215
60/100 ━━━━━━━━━━━━[37m━━━━━━━━ 40s 1s/step - loss: 38.2533 - sparse_categorical_accuracy: 0.3214
61/100 ━━━━━━━━━━━━[37m━━━━━━━━ 39s 1s/step - loss: 38.2683 - sparse_categorical_accuracy: 0.3213
62/100 ━━━━━━━━━━━━[37m━━━━━━━━ 38s 1s/step - loss: 38.2826 - sparse_categorical_accuracy: 0.3213
63/100 ━━━━━━━━━━━━[37m━━━━━━━━ 37s 1s/step - loss: 38.2961 - sparse_categorical_accuracy: 0.3212
64/100 ━━━━━━━━━━━━[37m━━━━━━━━ 36s 1s/step - loss: 38.3092 - sparse_categorical_accuracy: 0.3211
65/100 ━━━━━━━━━━━━━[37m━━━━━━━ 35s 1s/step - loss: 38.3217 - sparse_categorical_accuracy: 0.3210
66/100 ━━━━━━━━━━━━━[37m━━━━━━━ 34s 1s/step - loss: 38.3339 - sparse_categorical_accuracy: 0.3209
67/100 ━━━━━━━━━━━━━[37m━━━━━━━ 33s 1s/step - loss: 38.3452 - sparse_categorical_accuracy: 0.3208
68/100 ━━━━━━━━━━━━━[37m━━━━━━━ 32s 1s/step - loss: 38.3558 - sparse_categorical_accuracy: 0.3208
69/100 ━━━━━━━━━━━━━[37m━━━━━━━ 31s 1s/step - loss: 38.3657 - sparse_categorical_accuracy: 0.3207
70/100 ━━━━━━━━━━━━━━[37m━━━━━━ 30s 1s/step - loss: 38.3748 - sparse_categorical_accuracy: 0.3207
71/100 ━━━━━━━━━━━━━━[37m━━━━━━ 29s 1s/step - loss: 38.3835 - sparse_categorical_accuracy: 0.3206
72/100 ━━━━━━━━━━━━━━[37m━━━━━━ 28s 1s/step - loss: 38.3918 - sparse_categorical_accuracy: 0.3205
73/100 ━━━━━━━━━━━━━━[37m━━━━━━ 27s 1s/step - loss: 38.3994 - sparse_categorical_accuracy: 0.3204
74/100 ━━━━━━━━━━━━━━[37m━━━━━━ 26s 1s/step - loss: 38.4065 - sparse_categorical_accuracy: 0.3203
75/100 ━━━━━━━━━━━━━━━[37m━━━━━ 25s 1s/step - loss: 38.4139 - sparse_categorical_accuracy: 0.3202
76/100 ━━━━━━━━━━━━━━━[37m━━━━━ 24s 1s/step - loss: 38.4209 - sparse_categorical_accuracy: 0.3200
77/100 ━━━━━━━━━━━━━━━[37m━━━━━ 23s 1s/step - loss: 38.4286 - sparse_categorical_accuracy: 0.3199
78/100 ━━━━━━━━━━━━━━━[37m━━━━━ 22s 1s/step - loss: 38.4358 - sparse_categorical_accuracy: 0.3198
79/100 ━━━━━━━━━━━━━━━[37m━━━━━ 21s 1s/step - loss: 38.4423 - sparse_categorical_accuracy: 0.3197
80/100 ━━━━━━━━━━━━━━━━[37m━━━━ 20s 1s/step - loss: 38.4483 - sparse_categorical_accuracy: 0.3196
81/100 ━━━━━━━━━━━━━━━━[37m━━━━ 19s 1s/step - loss: 38.4539 - sparse_categorical_accuracy: 0.3196
82/100 ━━━━━━━━━━━━━━━━[37m━━━━ 18s 1s/step - loss: 38.4589 - sparse_categorical_accuracy: 0.3195
83/100 ━━━━━━━━━━━━━━━━[37m━━━━ 17s 1s/step - loss: 38.4636 - sparse_categorical_accuracy: 0.3195
84/100 ━━━━━━━━━━━━━━━━[37m━━━━ 16s 1s/step - loss: 38.4679 - sparse_categorical_accuracy: 0.3194
85/100 ━━━━━━━━━━━━━━━━━[37m━━━ 15s 1s/step - loss: 38.4719 - sparse_categorical_accuracy: 0.3194
86/100 ━━━━━━━━━━━━━━━━━[37m━━━ 14s 1s/step - loss: 38.4755 - sparse_categorical_accuracy: 0.3193
87/100 ━━━━━━━━━━━━━━━━━[37m━━━ 13s 1s/step - loss: 38.4788 - sparse_categorical_accuracy: 0.3193
88/100 ━━━━━━━━━━━━━━━━━[37m━━━ 12s 1s/step - loss: 38.4819 - sparse_categorical_accuracy: 0.3192
89/100 ━━━━━━━━━━━━━━━━━[37m━━━ 11s 1s/step - loss: 38.4846 - sparse_categorical_accuracy: 0.3191
90/100 ━━━━━━━━━━━━━━━━━━[37m━━ 10s 1s/step - loss: 38.4870 - sparse_categorical_accuracy: 0.3191
91/100 ━━━━━━━━━━━━━━━━━━[37m━━ 9s 1s/step - loss: 38.4891 - sparse_categorical_accuracy: 0.3190
92/100 ━━━━━━━━━━━━━━━━━━[37m━━ 8s 1s/step - loss: 38.4916 - sparse_categorical_accuracy: 0.3190
93/100 ━━━━━━━━━━━━━━━━━━[37m━━ 7s 1s/step - loss: 38.4937 - sparse_categorical_accuracy: 0.3189
94/100 ━━━━━━━━━━━━━━━━━━[37m━━ 6s 1s/step - loss: 38.4957 - sparse_categorical_accuracy: 0.3189
95/100 ━━━━━━━━━━━━━━━━━━━[37m━ 5s 1s/step - loss: 38.4974 - sparse_categorical_accuracy: 0.3188
96/100 ━━━━━━━━━━━━━━━━━━━[37m━ 4s 1s/step - loss: 38.4990 - sparse_categorical_accuracy: 0.3188
97/100 ━━━━━━━━━━━━━━━━━━━[37m━ 3s 1s/step - loss: 38.5005 - sparse_categorical_accuracy: 0.3188
98/100 ━━━━━━━━━━━━━━━━━━━[37m━ 2s 1s/step - loss: 38.5019 - sparse_categorical_accuracy: 0.3188
99/100 ━━━━━━━━━━━━━━━━━━━[37m━ 1s 1s/step - loss: 38.5032 - sparse_categorical_accuracy: 0.3187
100/100 ━━━━━━━━━━━━━━━━━━━━ 0s 1s/step - loss: 38.5028 - sparse_categorical_accuracy: 0.3187
100/100 ━━━━━━━━━━━━━━━━━━━━ 141s 1s/step - loss: 38.5024 - sparse_categorical_accuracy: 0.3187 - val_loss: 1930753792.0000 - val_sparse_categorical_accuracy: 0.2315
Epoch 12/20
1/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:00:07 36s/step - loss: 42.1152 - sparse_categorical_accuracy: 0.3750
2/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:38 1s/step - loss: 40.9939 - sparse_categorical_accuracy: 0.3359
3/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:36 997ms/step - loss: 40.3854 - sparse_categorical_accuracy: 0.3212
4/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:36 1s/step - loss: 40.0082 - sparse_categorical_accuracy: 0.3151
5/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:35 1s/step - loss: 39.7856 - sparse_categorical_accuracy: 0.3121
6/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:33 1000ms/step - loss: 39.6142 - sparse_categorical_accuracy: 0.3078
7/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:33 1s/step - loss: 39.4890 - sparse_categorical_accuracy: 0.3072
8/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:31 1000ms/step - loss: 39.3828 - sparse_categorical_accuracy: 0.3059
9/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:31 1s/step - loss: 39.2872 - sparse_categorical_accuracy: 0.3032
10/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:30 1s/step - loss: 39.1979 - sparse_categorical_accuracy: 0.3025
11/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:29 1s/step - loss: 39.1176 - sparse_categorical_accuracy: 0.3022
12/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:28 1s/step - loss: 39.0417 - sparse_categorical_accuracy: 0.3026
13/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:27 1s/step - loss: 38.9724 - sparse_categorical_accuracy: 0.3032
14/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:26 1s/step - loss: 38.9077 - sparse_categorical_accuracy: 0.3041
15/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:25 1s/step - loss: 38.8489 - sparse_categorical_accuracy: 0.3044
16/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:24 1s/step - loss: 38.7940 - sparse_categorical_accuracy: 0.3044
17/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:23 1s/step - loss: 38.7408 - sparse_categorical_accuracy: 0.3048
18/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:22 1s/step - loss: 38.6905 - sparse_categorical_accuracy: 0.3049
19/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:22 1s/step - loss: 38.6466 - sparse_categorical_accuracy: 0.3050
20/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:21 1s/step - loss: 38.6091 - sparse_categorical_accuracy: 0.3051
21/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:20 1s/step - loss: 38.5744 - sparse_categorical_accuracy: 0.3053
22/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:19 1s/step - loss: 38.5416 - sparse_categorical_accuracy: 0.3052
23/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:18 1s/step - loss: 38.5095 - sparse_categorical_accuracy: 0.3049
24/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:17 1s/step - loss: 38.4786 - sparse_categorical_accuracy: 0.3046
25/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:16 1s/step - loss: 38.4478 - sparse_categorical_accuracy: 0.3044
26/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:15 1s/step - loss: 38.4185 - sparse_categorical_accuracy: 0.3044
27/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:13 1s/step - loss: 38.3905 - sparse_categorical_accuracy: 0.3044
28/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:12 1s/step - loss: 38.3624 - sparse_categorical_accuracy: 0.3047
29/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:11 1s/step - loss: 38.3360 - sparse_categorical_accuracy: 0.3051
30/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:10 1s/step - loss: 38.3099 - sparse_categorical_accuracy: 0.3056
31/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:09 1s/step - loss: 38.2850 - sparse_categorical_accuracy: 0.3060
32/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:08 1s/step - loss: 38.2604 - sparse_categorical_accuracy: 0.3064
33/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:07 1s/step - loss: 38.2364 - sparse_categorical_accuracy: 0.3069
34/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:06 1s/step - loss: 38.2127 - sparse_categorical_accuracy: 0.3075
35/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:05 1s/step - loss: 38.1893 - sparse_categorical_accuracy: 0.3082
36/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:04 1s/step - loss: 38.1665 - sparse_categorical_accuracy: 0.3089
37/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:03 1s/step - loss: 38.1445 - sparse_categorical_accuracy: 0.3094
38/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:02 1s/step - loss: 38.1229 - sparse_categorical_accuracy: 0.3100
39/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:01 1s/step - loss: 38.1031 - sparse_categorical_accuracy: 0.3107
40/100 ━━━━━━━━[37m━━━━━━━━━━━━ 1:00 1s/step - loss: 38.0841 - sparse_categorical_accuracy: 0.3113
41/100 ━━━━━━━━[37m━━━━━━━━━━━━ 59s 1s/step - loss: 38.0655 - sparse_categorical_accuracy: 0.3119
42/100 ━━━━━━━━[37m━━━━━━━━━━━━ 58s 1s/step - loss: 38.0472 - sparse_categorical_accuracy: 0.3125
43/100 ━━━━━━━━[37m━━━━━━━━━━━━ 57s 1s/step - loss: 38.0293 - sparse_categorical_accuracy: 0.3130
44/100 ━━━━━━━━[37m━━━━━━━━━━━━ 56s 1s/step - loss: 38.0117 - sparse_categorical_accuracy: 0.3136
45/100 ━━━━━━━━━[37m━━━━━━━━━━━ 55s 1s/step - loss: 37.9946 - sparse_categorical_accuracy: 0.3140
46/100 ━━━━━━━━━[37m━━━━━━━━━━━ 54s 1s/step - loss: 37.9778 - sparse_categorical_accuracy: 0.3144
47/100 ━━━━━━━━━[37m━━━━━━━━━━━ 53s 1s/step - loss: 37.9615 - sparse_categorical_accuracy: 0.3149
48/100 ━━━━━━━━━[37m━━━━━━━━━━━ 52s 1s/step - loss: 37.9455 - sparse_categorical_accuracy: 0.3153
49/100 ━━━━━━━━━[37m━━━━━━━━━━━ 51s 1s/step - loss: 37.9298 - sparse_categorical_accuracy: 0.3156
50/100 ━━━━━━━━━━[37m━━━━━━━━━━ 50s 1s/step - loss: 37.9144 - sparse_categorical_accuracy: 0.3160
51/100 ━━━━━━━━━━[37m━━━━━━━━━━ 49s 1s/step - loss: 37.8994 - sparse_categorical_accuracy: 0.3163
52/100 ━━━━━━━━━━[37m━━━━━━━━━━ 48s 1s/step - loss: 37.8846 - sparse_categorical_accuracy: 0.3167
53/100 ━━━━━━━━━━[37m━━━━━━━━━━ 47s 1s/step - loss: 37.8702 - sparse_categorical_accuracy: 0.3171
54/100 ━━━━━━━━━━[37m━━━━━━━━━━ 46s 1s/step - loss: 37.8563 - sparse_categorical_accuracy: 0.3174
55/100 ━━━━━━━━━━━[37m━━━━━━━━━ 45s 1s/step - loss: 37.8424 - sparse_categorical_accuracy: 0.3178
56/100 ━━━━━━━━━━━[37m━━━━━━━━━ 44s 1s/step - loss: 37.8294 - sparse_categorical_accuracy: 0.3181
57/100 ━━━━━━━━━━━[37m━━━━━━━━━ 43s 1s/step - loss: 37.8166 - sparse_categorical_accuracy: 0.3184
58/100 ━━━━━━━━━━━[37m━━━━━━━━━ 42s 1s/step - loss: 37.8041 - sparse_categorical_accuracy: 0.3186
59/100 ━━━━━━━━━━━[37m━━━━━━━━━ 41s 1s/step - loss: 37.7917 - sparse_categorical_accuracy: 0.3189
60/100 ━━━━━━━━━━━━[37m━━━━━━━━ 40s 1s/step - loss: 37.7796 - sparse_categorical_accuracy: 0.3192
61/100 ━━━━━━━━━━━━[37m━━━━━━━━ 39s 1s/step - loss: 37.7678 - sparse_categorical_accuracy: 0.3194
62/100 ━━━━━━━━━━━━[37m━━━━━━━━ 38s 1s/step - loss: 37.7561 - sparse_categorical_accuracy: 0.3196
63/100 ━━━━━━━━━━━━[37m━━━━━━━━ 37s 1s/step - loss: 37.7444 - sparse_categorical_accuracy: 0.3198
64/100 ━━━━━━━━━━━━[37m━━━━━━━━ 36s 1s/step - loss: 37.7330 - sparse_categorical_accuracy: 0.3200
65/100 ━━━━━━━━━━━━━[37m━━━━━━━ 35s 1s/step - loss: 37.7218 - sparse_categorical_accuracy: 0.3202
66/100 ━━━━━━━━━━━━━[37m━━━━━━━ 34s 1s/step - loss: 37.7106 - sparse_categorical_accuracy: 0.3204
67/100 ━━━━━━━━━━━━━[37m━━━━━━━ 33s 1s/step - loss: 37.6996 - sparse_categorical_accuracy: 0.3205
68/100 ━━━━━━━━━━━━━[37m━━━━━━━ 32s 1s/step - loss: 37.6887 - sparse_categorical_accuracy: 0.3207
69/100 ━━━━━━━━━━━━━[37m━━━━━━━ 31s 1s/step - loss: 37.6780 - sparse_categorical_accuracy: 0.3209
70/100 ━━━━━━━━━━━━━━[37m━━━━━━ 30s 1s/step - loss: 37.6676 - sparse_categorical_accuracy: 0.3210
71/100 ━━━━━━━━━━━━━━[37m━━━━━━ 29s 1s/step - loss: 37.6572 - sparse_categorical_accuracy: 0.3212
72/100 ━━━━━━━━━━━━━━[37m━━━━━━ 28s 1s/step - loss: 37.6470 - sparse_categorical_accuracy: 0.3213
73/100 ━━━━━━━━━━━━━━[37m━━━━━━ 27s 1s/step - loss: 37.6370 - sparse_categorical_accuracy: 0.3215
74/100 ━━━━━━━━━━━━━━[37m━━━━━━ 26s 1s/step - loss: 37.6272 - sparse_categorical_accuracy: 0.3216
75/100 ━━━━━━━━━━━━━━━[37m━━━━━ 25s 1s/step - loss: 37.6175 - sparse_categorical_accuracy: 0.3218
76/100 ━━━━━━━━━━━━━━━[37m━━━━━ 24s 1s/step - loss: 37.6079 - sparse_categorical_accuracy: 0.3219
77/100 ━━━━━━━━━━━━━━━[37m━━━━━ 23s 1s/step - loss: 37.5986 - sparse_categorical_accuracy: 0.3221
78/100 ━━━━━━━━━━━━━━━[37m━━━━━ 22s 1s/step - loss: 37.5894 - sparse_categorical_accuracy: 0.3222
79/100 ━━━━━━━━━━━━━━━[37m━━━━━ 21s 1s/step - loss: 37.5804 - sparse_categorical_accuracy: 0.3223
80/100 ━━━━━━━━━━━━━━━━[37m━━━━ 20s 1s/step - loss: 37.5721 - sparse_categorical_accuracy: 0.3224
81/100 ━━━━━━━━━━━━━━━━[37m━━━━ 19s 1s/step - loss: 37.5639 - sparse_categorical_accuracy: 0.3226
82/100 ━━━━━━━━━━━━━━━━[37m━━━━ 18s 1s/step - loss: 37.5557 - sparse_categorical_accuracy: 0.3227
83/100 ━━━━━━━━━━━━━━━━[37m━━━━ 17s 1s/step - loss: 37.5477 - sparse_categorical_accuracy: 0.3229
84/100 ━━━━━━━━━━━━━━━━[37m━━━━ 16s 1s/step - loss: 37.5400 - sparse_categorical_accuracy: 0.3230
85/100 ━━━━━━━━━━━━━━━━━[37m━━━ 15s 1s/step - loss: 37.5324 - sparse_categorical_accuracy: 0.3232
86/100 ━━━━━━━━━━━━━━━━━[37m━━━ 14s 1s/step - loss: 37.5249 - sparse_categorical_accuracy: 0.3233
87/100 ━━━━━━━━━━━━━━━━━[37m━━━ 13s 1s/step - loss: 37.5174 - sparse_categorical_accuracy: 0.3235
88/100 ━━━━━━━━━━━━━━━━━[37m━━━ 12s 1s/step - loss: 37.5100 - sparse_categorical_accuracy: 0.3237
89/100 ━━━━━━━━━━━━━━━━━[37m━━━ 11s 1s/step - loss: 37.5027 - sparse_categorical_accuracy: 0.3238
90/100 ━━━━━━━━━━━━━━━━━━[37m━━ 10s 1s/step - loss: 37.4956 - sparse_categorical_accuracy: 0.3240
91/100 ━━━━━━━━━━━━━━━━━━[37m━━ 9s 1s/step - loss: 37.4886 - sparse_categorical_accuracy: 0.3241
92/100 ━━━━━━━━━━━━━━━━━━[37m━━ 8s 1s/step - loss: 37.4816 - sparse_categorical_accuracy: 0.3243
93/100 ━━━━━━━━━━━━━━━━━━[37m━━ 7s 1s/step - loss: 37.4747 - sparse_categorical_accuracy: 0.3244
94/100 ━━━━━━━━━━━━━━━━━━[37m━━ 6s 1s/step - loss: 37.4679 - sparse_categorical_accuracy: 0.3246
95/100 ━━━━━━━━━━━━━━━━━━━[37m━ 5s 1s/step - loss: 37.4613 - sparse_categorical_accuracy: 0.3247
96/100 ━━━━━━━━━━━━━━━━━━━[37m━ 4s 1s/step - loss: 37.4547 - sparse_categorical_accuracy: 0.3249
97/100 ━━━━━━━━━━━━━━━━━━━[37m━ 3s 1s/step - loss: 37.4482 - sparse_categorical_accuracy: 0.3250
98/100 ━━━━━━━━━━━━━━━━━━━[37m━ 2s 1s/step - loss: 37.4417 - sparse_categorical_accuracy: 0.3252
99/100 ━━━━━━━━━━━━━━━━━━━[37m━ 1s 1s/step - loss: 37.4353 - sparse_categorical_accuracy: 0.3253
100/100 ━━━━━━━━━━━━━━━━━━━━ 0s 1s/step - loss: 37.4279 - sparse_categorical_accuracy: 0.3255
100/100 ━━━━━━━━━━━━━━━━━━━━ 142s 1s/step - loss: 37.4206 - sparse_categorical_accuracy: 0.3256 - val_loss: 1793616557963500563988480.0000 - val_sparse_categorical_accuracy: 0.2328
Epoch 13/20
1/100 [37m━━━━━━━━━━━━━━━━━━━━ 59:52 36s/step - loss: 43.0665 - sparse_categorical_accuracy: 0.1875
2/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:41 1s/step - loss: 41.4007 - sparse_categorical_accuracy: 0.2344
3/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:38 1s/step - loss: 40.5478 - sparse_categorical_accuracy: 0.2361
4/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:37 1s/step - loss: 39.9836 - sparse_categorical_accuracy: 0.2513
5/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:37 1s/step - loss: 39.6005 - sparse_categorical_accuracy: 0.2623
6/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:37 1s/step - loss: 39.4050 - sparse_categorical_accuracy: 0.2663
7/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:36 1s/step - loss: 39.2307 - sparse_categorical_accuracy: 0.2659
8/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:35 1s/step - loss: 39.0731 - sparse_categorical_accuracy: 0.2688
9/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:33 1s/step - loss: 38.9341 - sparse_categorical_accuracy: 0.2721
10/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:32 1s/step - loss: 38.8113 - sparse_categorical_accuracy: 0.2768
11/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:31 1s/step - loss: 38.7010 - sparse_categorical_accuracy: 0.2811
12/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:30 1s/step - loss: 38.6074 - sparse_categorical_accuracy: 0.2837
13/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:29 1s/step - loss: 38.5211 - sparse_categorical_accuracy: 0.2853
14/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:27 1s/step - loss: 38.4446 - sparse_categorical_accuracy: 0.2863
15/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:26 1s/step - loss: 38.3741 - sparse_categorical_accuracy: 0.2876
16/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:25 1s/step - loss: 38.3085 - sparse_categorical_accuracy: 0.2893
17/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:24 1s/step - loss: 38.2497 - sparse_categorical_accuracy: 0.2910
18/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:23 1s/step - loss: 38.1954 - sparse_categorical_accuracy: 0.2925
19/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:22 1s/step - loss: 38.1438 - sparse_categorical_accuracy: 0.2942
20/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:21 1s/step - loss: 38.0973 - sparse_categorical_accuracy: 0.2962
21/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:20 1s/step - loss: 38.0548 - sparse_categorical_accuracy: 0.2978
22/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:19 1s/step - loss: 38.0137 - sparse_categorical_accuracy: 0.2996
23/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:18 1s/step - loss: 37.9745 - sparse_categorical_accuracy: 0.3013
24/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:17 1s/step - loss: 37.9374 - sparse_categorical_accuracy: 0.3029
25/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:16 1s/step - loss: 37.9020 - sparse_categorical_accuracy: 0.3044
26/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:15 1s/step - loss: 37.8688 - sparse_categorical_accuracy: 0.3058
27/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:14 1s/step - loss: 37.8374 - sparse_categorical_accuracy: 0.3069
28/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:13 1s/step - loss: 37.8071 - sparse_categorical_accuracy: 0.3081
29/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:12 1s/step - loss: 37.7780 - sparse_categorical_accuracy: 0.3092
30/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:11 1s/step - loss: 37.7549 - sparse_categorical_accuracy: 0.3103
31/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:10 1s/step - loss: 37.7322 - sparse_categorical_accuracy: 0.3112
32/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:09 1s/step - loss: 37.7103 - sparse_categorical_accuracy: 0.3122
33/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:08 1s/step - loss: 37.6895 - sparse_categorical_accuracy: 0.3130
34/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:07 1s/step - loss: 37.6693 - sparse_categorical_accuracy: 0.3139
35/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:06 1s/step - loss: 37.6500 - sparse_categorical_accuracy: 0.3147
36/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:05 1s/step - loss: 37.6313 - sparse_categorical_accuracy: 0.3155
37/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:04 1s/step - loss: 37.6136 - sparse_categorical_accuracy: 0.3163
38/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:03 1s/step - loss: 37.5964 - sparse_categorical_accuracy: 0.3170
39/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:02 1s/step - loss: 37.5801 - sparse_categorical_accuracy: 0.3176
40/100 ━━━━━━━━[37m━━━━━━━━━━━━ 1:00 1s/step - loss: 37.5643 - sparse_categorical_accuracy: 0.3182
41/100 ━━━━━━━━[37m━━━━━━━━━━━━ 1:00 1s/step - loss: 37.5490 - sparse_categorical_accuracy: 0.3187
42/100 ━━━━━━━━[37m━━━━━━━━━━━━ 59s 1s/step - loss: 37.5343 - sparse_categorical_accuracy: 0.3192
43/100 ━━━━━━━━[37m━━━━━━━━━━━━ 58s 1s/step - loss: 37.5202 - sparse_categorical_accuracy: 0.3197
44/100 ━━━━━━━━[37m━━━━━━━━━━━━ 57s 1s/step - loss: 37.5065 - sparse_categorical_accuracy: 0.3202
45/100 ━━━━━━━━━[37m━━━━━━━━━━━ 56s 1s/step - loss: 37.4937 - sparse_categorical_accuracy: 0.3207
46/100 ━━━━━━━━━[37m━━━━━━━━━━━ 55s 1s/step - loss: 37.4820 - sparse_categorical_accuracy: 0.3210
47/100 ━━━━━━━━━[37m━━━━━━━━━━━ 54s 1s/step - loss: 37.4705 - sparse_categorical_accuracy: 0.3213
48/100 ━━━━━━━━━[37m━━━━━━━━━━━ 52s 1s/step - loss: 37.4600 - sparse_categorical_accuracy: 0.3216
49/100 ━━━━━━━━━[37m━━━━━━━━━━━ 51s 1s/step - loss: 37.4499 - sparse_categorical_accuracy: 0.3220
50/100 ━━━━━━━━━━[37m━━━━━━━━━━ 50s 1s/step - loss: 37.4459 - sparse_categorical_accuracy: 0.3223
51/100 ━━━━━━━━━━[37m━━━━━━━━━━ 49s 1s/step - loss: 37.4418 - sparse_categorical_accuracy: 0.3226
52/100 ━━━━━━━━━━[37m━━━━━━━━━━ 48s 1s/step - loss: 37.4394 - sparse_categorical_accuracy: 0.3229
53/100 ━━━━━━━━━━[37m━━━━━━━━━━ 47s 1s/step - loss: 37.4379 - sparse_categorical_accuracy: 0.3231
54/100 ━━━━━━━━━━[37m━━━━━━━━━━ 46s 1s/step - loss: 37.4367 - sparse_categorical_accuracy: 0.3233
55/100 ━━━━━━━━━━━[37m━━━━━━━━━ 45s 1s/step - loss: 37.4355 - sparse_categorical_accuracy: 0.3234
56/100 ━━━━━━━━━━━[37m━━━━━━━━━ 44s 1s/step - loss: 37.4344 - sparse_categorical_accuracy: 0.3236
57/100 ━━━━━━━━━━━[37m━━━━━━━━━ 43s 1s/step - loss: 37.4333 - sparse_categorical_accuracy: 0.3237
58/100 ━━━━━━━━━━━[37m━━━━━━━━━ 42s 1s/step - loss: 37.4332 - sparse_categorical_accuracy: 0.3239
59/100 ━━━━━━━━━━━[37m━━━━━━━━━ 41s 1s/step - loss: 37.4330 - sparse_categorical_accuracy: 0.3240
60/100 ━━━━━━━━━━━━[37m━━━━━━━━ 40s 1s/step - loss: 37.4355 - sparse_categorical_accuracy: 0.3242
61/100 ━━━━━━━━━━━━[37m━━━━━━━━ 39s 1s/step - loss: 37.4376 - sparse_categorical_accuracy: 0.3243
62/100 ━━━━━━━━━━━━[37m━━━━━━━━ 38s 1s/step - loss: 37.4397 - sparse_categorical_accuracy: 0.3244
63/100 ━━━━━━━━━━━━[37m━━━━━━━━ 37s 1s/step - loss: 37.4570 - sparse_categorical_accuracy: 0.3245
64/100 ━━━━━━━━━━━━[37m━━━━━━━━ 36s 1s/step - loss: 37.4780 - sparse_categorical_accuracy: 0.3246
65/100 ━━━━━━━━━━━━━[37m━━━━━━━ 35s 1s/step - loss: 37.4992 - sparse_categorical_accuracy: 0.3246
66/100 ━━━━━━━━━━━━━[37m━━━━━━━ 34s 1s/step - loss: 37.5211 - sparse_categorical_accuracy: 0.3247
67/100 ━━━━━━━━━━━━━[37m━━━━━━━ 33s 1s/step - loss: 37.5453 - sparse_categorical_accuracy: 0.3248
68/100 ━━━━━━━━━━━━━[37m━━━━━━━ 32s 1s/step - loss: 37.6848 - sparse_categorical_accuracy: 0.3249
69/100 ━━━━━━━━━━━━━[37m━━━━━━━ 31s 1s/step - loss: 37.8449 - sparse_categorical_accuracy: 0.3250
70/100 ━━━━━━━━━━━━━━[37m━━━━━━ 30s 1s/step - loss: 38.0000 - sparse_categorical_accuracy: 0.3250
71/100 ━━━━━━━━━━━━━━[37m━━━━━━ 29s 1s/step - loss: 38.1557 - sparse_categorical_accuracy: 0.3251
72/100 ━━━━━━━━━━━━━━[37m━━━━━━ 28s 1s/step - loss: 38.5126 - sparse_categorical_accuracy: 0.3250
73/100 ━━━━━━━━━━━━━━[37m━━━━━━ 27s 1s/step - loss: 39.0564 - sparse_categorical_accuracy: 0.3250
74/100 ━━━━━━━━━━━━━━[37m━━━━━━ 26s 1s/step - loss: 39.5901 - sparse_categorical_accuracy: 0.3249
75/100 ━━━━━━━━━━━━━━━[37m━━━━━ 25s 1s/step - loss: 40.1041 - sparse_categorical_accuracy: 0.3249
76/100 ━━━━━━━━━━━━━━━[37m━━━━━ 24s 1s/step - loss: 40.6028 - sparse_categorical_accuracy: 0.3248
77/100 ━━━━━━━━━━━━━━━[37m━━━━━ 23s 1s/step - loss: 41.1546 - sparse_categorical_accuracy: 0.3247
78/100 ━━━━━━━━━━━━━━━[37m━━━━━ 22s 1s/step - loss: 41.7197 - sparse_categorical_accuracy: 0.3246
79/100 ━━━━━━━━━━━━━━━[37m━━━━━ 21s 1s/step - loss: 42.2922 - sparse_categorical_accuracy: 0.3245
80/100 ━━━━━━━━━━━━━━━━[37m━━━━ 20s 1s/step - loss: 42.8838 - sparse_categorical_accuracy: 0.3244
81/100 ━━━━━━━━━━━━━━━━[37m━━━━ 19s 1s/step - loss: 43.4631 - sparse_categorical_accuracy: 0.3243
82/100 ━━━━━━━━━━━━━━━━[37m━━━━ 18s 1s/step - loss: 44.0304 - sparse_categorical_accuracy: 0.3242
83/100 ━━━━━━━━━━━━━━━━[37m━━━━ 17s 1s/step - loss: 44.8038 - sparse_categorical_accuracy: 0.3241
84/100 ━━━━━━━━━━━━━━━━[37m━━━━ 16s 1s/step - loss: 45.5640 - sparse_categorical_accuracy: 0.3240
85/100 ━━━━━━━━━━━━━━━━━[37m━━━ 15s 1s/step - loss: 46.2985 - sparse_categorical_accuracy: 0.3240
86/100 ━━━━━━━━━━━━━━━━━[37m━━━ 14s 1s/step - loss: 47.0196 - sparse_categorical_accuracy: 0.3239
87/100 ━━━━━━━━━━━━━━━━━[37m━━━ 13s 1s/step - loss: 47.7189 - sparse_categorical_accuracy: 0.3238
88/100 ━━━━━━━━━━━━━━━━━[37m━━━ 12s 1s/step - loss: 48.3950 - sparse_categorical_accuracy: 0.3237
89/100 ━━━━━━━━━━━━━━━━━[37m━━━ 11s 1s/step - loss: 49.0544 - sparse_categorical_accuracy: 0.3236
90/100 ━━━━━━━━━━━━━━━━━━[37m━━ 10s 1s/step - loss: 49.6933 - sparse_categorical_accuracy: 0.3235
91/100 ━━━━━━━━━━━━━━━━━━[37m━━ 9s 1s/step - loss: 50.3141 - sparse_categorical_accuracy: 0.3234
92/100 ━━━━━━━━━━━━━━━━━━[37m━━ 8s 1s/step - loss: 51.0231 - sparse_categorical_accuracy: 0.3234
93/100 ━━━━━━━━━━━━━━━━━━[37m━━ 7s 1s/step - loss: 51.7102 - sparse_categorical_accuracy: 0.3233
94/100 ━━━━━━━━━━━━━━━━━━[37m━━ 6s 1s/step - loss: 52.3764 - sparse_categorical_accuracy: 0.3232
95/100 ━━━━━━━━━━━━━━━━━━━[37m━ 5s 1s/step - loss: 53.0224 - sparse_categorical_accuracy: 0.3231
96/100 ━━━━━━━━━━━━━━━━━━━[37m━ 4s 1s/step - loss: 53.6491 - sparse_categorical_accuracy: 0.3230
97/100 ━━━━━━━━━━━━━━━━━━━[37m━ 3s 1s/step - loss: 54.2575 - sparse_categorical_accuracy: 0.3230
98/100 ━━━━━━━━━━━━━━━━━━━[37m━ 2s 1s/step - loss: 54.8483 - sparse_categorical_accuracy: 0.3229
99/100 ━━━━━━━━━━━━━━━━━━━[37m━ 1s 1s/step - loss: 55.4269 - sparse_categorical_accuracy: 0.3228
100/100 ━━━━━━━━━━━━━━━━━━━━ 0s 1s/step - loss: 55.9873 - sparse_categorical_accuracy: 0.3227
100/100 ━━━━━━━━━━━━━━━━━━━━ 142s 1s/step - loss: 56.5366 - sparse_categorical_accuracy: 0.3226 - val_loss: 505209651200.0000 - val_sparse_categorical_accuracy: 0.2528
Epoch 14/20
1/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:46 1s/step - loss: 72.5004 - sparse_categorical_accuracy: 0.2812
2/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:37 992ms/step - loss: 84.3191 - sparse_categorical_accuracy: 0.2891
3/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:36 995ms/step - loss: 86.3062 - sparse_categorical_accuracy: 0.2865
4/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:36 1s/step - loss: 102.5759 - sparse_categorical_accuracy: 0.2891
5/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:36 1s/step - loss: 111.2810 - sparse_categorical_accuracy: 0.2925
6/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:34 1s/step - loss: 116.4263 - sparse_categorical_accuracy: 0.2950
7/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:33 1s/step - loss: 120.4184 - sparse_categorical_accuracy: 0.2949
8/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:32 1s/step - loss: 122.9799 - sparse_categorical_accuracy: 0.2976
9/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:32 1s/step - loss: 123.9803 - sparse_categorical_accuracy: 0.2985
10/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:31 1s/step - loss: 124.1441 - sparse_categorical_accuracy: 0.2996
11/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:30 1s/step - loss: 123.8266 - sparse_categorical_accuracy: 0.2997
12/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:29 1s/step - loss: 148.8502 - sparse_categorical_accuracy: 0.2999
13/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:28 1s/step - loss: 167.8486 - sparse_categorical_accuracy: 0.3009
14/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:27 1s/step - loss: 182.3929 - sparse_categorical_accuracy: 0.3014
15/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:27 1s/step - loss: 193.6643 - sparse_categorical_accuracy: 0.3017
16/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:25 1s/step - loss: 202.4236 - sparse_categorical_accuracy: 0.3023
17/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:24 1s/step - loss: 209.2320 - sparse_categorical_accuracy: 0.3023
18/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:23 1s/step - loss: 215.1761 - sparse_categorical_accuracy: 0.3022
19/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:22 1s/step - loss: 219.8418 - sparse_categorical_accuracy: 0.3026
20/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:21 1s/step - loss: 241.0950 - sparse_categorical_accuracy: 0.3032
21/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:20 1s/step - loss: 262.8609 - sparse_categorical_accuracy: 0.3038
22/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:19 1s/step - loss: 281.3412 - sparse_categorical_accuracy: 0.3045
23/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:18 1s/step - loss: 297.2592 - sparse_categorical_accuracy: 0.3051
24/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:17 1s/step - loss: 310.9528 - sparse_categorical_accuracy: 0.3058
25/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:16 1s/step - loss: 322.7583 - sparse_categorical_accuracy: 0.3064
26/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:15 1s/step - loss: 333.3093 - sparse_categorical_accuracy: 0.3068
27/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:14 1s/step - loss: 346.8104 - sparse_categorical_accuracy: 0.3072
28/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:13 1s/step - loss: 358.5458 - sparse_categorical_accuracy: 0.3073
29/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:12 1s/step - loss: 368.7500 - sparse_categorical_accuracy: 0.3072
30/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:11 1s/step - loss: 378.8999 - sparse_categorical_accuracy: 0.3072
31/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:10 1s/step - loss: 388.4263 - sparse_categorical_accuracy: 0.3071
32/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:09 1s/step - loss: 396.7980 - sparse_categorical_accuracy: 0.3070
33/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:08 1s/step - loss: 404.4334 - sparse_categorical_accuracy: 0.3069
34/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:07 1s/step - loss: 411.2321 - sparse_categorical_accuracy: 0.3070
35/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:06 1s/step - loss: 417.2190 - sparse_categorical_accuracy: 0.3070
36/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:05 1s/step - loss: 422.5132 - sparse_categorical_accuracy: 0.3070
37/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:04 1s/step - loss: 427.1383 - sparse_categorical_accuracy: 0.3070
38/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:03 1s/step - loss: 431.2506 - sparse_categorical_accuracy: 0.3070
39/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:02 1s/step - loss: 434.8232 - sparse_categorical_accuracy: 0.3070
40/100 ━━━━━━━━[37m━━━━━━━━━━━━ 1:01 1s/step - loss: 437.9098 - sparse_categorical_accuracy: 0.3068
41/100 ━━━━━━━━[37m━━━━━━━━━━━━ 1:00 1s/step - loss: 440.6833 - sparse_categorical_accuracy: 0.3066
42/100 ━━━━━━━━[37m━━━━━━━━━━━━ 59s 1s/step - loss: 443.0559 - sparse_categorical_accuracy: 0.3064
43/100 ━━━━━━━━[37m━━━━━━━━━━━━ 58s 1s/step - loss: 445.1284 - sparse_categorical_accuracy: 0.3063
44/100 ━━━━━━━━[37m━━━━━━━━━━━━ 57s 1s/step - loss: 446.8688 - sparse_categorical_accuracy: 0.3062
45/100 ━━━━━━━━━[37m━━━━━━━━━━━ 56s 1s/step - loss: 448.4276 - sparse_categorical_accuracy: 0.3060
46/100 ━━━━━━━━━[37m━━━━━━━━━━━ 55s 1s/step - loss: 449.8117 - sparse_categorical_accuracy: 0.3059
47/100 ━━━━━━━━━[37m━━━━━━━━━━━ 54s 1s/step - loss: 450.9800 - sparse_categorical_accuracy: 0.3058
48/100 ━━━━━━━━━[37m━━━━━━━━━━━ 53s 1s/step - loss: 451.9573 - sparse_categorical_accuracy: 0.3058
49/100 ━━━━━━━━━[37m━━━━━━━━━━━ 52s 1s/step - loss: 452.7186 - sparse_categorical_accuracy: 0.3058
50/100 ━━━━━━━━━━[37m━━━━━━━━━━ 51s 1s/step - loss: 453.3130 - sparse_categorical_accuracy: 0.3058
51/100 ━━━━━━━━━━[37m━━━━━━━━━━ 50s 1s/step - loss: 453.7388 - sparse_categorical_accuracy: 0.3057
52/100 ━━━━━━━━━━[37m━━━━━━━━━━ 49s 1s/step - loss: 454.0486 - sparse_categorical_accuracy: 0.3056
53/100 ━━━━━━━━━━[37m━━━━━━━━━━ 48s 1s/step - loss: 454.2064 - sparse_categorical_accuracy: 0.3055
54/100 ━━━━━━━━━━[37m━━━━━━━━━━ 46s 1s/step - loss: 454.2328 - sparse_categorical_accuracy: 0.3053
55/100 ━━━━━━━━━━━[37m━━━━━━━━━ 46s 1s/step - loss: 454.1332 - sparse_categorical_accuracy: 0.3052
56/100 ━━━━━━━━━━━[37m━━━━━━━━━ 44s 1s/step - loss: 453.9173 - sparse_categorical_accuracy: 0.3050
57/100 ━━━━━━━━━━━[37m━━━━━━━━━ 43s 1s/step - loss: 453.5970 - sparse_categorical_accuracy: 0.3048
58/100 ━━━━━━━━━━━[37m━━━━━━━━━ 42s 1s/step - loss: 453.1803 - sparse_categorical_accuracy: 0.3046
59/100 ━━━━━━━━━━━[37m━━━━━━━━━ 41s 1s/step - loss: 452.6779 - sparse_categorical_accuracy: 0.3044
60/100 ━━━━━━━━━━━━[37m━━━━━━━━ 40s 1s/step - loss: 452.0964 - sparse_categorical_accuracy: 0.3042
61/100 ━━━━━━━━━━━━[37m━━━━━━━━ 39s 1s/step - loss: 451.4410 - sparse_categorical_accuracy: 0.3040
62/100 ━━━━━━━━━━━━[37m━━━━━━━━ 38s 1s/step - loss: 450.7515 - sparse_categorical_accuracy: 0.3038
63/100 ━━━━━━━━━━━━[37m━━━━━━━━ 37s 1s/step - loss: 449.9997 - sparse_categorical_accuracy: 0.3036
64/100 ━━━━━━━━━━━━[37m━━━━━━━━ 36s 1s/step - loss: 449.1942 - sparse_categorical_accuracy: 0.3034
65/100 ━━━━━━━━━━━━━[37m━━━━━━━ 35s 1s/step - loss: 448.3498 - sparse_categorical_accuracy: 0.3032
66/100 ━━━━━━━━━━━━━[37m━━━━━━━ 34s 1s/step - loss: 447.4845 - sparse_categorical_accuracy: 0.3030
67/100 ━━━━━━━━━━━━━[37m━━━━━━━ 33s 1s/step - loss: 446.5741 - sparse_categorical_accuracy: 0.3028
68/100 ━━━━━━━━━━━━━[37m━━━━━━━ 32s 1s/step - loss: 445.6242 - sparse_categorical_accuracy: 0.3026
69/100 ━━━━━━━━━━━━━[37m━━━━━━━ 31s 1s/step - loss: 444.6494 - sparse_categorical_accuracy: 0.3024
70/100 ━━━━━━━━━━━━━━[37m━━━━━━ 30s 1s/step - loss: 443.6421 - sparse_categorical_accuracy: 0.3022
71/100 ━━━━━━━━━━━━━━[37m━━━━━━ 29s 1s/step - loss: 442.6296 - sparse_categorical_accuracy: 0.3020
72/100 ━━━━━━━━━━━━━━[37m━━━━━━ 28s 1s/step - loss: 441.5871 - sparse_categorical_accuracy: 0.3019
73/100 ━━━━━━━━━━━━━━[37m━━━━━━ 27s 1s/step - loss: 440.5179 - sparse_categorical_accuracy: 0.3017
74/100 ━━━━━━━━━━━━━━[37m━━━━━━ 26s 1s/step - loss: 439.4271 - sparse_categorical_accuracy: 0.3016
75/100 ━━━━━━━━━━━━━━━[37m━━━━━ 25s 1s/step - loss: 438.3216 - sparse_categorical_accuracy: 0.3014
76/100 ━━━━━━━━━━━━━━━[37m━━━━━ 24s 1s/step - loss: 437.1978 - sparse_categorical_accuracy: 0.3013
77/100 ━━━━━━━━━━━━━━━[37m━━━━━ 23s 1s/step - loss: 436.0553 - sparse_categorical_accuracy: 0.3012
78/100 ━━━━━━━━━━━━━━━[37m━━━━━ 22s 1s/step - loss: 434.9005 - sparse_categorical_accuracy: 0.3011
79/100 ━━━━━━━━━━━━━━━[37m━━━━━ 21s 1s/step - loss: 433.7516 - sparse_categorical_accuracy: 0.3010
80/100 ━━━━━━━━━━━━━━━━[37m━━━━ 20s 1s/step - loss: 432.6144 - sparse_categorical_accuracy: 0.3010
81/100 ━━━━━━━━━━━━━━━━[37m━━━━ 19s 1s/step - loss: 431.4657 - sparse_categorical_accuracy: 0.3010
82/100 ━━━━━━━━━━━━━━━━[37m━━━━ 18s 1s/step - loss: 430.3048 - sparse_categorical_accuracy: 0.3009
83/100 ━━━━━━━━━━━━━━━━[37m━━━━ 17s 1s/step - loss: 429.1349 - sparse_categorical_accuracy: 0.3009
84/100 ━━━━━━━━━━━━━━━━[37m━━━━ 16s 1s/step - loss: 427.9555 - sparse_categorical_accuracy: 0.3009
85/100 ━━━━━━━━━━━━━━━━━[37m━━━ 15s 1s/step - loss: 426.7693 - sparse_categorical_accuracy: 0.3009
86/100 ━━━━━━━━━━━━━━━━━[37m━━━ 14s 1s/step - loss: 425.5820 - sparse_categorical_accuracy: 0.3009
87/100 ━━━━━━━━━━━━━━━━━[37m━━━ 13s 1s/step - loss: 424.3880 - sparse_categorical_accuracy: 0.3009
88/100 ━━━━━━━━━━━━━━━━━[37m━━━ 12s 1s/step - loss: 423.1917 - sparse_categorical_accuracy: 0.3009
89/100 ━━━━━━━━━━━━━━━━━[37m━━━ 11s 1s/step - loss: 421.9930 - sparse_categorical_accuracy: 0.3009
90/100 ━━━━━━━━━━━━━━━━━━[37m━━ 10s 1s/step - loss: 420.7901 - sparse_categorical_accuracy: 0.3008
91/100 ━━━━━━━━━━━━━━━━━━[37m━━ 9s 1s/step - loss: 419.5866 - sparse_categorical_accuracy: 0.3008
92/100 ━━━━━━━━━━━━━━━━━━[37m━━ 8s 1s/step - loss: 418.3845 - sparse_categorical_accuracy: 0.3008
93/100 ━━━━━━━━━━━━━━━━━━[37m━━ 7s 1s/step - loss: 417.1804 - sparse_categorical_accuracy: 0.3008
94/100 ━━━━━━━━━━━━━━━━━━[37m━━ 6s 1s/step - loss: 415.9749 - sparse_categorical_accuracy: 0.3008
95/100 ━━━━━━━━━━━━━━━━━━━[37m━ 5s 1s/step - loss: 414.7687 - sparse_categorical_accuracy: 0.3008
96/100 ━━━━━━━━━━━━━━━━━━━[37m━ 4s 1s/step - loss: 413.5732 - sparse_categorical_accuracy: 0.3007
97/100 ━━━━━━━━━━━━━━━━━━━[37m━ 3s 1s/step - loss: 412.3854 - sparse_categorical_accuracy: 0.3007
98/100 ━━━━━━━━━━━━━━━━━━━[37m━ 2s 1s/step - loss: 411.1977 - sparse_categorical_accuracy: 0.3007
99/100 ━━━━━━━━━━━━━━━━━━━[37m━ 1s 1s/step - loss: 410.0114 - sparse_categorical_accuracy: 0.3007
100/100 ━━━━━━━━━━━━━━━━━━━━ 0s 1s/step - loss: 408.8264 - sparse_categorical_accuracy: 0.3007
100/100 ━━━━━━━━━━━━━━━━━━━━ 107s 1s/step - loss: 407.6649 - sparse_categorical_accuracy: 0.3007 - val_loss: 35970580884750336.0000 - val_sparse_categorical_accuracy: 0.3392
Epoch 15/20
1/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:41 1s/step - loss: 67.1360 - sparse_categorical_accuracy: 0.1875
2/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:37 999ms/step - loss: 67.1150 - sparse_categorical_accuracy: 0.2500
3/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:37 1s/step - loss: 72.1596 - sparse_categorical_accuracy: 0.2743
4/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:36 1s/step - loss: 73.8228 - sparse_categorical_accuracy: 0.2741
5/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:36 1s/step - loss: 74.3511 - sparse_categorical_accuracy: 0.2730
6/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:35 1s/step - loss: 75.8008 - sparse_categorical_accuracy: 0.2779
7/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:34 1s/step - loss: 76.9862 - sparse_categorical_accuracy: 0.2841
8/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:33 1s/step - loss: 77.6230 - sparse_categorical_accuracy: 0.2891
9/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:32 1s/step - loss: 78.0145 - sparse_categorical_accuracy: 0.2932
10/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:31 1s/step - loss: 78.4696 - sparse_categorical_accuracy: 0.2986
11/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:30 1s/step - loss: 78.7647 - sparse_categorical_accuracy: 0.3035
12/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:29 1s/step - loss: 78.8917 - sparse_categorical_accuracy: 0.3075
13/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:28 1s/step - loss: 79.0025 - sparse_categorical_accuracy: 0.3108
14/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:27 1s/step - loss: 79.0261 - sparse_categorical_accuracy: 0.3135
15/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:26 1s/step - loss: 79.1682 - sparse_categorical_accuracy: 0.3158
16/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:25 1s/step - loss: 79.2325 - sparse_categorical_accuracy: 0.3180
17/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:24 1s/step - loss: 79.3086 - sparse_categorical_accuracy: 0.3197
18/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:23 1s/step - loss: 79.3264 - sparse_categorical_accuracy: 0.3212
19/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:22 1s/step - loss: 79.3429 - sparse_categorical_accuracy: 0.3225
20/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:21 1s/step - loss: 79.3826 - sparse_categorical_accuracy: 0.3232
21/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:20 1s/step - loss: 79.3818 - sparse_categorical_accuracy: 0.3240
22/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:18 1s/step - loss: 79.3914 - sparse_categorical_accuracy: 0.3247
23/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:17 1s/step - loss: 79.3727 - sparse_categorical_accuracy: 0.3256
24/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:16 1s/step - loss: 79.3307 - sparse_categorical_accuracy: 0.3264
25/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:15 1s/step - loss: 79.2707 - sparse_categorical_accuracy: 0.3271
26/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:14 1s/step - loss: 79.1959 - sparse_categorical_accuracy: 0.3279
27/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:13 1s/step - loss: 79.1077 - sparse_categorical_accuracy: 0.3288
28/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:13 1s/step - loss: 79.0754 - sparse_categorical_accuracy: 0.3295
29/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:12 1s/step - loss: 79.0420 - sparse_categorical_accuracy: 0.3301
30/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:11 1s/step - loss: 78.9981 - sparse_categorical_accuracy: 0.3305
31/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:10 1s/step - loss: 78.9976 - sparse_categorical_accuracy: 0.3310
32/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:09 1s/step - loss: 78.9829 - sparse_categorical_accuracy: 0.3315
33/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:08 1s/step - loss: 78.9716 - sparse_categorical_accuracy: 0.3319
34/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:07 1s/step - loss: 78.9489 - sparse_categorical_accuracy: 0.3325
35/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:06 1s/step - loss: 78.9179 - sparse_categorical_accuracy: 0.3330
36/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:05 1s/step - loss: 78.8956 - sparse_categorical_accuracy: 0.3335
37/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:04 1s/step - loss: 78.8663 - sparse_categorical_accuracy: 0.3339
38/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:02 1s/step - loss: 78.8289 - sparse_categorical_accuracy: 0.3342
39/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:01 1s/step - loss: 78.7841 - sparse_categorical_accuracy: 0.3344
40/100 ━━━━━━━━[37m━━━━━━━━━━━━ 1:00 1s/step - loss: 78.7402 - sparse_categorical_accuracy: 0.3346
41/100 ━━━━━━━━[37m━━━━━━━━━━━━ 59s 1s/step - loss: 78.6895 - sparse_categorical_accuracy: 0.3348
42/100 ━━━━━━━━[37m━━━━━━━━━━━━ 58s 1s/step - loss: 78.6423 - sparse_categorical_accuracy: 0.3351
43/100 ━━━━━━━━[37m━━━━━━━━━━━━ 57s 1s/step - loss: 78.6159 - sparse_categorical_accuracy: 0.3354
44/100 ━━━━━━━━[37m━━━━━━━━━━━━ 56s 1s/step - loss: 78.5880 - sparse_categorical_accuracy: 0.3356
45/100 ━━━━━━━━━[37m━━━━━━━━━━━ 55s 1s/step - loss: 78.5554 - sparse_categorical_accuracy: 0.3359
46/100 ━━━━━━━━━[37m━━━━━━━━━━━ 54s 1s/step - loss: 78.5176 - sparse_categorical_accuracy: 0.3362
47/100 ━━━━━━━━━[37m━━━━━━━━━━━ 53s 1s/step - loss: 78.5012 - sparse_categorical_accuracy: 0.3364
48/100 ━━━━━━━━━[37m━━━━━━━━━━━ 52s 1s/step - loss: 78.4792 - sparse_categorical_accuracy: 0.3367
49/100 ━━━━━━━━━[37m━━━━━━━━━━━ 51s 1s/step - loss: 78.4721 - sparse_categorical_accuracy: 0.3370
50/100 ━━━━━━━━━━[37m━━━━━━━━━━ 50s 1s/step - loss: 78.4589 - sparse_categorical_accuracy: 0.3373
51/100 ━━━━━━━━━━[37m━━━━━━━━━━ 49s 1s/step - loss: 78.4406 - sparse_categorical_accuracy: 0.3375
52/100 ━━━━━━━━━━[37m━━━━━━━━━━ 48s 1s/step - loss: 78.4466 - sparse_categorical_accuracy: 0.3378
53/100 ━━━━━━━━━━[37m━━━━━━━━━━ 47s 1s/step - loss: 78.4569 - sparse_categorical_accuracy: 0.3381
54/100 ━━━━━━━━━━[37m━━━━━━━━━━ 46s 1s/step - loss: 78.4790 - sparse_categorical_accuracy: 0.3384
55/100 ━━━━━━━━━━━[37m━━━━━━━━━ 45s 1s/step - loss: 78.4997 - sparse_categorical_accuracy: 0.3386
56/100 ━━━━━━━━━━━[37m━━━━━━━━━ 44s 1s/step - loss: 78.5142 - sparse_categorical_accuracy: 0.3388
57/100 ━━━━━━━━━━━[37m━━━━━━━━━ 43s 1s/step - loss: 78.5305 - sparse_categorical_accuracy: 0.3390
58/100 ━━━━━━━━━━━[37m━━━━━━━━━ 42s 1s/step - loss: 78.5410 - sparse_categorical_accuracy: 0.3391
59/100 ━━━━━━━━━━━[37m━━━━━━━━━ 41s 1s/step - loss: 78.5479 - sparse_categorical_accuracy: 0.3392
60/100 ━━━━━━━━━━━━[37m━━━━━━━━ 40s 1s/step - loss: 78.5502 - sparse_categorical_accuracy: 0.3392
61/100 ━━━━━━━━━━━━[37m━━━━━━━━ 39s 1s/step - loss: 78.5480 - sparse_categorical_accuracy: 0.3393
62/100 ━━━━━━━━━━━━[37m━━━━━━━━ 38s 1s/step - loss: 78.5418 - sparse_categorical_accuracy: 0.3392
63/100 ━━━━━━━━━━━━[37m━━━━━━━━ 37s 1s/step - loss: 78.5315 - sparse_categorical_accuracy: 0.3391
64/100 ━━━━━━━━━━━━[37m━━━━━━━━ 36s 1s/step - loss: 78.5173 - sparse_categorical_accuracy: 0.3390
65/100 ━━━━━━━━━━━━━[37m━━━━━━━ 35s 1s/step - loss: 78.5009 - sparse_categorical_accuracy: 0.3389
66/100 ━━━━━━━━━━━━━[37m━━━━━━━ 34s 1s/step - loss: 78.4822 - sparse_categorical_accuracy: 0.3389
67/100 ━━━━━━━━━━━━━[37m━━━━━━━ 33s 1s/step - loss: 78.4737 - sparse_categorical_accuracy: 0.3388
68/100 ━━━━━━━━━━━━━[37m━━━━━━━ 32s 1s/step - loss: 78.4618 - sparse_categorical_accuracy: 0.3388
69/100 ━━━━━━━━━━━━━[37m━━━━━━━ 31s 1s/step - loss: 78.4472 - sparse_categorical_accuracy: 0.3387
70/100 ━━━━━━━━━━━━━━[37m━━━━━━ 30s 1s/step - loss: 78.4297 - sparse_categorical_accuracy: 0.3387
71/100 ━━━━━━━━━━━━━━[37m━━━━━━ 29s 1s/step - loss: 78.4095 - sparse_categorical_accuracy: 0.3386
72/100 ━━━━━━━━━━━━━━[37m━━━━━━ 28s 1s/step - loss: 78.3903 - sparse_categorical_accuracy: 0.3386
73/100 ━━━━━━━━━━━━━━[37m━━━━━━ 27s 1s/step - loss: 78.3707 - sparse_categorical_accuracy: 0.3386
74/100 ━━━━━━━━━━━━━━[37m━━━━━━ 26s 1s/step - loss: 78.3488 - sparse_categorical_accuracy: 0.3385
75/100 ━━━━━━━━━━━━━━━[37m━━━━━ 25s 1s/step - loss: 78.3245 - sparse_categorical_accuracy: 0.3385
76/100 ━━━━━━━━━━━━━━━[37m━━━━━ 24s 1s/step - loss: 78.2985 - sparse_categorical_accuracy: 0.3384
77/100 ━━━━━━━━━━━━━━━[37m━━━━━ 23s 1s/step - loss: 78.2730 - sparse_categorical_accuracy: 0.3384
78/100 ━━━━━━━━━━━━━━━[37m━━━━━ 22s 1s/step - loss: 78.2458 - sparse_categorical_accuracy: 0.3384
79/100 ━━━━━━━━━━━━━━━[37m━━━━━ 21s 1s/step - loss: 78.2171 - sparse_categorical_accuracy: 0.3383
80/100 ━━━━━━━━━━━━━━━━[37m━━━━ 20s 1s/step - loss: 78.1887 - sparse_categorical_accuracy: 0.3382
81/100 ━━━━━━━━━━━━━━━━[37m━━━━ 19s 1s/step - loss: 78.1586 - sparse_categorical_accuracy: 0.3382
82/100 ━━━━━━━━━━━━━━━━[37m━━━━ 18s 1s/step - loss: 78.1290 - sparse_categorical_accuracy: 0.3382
83/100 ━━━━━━━━━━━━━━━━[37m━━━━ 17s 1s/step - loss: 78.0979 - sparse_categorical_accuracy: 0.3381
84/100 ━━━━━━━━━━━━━━━━[37m━━━━ 16s 1s/step - loss: 78.0656 - sparse_categorical_accuracy: 0.3381
85/100 ━━━━━━━━━━━━━━━━━[37m━━━ 15s 1s/step - loss: 78.0319 - sparse_categorical_accuracy: 0.3380
86/100 ━━━━━━━━━━━━━━━━━[37m━━━ 14s 1s/step - loss: 77.9983 - sparse_categorical_accuracy: 0.3380
87/100 ━━━━━━━━━━━━━━━━━[37m━━━ 13s 1s/step - loss: 77.9636 - sparse_categorical_accuracy: 0.3380
88/100 ━━━━━━━━━━━━━━━━━[37m━━━ 12s 1s/step - loss: 77.9280 - sparse_categorical_accuracy: 0.3380
89/100 ━━━━━━━━━━━━━━━━━[37m━━━ 11s 1s/step - loss: 77.8915 - sparse_categorical_accuracy: 0.3379
90/100 ━━━━━━━━━━━━━━━━━━[37m━━ 10s 1s/step - loss: 77.8541 - sparse_categorical_accuracy: 0.3379
91/100 ━━━━━━━━━━━━━━━━━━[37m━━ 9s 1s/step - loss: 77.8170 - sparse_categorical_accuracy: 0.3378
92/100 ━━━━━━━━━━━━━━━━━━[37m━━ 8s 1s/step - loss: 77.7791 - sparse_categorical_accuracy: 0.3378
93/100 ━━━━━━━━━━━━━━━━━━[37m━━ 7s 1s/step - loss: 77.7424 - sparse_categorical_accuracy: 0.3378
94/100 ━━━━━━━━━━━━━━━━━━[37m━━ 6s 1s/step - loss: 77.7098 - sparse_categorical_accuracy: 0.3377
95/100 ━━━━━━━━━━━━━━━━━━━[37m━ 5s 1s/step - loss: 77.6769 - sparse_categorical_accuracy: 0.3377
96/100 ━━━━━━━━━━━━━━━━━━━[37m━ 4s 1s/step - loss: 77.6433 - sparse_categorical_accuracy: 0.3377
97/100 ━━━━━━━━━━━━━━━━━━━[37m━ 3s 1s/step - loss: 77.6111 - sparse_categorical_accuracy: 0.3377
98/100 ━━━━━━━━━━━━━━━━━━━[37m━ 2s 1s/step - loss: 77.5781 - sparse_categorical_accuracy: 0.3377
99/100 ━━━━━━━━━━━━━━━━━━━[37m━ 1s 1s/step - loss: 77.5445 - sparse_categorical_accuracy: 0.3377
100/100 ━━━━━━━━━━━━━━━━━━━━ 0s 1s/step - loss: 77.5074 - sparse_categorical_accuracy: 0.3377
100/100 ━━━━━━━━━━━━━━━━━━━━ 106s 1s/step - loss: 77.4712 - sparse_categorical_accuracy: 0.3377 - val_loss: 2983669504.0000 - val_sparse_categorical_accuracy: 0.2966
Epoch 16/20
1/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:38 992ms/step - loss: 59.8730 - sparse_categorical_accuracy: 0.2188
2/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:44 1s/step - loss: 59.6142 - sparse_categorical_accuracy: 0.2734
3/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:43 1s/step - loss: 59.5408 - sparse_categorical_accuracy: 0.2865
4/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:40 1s/step - loss: 60.5291 - sparse_categorical_accuracy: 0.2930
5/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:38 1s/step - loss: 60.9421 - sparse_categorical_accuracy: 0.3006
6/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:36 1s/step - loss: 61.1234 - sparse_categorical_accuracy: 0.3052
7/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:35 1s/step - loss: 61.9223 - sparse_categorical_accuracy: 0.3094
8/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:34 1s/step - loss: 62.3840 - sparse_categorical_accuracy: 0.3137
9/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:33 1s/step - loss: 62.6786 - sparse_categorical_accuracy: 0.3155
10/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:31 1s/step - loss: 62.8811 - sparse_categorical_accuracy: 0.3171
11/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:30 1s/step - loss: 63.0504 - sparse_categorical_accuracy: 0.3175
12/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:29 1s/step - loss: 63.1466 - sparse_categorical_accuracy: 0.3179
13/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:29 1s/step - loss: 63.1934 - sparse_categorical_accuracy: 0.3182
14/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:27 1s/step - loss: 63.2089 - sparse_categorical_accuracy: 0.3186
15/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:26 1s/step - loss: 63.2054 - sparse_categorical_accuracy: 0.3189
16/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:25 1s/step - loss: 63.3949 - sparse_categorical_accuracy: 0.3190
17/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:24 1s/step - loss: 63.6763 - sparse_categorical_accuracy: 0.3192
18/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:23 1s/step - loss: 63.9220 - sparse_categorical_accuracy: 0.3192
19/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:22 1s/step - loss: 64.1147 - sparse_categorical_accuracy: 0.3192
20/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:21 1s/step - loss: 64.2688 - sparse_categorical_accuracy: 0.3191
21/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:20 1s/step - loss: 64.3975 - sparse_categorical_accuracy: 0.3190
22/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:19 1s/step - loss: 64.5064 - sparse_categorical_accuracy: 0.3191
23/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:18 1s/step - loss: 64.5882 - sparse_categorical_accuracy: 0.3188
24/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:17 1s/step - loss: 64.6458 - sparse_categorical_accuracy: 0.3186
25/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:16 1s/step - loss: 64.6847 - sparse_categorical_accuracy: 0.3183
26/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:15 1s/step - loss: 64.7102 - sparse_categorical_accuracy: 0.3180
27/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:14 1s/step - loss: 64.7238 - sparse_categorical_accuracy: 0.3176
28/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:13 1s/step - loss: 64.7253 - sparse_categorical_accuracy: 0.3172
29/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:12 1s/step - loss: 64.7203 - sparse_categorical_accuracy: 0.3167
30/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:11 1s/step - loss: 64.7130 - sparse_categorical_accuracy: 0.3163
31/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:10 1s/step - loss: 64.8311 - sparse_categorical_accuracy: 0.3157
32/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:09 1s/step - loss: 64.9315 - sparse_categorical_accuracy: 0.3152
33/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:08 1s/step - loss: 65.0175 - sparse_categorical_accuracy: 0.3150
34/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:07 1s/step - loss: 65.1062 - sparse_categorical_accuracy: 0.3148
35/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:06 1s/step - loss: 65.2656 - sparse_categorical_accuracy: 0.3147
36/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:05 1s/step - loss: 65.4292 - sparse_categorical_accuracy: 0.3146
37/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:04 1s/step - loss: 65.5736 - sparse_categorical_accuracy: 0.3146
38/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:03 1s/step - loss: 65.7009 - sparse_categorical_accuracy: 0.3146
39/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:02 1s/step - loss: 65.8135 - sparse_categorical_accuracy: 0.3146
40/100 ━━━━━━━━[37m━━━━━━━━━━━━ 1:01 1s/step - loss: 65.9128 - sparse_categorical_accuracy: 0.3145
41/100 ━━━━━━━━[37m━━━━━━━━━━━━ 1:00 1s/step - loss: 66.0006 - sparse_categorical_accuracy: 0.3145
42/100 ━━━━━━━━[37m━━━━━━━━━━━━ 59s 1s/step - loss: 66.0767 - sparse_categorical_accuracy: 0.3144
43/100 ━━━━━━━━[37m━━━━━━━━━━━━ 58s 1s/step - loss: 66.1421 - sparse_categorical_accuracy: 0.3143
44/100 ━━━━━━━━[37m━━━━━━━━━━━━ 57s 1s/step - loss: 66.1978 - sparse_categorical_accuracy: 0.3143
45/100 ━━━━━━━━━[37m━━━━━━━━━━━ 56s 1s/step - loss: 66.2447 - sparse_categorical_accuracy: 0.3142
46/100 ━━━━━━━━━[37m━━━━━━━━━━━ 55s 1s/step - loss: 66.2840 - sparse_categorical_accuracy: 0.3142
47/100 ━━━━━━━━━[37m━━━━━━━━━━━ 54s 1s/step - loss: 66.3271 - sparse_categorical_accuracy: 0.3142
48/100 ━━━━━━━━━[37m━━━━━━━━━━━ 53s 1s/step - loss: 66.3801 - sparse_categorical_accuracy: 0.3143
49/100 ━━━━━━━━━[37m━━━━━━━━━━━ 52s 1s/step - loss: 66.4257 - sparse_categorical_accuracy: 0.3144
50/100 ━━━━━━━━━━[37m━━━━━━━━━━ 51s 1s/step - loss: 66.4652 - sparse_categorical_accuracy: 0.3144
51/100 ━━━━━━━━━━[37m━━━━━━━━━━ 50s 1s/step - loss: 66.4984 - sparse_categorical_accuracy: 0.3144
52/100 ━━━━━━━━━━[37m━━━━━━━━━━ 49s 1s/step - loss: 66.5277 - sparse_categorical_accuracy: 0.3144
53/100 ━━━━━━━━━━[37m━━━━━━━━━━ 48s 1s/step - loss: 66.5540 - sparse_categorical_accuracy: 0.3144
54/100 ━━━━━━━━━━[37m━━━━━━━━━━ 47s 1s/step - loss: 66.5844 - sparse_categorical_accuracy: 0.3144
55/100 ━━━━━━━━━━━[37m━━━━━━━━━ 46s 1s/step - loss: 66.6358 - sparse_categorical_accuracy: 0.3144
56/100 ━━━━━━━━━━━[37m━━━━━━━━━ 45s 1s/step - loss: 66.6834 - sparse_categorical_accuracy: 0.3144
57/100 ━━━━━━━━━━━[37m━━━━━━━━━ 44s 1s/step - loss: 66.7256 - sparse_categorical_accuracy: 0.3144
58/100 ━━━━━━━━━━━[37m━━━━━━━━━ 43s 1s/step - loss: 66.7642 - sparse_categorical_accuracy: 0.3144
59/100 ━━━━━━━━━━━[37m━━━━━━━━━ 42s 1s/step - loss: 66.7980 - sparse_categorical_accuracy: 0.3145
60/100 ━━━━━━━━━━━━[37m━━━━━━━━ 41s 1s/step - loss: 66.8283 - sparse_categorical_accuracy: 0.3145
61/100 ━━━━━━━━━━━━[37m━━━━━━━━ 39s 1s/step - loss: 66.8676 - sparse_categorical_accuracy: 0.3145
62/100 ━━━━━━━━━━━━[37m━━━━━━━━ 38s 1s/step - loss: 66.9055 - sparse_categorical_accuracy: 0.3145
63/100 ━━━━━━━━━━━━[37m━━━━━━━━ 37s 1s/step - loss: 66.9389 - sparse_categorical_accuracy: 0.3145
64/100 ━━━━━━━━━━━━[37m━━━━━━━━ 36s 1s/step - loss: 66.9682 - sparse_categorical_accuracy: 0.3146
65/100 ━━━━━━━━━━━━━[37m━━━━━━━ 35s 1s/step - loss: 67.0068 - sparse_categorical_accuracy: 0.3147
66/100 ━━━━━━━━━━━━━[37m━━━━━━━ 34s 1s/step - loss: 67.0413 - sparse_categorical_accuracy: 0.3147
67/100 ━━━━━━━━━━━━━[37m━━━━━━━ 33s 1s/step - loss: 67.0722 - sparse_categorical_accuracy: 0.3148
68/100 ━━━━━━━━━━━━━[37m━━━━━━━ 32s 1s/step - loss: 67.0993 - sparse_categorical_accuracy: 0.3149
69/100 ━━━━━━━━━━━━━[37m━━━━━━━ 31s 1s/step - loss: 67.1250 - sparse_categorical_accuracy: 0.3150
70/100 ━━━━━━━━━━━━━━[37m━━━━━━ 30s 1s/step - loss: 67.1480 - sparse_categorical_accuracy: 0.3150
71/100 ━━━━━━━━━━━━━━[37m━━━━━━ 29s 1s/step - loss: 67.1680 - sparse_categorical_accuracy: 0.3151
72/100 ━━━━━━━━━━━━━━[37m━━━━━━ 28s 1s/step - loss: 67.1852 - sparse_categorical_accuracy: 0.3152
73/100 ━━━━━━━━━━━━━━[37m━━━━━━ 27s 1s/step - loss: 67.2117 - sparse_categorical_accuracy: 0.3154
74/100 ━━━━━━━━━━━━━━[37m━━━━━━ 26s 1s/step - loss: 67.2353 - sparse_categorical_accuracy: 0.3155
75/100 ━━━━━━━━━━━━━━━[37m━━━━━ 25s 1s/step - loss: 67.2570 - sparse_categorical_accuracy: 0.3156
76/100 ━━━━━━━━━━━━━━━[37m━━━━━ 24s 1s/step - loss: 67.2819 - sparse_categorical_accuracy: 0.3157
77/100 ━━━━━━━━━━━━━━━[37m━━━━━ 23s 1s/step - loss: 67.3040 - sparse_categorical_accuracy: 0.3158
78/100 ━━━━━━━━━━━━━━━[37m━━━━━ 22s 1s/step - loss: 67.3234 - sparse_categorical_accuracy: 0.3159
79/100 ━━━━━━━━━━━━━━━[37m━━━━━ 21s 1s/step - loss: 67.3401 - sparse_categorical_accuracy: 0.3160
80/100 ━━━━━━━━━━━━━━━━[37m━━━━ 20s 1s/step - loss: 67.3545 - sparse_categorical_accuracy: 0.3161
81/100 ━━━━━━━━━━━━━━━━[37m━━━━ 19s 1s/step - loss: 67.3668 - sparse_categorical_accuracy: 0.3162
82/100 ━━━━━━━━━━━━━━━━[37m━━━━ 18s 1s/step - loss: 67.3805 - sparse_categorical_accuracy: 0.3164
83/100 ━━━━━━━━━━━━━━━━[37m━━━━ 17s 1s/step - loss: 67.3918 - sparse_categorical_accuracy: 0.3165
84/100 ━━━━━━━━━━━━━━━━[37m━━━━ 16s 1s/step - loss: 67.4010 - sparse_categorical_accuracy: 0.3166
85/100 ━━━━━━━━━━━━━━━━━[37m━━━ 15s 1s/step - loss: 67.4103 - sparse_categorical_accuracy: 0.3168
86/100 ━━━━━━━━━━━━━━━━━[37m━━━ 14s 1s/step - loss: 67.4179 - sparse_categorical_accuracy: 0.3169
87/100 ━━━━━━━━━━━━━━━━━[37m━━━ 13s 1s/step - loss: 67.4237 - sparse_categorical_accuracy: 0.3171
88/100 ━━━━━━━━━━━━━━━━━[37m━━━ 12s 1s/step - loss: 67.4318 - sparse_categorical_accuracy: 0.3172
89/100 ━━━━━━━━━━━━━━━━━[37m━━━ 11s 1s/step - loss: 67.4379 - sparse_categorical_accuracy: 0.3174
90/100 ━━━━━━━━━━━━━━━━━━[37m━━ 10s 1s/step - loss: 67.4424 - sparse_categorical_accuracy: 0.3175
91/100 ━━━━━━━━━━━━━━━━━━[37m━━ 9s 1s/step - loss: 67.4458 - sparse_categorical_accuracy: 0.3176
92/100 ━━━━━━━━━━━━━━━━━━[37m━━ 8s 1s/step - loss: 67.4481 - sparse_categorical_accuracy: 0.3178
93/100 ━━━━━━━━━━━━━━━━━━[37m━━ 7s 1s/step - loss: 67.4508 - sparse_categorical_accuracy: 0.3179
94/100 ━━━━━━━━━━━━━━━━━━[37m━━ 6s 1s/step - loss: 67.4519 - sparse_categorical_accuracy: 0.3180
95/100 ━━━━━━━━━━━━━━━━━━━[37m━ 5s 1s/step - loss: 67.4519 - sparse_categorical_accuracy: 0.3181
96/100 ━━━━━━━━━━━━━━━━━━━[37m━ 4s 1s/step - loss: 67.4504 - sparse_categorical_accuracy: 0.3182
97/100 ━━━━━━━━━━━━━━━━━━━[37m━ 3s 1s/step - loss: 67.4478 - sparse_categorical_accuracy: 0.3184
98/100 ━━━━━━━━━━━━━━━━━━━[37m━ 2s 1s/step - loss: 67.4438 - sparse_categorical_accuracy: 0.3185
99/100 ━━━━━━━━━━━━━━━━━━━[37m━ 1s 1s/step - loss: 67.4389 - sparse_categorical_accuracy: 0.3186
100/100 ━━━━━━━━━━━━━━━━━━━━ 0s 1s/step - loss: 67.4304 - sparse_categorical_accuracy: 0.3187
100/100 ━━━━━━━━━━━━━━━━━━━━ 107s 1s/step - loss: 67.4222 - sparse_categorical_accuracy: 0.3189 - val_loss: 37.0687 - val_sparse_categorical_accuracy: 0.1477
Epoch 17/20
1/100 [37m━━━━━━━━━━━━━━━━━━━━ 58:50 36s/step - loss: 54.1712 - sparse_categorical_accuracy: 0.5312
2/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:37 996ms/step - loss: 54.1433 - sparse_categorical_accuracy: 0.4844
3/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:39 1s/step - loss: 54.2923 - sparse_categorical_accuracy: 0.4583
4/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:37 1s/step - loss: 54.3945 - sparse_categorical_accuracy: 0.4395
5/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:38 1s/step - loss: 54.4431 - sparse_categorical_accuracy: 0.4228
6/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:36 1s/step - loss: 54.4496 - sparse_categorical_accuracy: 0.4122
7/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:35 1s/step - loss: 54.4618 - sparse_categorical_accuracy: 0.4031
8/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:34 1s/step - loss: 54.4794 - sparse_categorical_accuracy: 0.3937
9/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:32 1s/step - loss: 54.5192 - sparse_categorical_accuracy: 0.3851
10/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:31 1s/step - loss: 54.5401 - sparse_categorical_accuracy: 0.3766
11/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:30 1s/step - loss: 54.5954 - sparse_categorical_accuracy: 0.3710
12/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:29 1s/step - loss: 54.6501 - sparse_categorical_accuracy: 0.3659
13/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:28 1s/step - loss: 54.7149 - sparse_categorical_accuracy: 0.3622
14/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:27 1s/step - loss: 54.7656 - sparse_categorical_accuracy: 0.3591
15/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:26 1s/step - loss: 54.8022 - sparse_categorical_accuracy: 0.3567
16/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:25 1s/step - loss: 54.8257 - sparse_categorical_accuracy: 0.3542
17/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:24 1s/step - loss: 54.8423 - sparse_categorical_accuracy: 0.3525
18/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:23 1s/step - loss: 54.9699 - sparse_categorical_accuracy: 0.3509
19/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:22 1s/step - loss: 55.0764 - sparse_categorical_accuracy: 0.3496
20/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:21 1s/step - loss: 55.1662 - sparse_categorical_accuracy: 0.3486
21/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:20 1s/step - loss: 55.2427 - sparse_categorical_accuracy: 0.3476
22/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:19 1s/step - loss: 55.3652 - sparse_categorical_accuracy: 0.3469
23/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:18 1s/step - loss: 55.4674 - sparse_categorical_accuracy: 0.3462
24/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:17 1s/step - loss: 55.5522 - sparse_categorical_accuracy: 0.3454
25/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:16 1s/step - loss: 55.6296 - sparse_categorical_accuracy: 0.3448
26/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:15 1s/step - loss: 55.6969 - sparse_categorical_accuracy: 0.3443
27/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:14 1s/step - loss: 55.7546 - sparse_categorical_accuracy: 0.3437
28/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:13 1s/step - loss: 55.8086 - sparse_categorical_accuracy: 0.3432
29/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:12 1s/step - loss: 55.8801 - sparse_categorical_accuracy: 0.3426
30/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:11 1s/step - loss: 55.9433 - sparse_categorical_accuracy: 0.3422
31/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:10 1s/step - loss: 55.9972 - sparse_categorical_accuracy: 0.3418
32/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:09 1s/step - loss: 56.0430 - sparse_categorical_accuracy: 0.3416
33/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:08 1s/step - loss: 56.1322 - sparse_categorical_accuracy: 0.3413
34/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:07 1s/step - loss: 56.2106 - sparse_categorical_accuracy: 0.3411
35/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:06 1s/step - loss: 56.2797 - sparse_categorical_accuracy: 0.3408
36/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:05 1s/step - loss: 56.3416 - sparse_categorical_accuracy: 0.3404
37/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:04 1s/step - loss: 56.4020 - sparse_categorical_accuracy: 0.3399
38/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:03 1s/step - loss: 56.5119 - sparse_categorical_accuracy: 0.3394
39/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:02 1s/step - loss: 56.6107 - sparse_categorical_accuracy: 0.3390
40/100 ━━━━━━━━[37m━━━━━━━━━━━━ 1:00 1s/step - loss: 56.7063 - sparse_categorical_accuracy: 0.3387
41/100 ━━━━━━━━[37m━━━━━━━━━━━━ 59s 1s/step - loss: 56.7925 - sparse_categorical_accuracy: 0.3384
42/100 ━━━━━━━━[37m━━━━━━━━━━━━ 58s 1s/step - loss: 56.8706 - sparse_categorical_accuracy: 0.3381
43/100 ━━━━━━━━[37m━━━━━━━━━━━━ 57s 1s/step - loss: 56.9405 - sparse_categorical_accuracy: 0.3377
44/100 ━━━━━━━━[37m━━━━━━━━━━━━ 56s 1s/step - loss: 57.0081 - sparse_categorical_accuracy: 0.3373
45/100 ━━━━━━━━━[37m━━━━━━━━━━━ 55s 1s/step - loss: 57.0696 - sparse_categorical_accuracy: 0.3369
46/100 ━━━━━━━━━[37m━━━━━━━━━━━ 54s 1s/step - loss: 57.1252 - sparse_categorical_accuracy: 0.3366
47/100 ━━━━━━━━━[37m━━━━━━━━━━━ 53s 1s/step - loss: 57.1747 - sparse_categorical_accuracy: 0.3363
48/100 ━━━━━━━━━[37m━━━━━━━━━━━ 52s 1s/step - loss: 57.2194 - sparse_categorical_accuracy: 0.3360
49/100 ━━━━━━━━━[37m━━━━━━━━━━━ 51s 1s/step - loss: 57.2593 - sparse_categorical_accuracy: 0.3357
50/100 ━━━━━━━━━━[37m━━━━━━━━━━ 50s 1s/step - loss: 57.2964 - sparse_categorical_accuracy: 0.3355
51/100 ━━━━━━━━━━[37m━━━━━━━━━━ 49s 1s/step - loss: 57.3293 - sparse_categorical_accuracy: 0.3352
52/100 ━━━━━━━━━━[37m━━━━━━━━━━ 48s 1s/step - loss: 57.3585 - sparse_categorical_accuracy: 0.3351
53/100 ━━━━━━━━━━[37m━━━━━━━━━━ 47s 1s/step - loss: 57.3855 - sparse_categorical_accuracy: 0.3348
54/100 ━━━━━━━━━━[37m━━━━━━━━━━ 46s 1s/step - loss: 57.4333 - sparse_categorical_accuracy: 0.3346
55/100 ━━━━━━━━━━━[37m━━━━━━━━━ 45s 1s/step - loss: 57.4782 - sparse_categorical_accuracy: 0.3343
56/100 ━━━━━━━━━━━[37m━━━━━━━━━ 44s 1s/step - loss: 57.5188 - sparse_categorical_accuracy: 0.3341
57/100 ━━━━━━━━━━━[37m━━━━━━━━━ 43s 1s/step - loss: 57.5586 - sparse_categorical_accuracy: 0.3338
58/100 ━━━━━━━━━━━[37m━━━━━━━━━ 42s 1s/step - loss: 57.5993 - sparse_categorical_accuracy: 0.3335
59/100 ━━━━━━━━━━━[37m━━━━━━━━━ 41s 1s/step - loss: 57.6384 - sparse_categorical_accuracy: 0.3333
60/100 ━━━━━━━━━━━━[37m━━━━━━━━ 40s 1s/step - loss: 57.6740 - sparse_categorical_accuracy: 0.3331
61/100 ━━━━━━━━━━━━[37m━━━━━━━━ 39s 1s/step - loss: 57.7064 - sparse_categorical_accuracy: 0.3329
62/100 ━━━━━━━━━━━━[37m━━━━━━━━ 38s 1s/step - loss: 57.7355 - sparse_categorical_accuracy: 0.3327
63/100 ━━━━━━━━━━━━[37m━━━━━━━━ 37s 1s/step - loss: 57.7617 - sparse_categorical_accuracy: 0.3325
64/100 ━━━━━━━━━━━━[37m━━━━━━━━ 36s 1s/step - loss: 57.7892 - sparse_categorical_accuracy: 0.3323
65/100 ━━━━━━━━━━━━━[37m━━━━━━━ 35s 1s/step - loss: 57.8148 - sparse_categorical_accuracy: 0.3321
66/100 ━━━━━━━━━━━━━[37m━━━━━━━ 34s 1s/step - loss: 57.8380 - sparse_categorical_accuracy: 0.3320
67/100 ━━━━━━━━━━━━━[37m━━━━━━━ 33s 1s/step - loss: 57.8589 - sparse_categorical_accuracy: 0.3318
68/100 ━━━━━━━━━━━━━[37m━━━━━━━ 32s 1s/step - loss: 57.8776 - sparse_categorical_accuracy: 0.3317
69/100 ━━━━━━━━━━━━━[37m━━━━━━━ 31s 1s/step - loss: 57.8941 - sparse_categorical_accuracy: 0.3315
70/100 ━━━━━━━━━━━━━━[37m━━━━━━ 30s 1s/step - loss: 57.9087 - sparse_categorical_accuracy: 0.3314
71/100 ━━━━━━━━━━━━━━[37m━━━━━━ 29s 1s/step - loss: 57.9215 - sparse_categorical_accuracy: 0.3312
72/100 ━━━━━━━━━━━━━━[37m━━━━━━ 28s 1s/step - loss: 57.9324 - sparse_categorical_accuracy: 0.3310
73/100 ━━━━━━━━━━━━━━[37m━━━━━━ 27s 1s/step - loss: 57.9434 - sparse_categorical_accuracy: 0.3309
74/100 ━━━━━━━━━━━━━━[37m━━━━━━ 26s 1s/step - loss: 57.9529 - sparse_categorical_accuracy: 0.3307
75/100 ━━━━━━━━━━━━━━━[37m━━━━━ 25s 1s/step - loss: 57.9608 - sparse_categorical_accuracy: 0.3305
76/100 ━━━━━━━━━━━━━━━[37m━━━━━ 24s 1s/step - loss: 57.9671 - sparse_categorical_accuracy: 0.3304
77/100 ━━━━━━━━━━━━━━━[37m━━━━━ 23s 1s/step - loss: 57.9843 - sparse_categorical_accuracy: 0.3302
78/100 ━━━━━━━━━━━━━━━[37m━━━━━ 22s 1s/step - loss: 57.9998 - sparse_categorical_accuracy: 0.3300
79/100 ━━━━━━━━━━━━━━━[37m━━━━━ 21s 1s/step - loss: 58.0135 - sparse_categorical_accuracy: 0.3299
80/100 ━━━━━━━━━━━━━━━━[37m━━━━ 20s 1s/step - loss: 58.0259 - sparse_categorical_accuracy: 0.3298
81/100 ━━━━━━━━━━━━━━━━[37m━━━━ 19s 1s/step - loss: 58.0429 - sparse_categorical_accuracy: 0.3296
82/100 ━━━━━━━━━━━━━━━━[37m━━━━ 18s 1s/step - loss: 58.0585 - sparse_categorical_accuracy: 0.3295
83/100 ━━━━━━━━━━━━━━━━[37m━━━━ 17s 1s/step - loss: 58.0728 - sparse_categorical_accuracy: 0.3293
84/100 ━━━━━━━━━━━━━━━━[37m━━━━ 16s 1s/step - loss: 58.0856 - sparse_categorical_accuracy: 0.3292
85/100 ━━━━━━━━━━━━━━━━━[37m━━━ 15s 1s/step - loss: 58.1039 - sparse_categorical_accuracy: 0.3291
86/100 ━━━━━━━━━━━━━━━━━[37m━━━ 14s 1s/step - loss: 58.1206 - sparse_categorical_accuracy: 0.3290
87/100 ━━━━━━━━━━━━━━━━━[37m━━━ 13s 1s/step - loss: 58.1372 - sparse_categorical_accuracy: 0.3289
88/100 ━━━━━━━━━━━━━━━━━[37m━━━ 12s 1s/step - loss: 58.1528 - sparse_categorical_accuracy: 0.3288
89/100 ━━━━━━━━━━━━━━━━━[37m━━━ 11s 1s/step - loss: 58.1669 - sparse_categorical_accuracy: 0.3288
90/100 ━━━━━━━━━━━━━━━━━━[37m━━ 10s 1s/step - loss: 58.1796 - sparse_categorical_accuracy: 0.3287
91/100 ━━━━━━━━━━━━━━━━━━[37m━━ 9s 1s/step - loss: 58.1911 - sparse_categorical_accuracy: 0.3286
92/100 ━━━━━━━━━━━━━━━━━━[37m━━ 8s 1s/step - loss: 58.2014 - sparse_categorical_accuracy: 0.3285
93/100 ━━━━━━━━━━━━━━━━━━[37m━━ 7s 1s/step - loss: 58.2118 - sparse_categorical_accuracy: 0.3285
94/100 ━━━━━━━━━━━━━━━━━━[37m━━ 6s 1s/step - loss: 58.2212 - sparse_categorical_accuracy: 0.3284
95/100 ━━━━━━━━━━━━━━━━━━━[37m━ 5s 1s/step - loss: 58.2345 - sparse_categorical_accuracy: 0.3284
96/100 ━━━━━━━━━━━━━━━━━━━[37m━ 4s 1s/step - loss: 58.2465 - sparse_categorical_accuracy: 0.3283
97/100 ━━━━━━━━━━━━━━━━━━━[37m━ 3s 1s/step - loss: 58.2574 - sparse_categorical_accuracy: 0.3283
98/100 ━━━━━━━━━━━━━━━━━━━[37m━ 2s 1s/step - loss: 58.2673 - sparse_categorical_accuracy: 0.3283
99/100 ━━━━━━━━━━━━━━━━━━━[37m━ 1s 1s/step - loss: 58.2759 - sparse_categorical_accuracy: 0.3282
100/100 ━━━━━━━━━━━━━━━━━━━━ 0s 1s/step - loss: 58.2815 - sparse_categorical_accuracy: 0.3282
100/100 ━━━━━━━━━━━━━━━━━━━━ 141s 1s/step - loss: 58.2869 - sparse_categorical_accuracy: 0.3282 - val_loss: 4191578574815232.0000 - val_sparse_categorical_accuracy: 0.3129
Epoch 18/20
1/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:39 1s/step - loss: 51.9365 - sparse_categorical_accuracy: 0.4375
2/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:44 1s/step - loss: 57.0536 - sparse_categorical_accuracy: 0.3984
3/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:40 1s/step - loss: 57.4789 - sparse_categorical_accuracy: 0.3767
4/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:38 1s/step - loss: 57.1816 - sparse_categorical_accuracy: 0.3529
5/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:37 1s/step - loss: 57.1706 - sparse_categorical_accuracy: 0.3435
6/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:35 1s/step - loss: 57.8198 - sparse_categorical_accuracy: 0.3349
7/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:35 1s/step - loss: 58.1971 - sparse_categorical_accuracy: 0.3285
8/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:34 1s/step - loss: 58.3237 - sparse_categorical_accuracy: 0.3236
9/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:33 1s/step - loss: 58.3409 - sparse_categorical_accuracy: 0.3200
10/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:32 1s/step - loss: 58.5552 - sparse_categorical_accuracy: 0.3165
11/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:31 1s/step - loss: 58.6516 - sparse_categorical_accuracy: 0.3143
12/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:30 1s/step - loss: 58.6702 - sparse_categorical_accuracy: 0.3131
13/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:29 1s/step - loss: 58.6391 - sparse_categorical_accuracy: 0.3126
14/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:28 1s/step - loss: 58.6047 - sparse_categorical_accuracy: 0.3125
15/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:26 1s/step - loss: 58.5388 - sparse_categorical_accuracy: 0.3126
16/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:25 1s/step - loss: 58.4930 - sparse_categorical_accuracy: 0.3130
17/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:24 1s/step - loss: 58.5077 - sparse_categorical_accuracy: 0.3135
18/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:23 1s/step - loss: 58.5053 - sparse_categorical_accuracy: 0.3142
19/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:22 1s/step - loss: 58.4806 - sparse_categorical_accuracy: 0.3154
20/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:21 1s/step - loss: 58.4394 - sparse_categorical_accuracy: 0.3170
21/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:20 1s/step - loss: 58.4049 - sparse_categorical_accuracy: 0.3185
22/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:19 1s/step - loss: 58.3601 - sparse_categorical_accuracy: 0.3198
23/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:18 1s/step - loss: 58.3112 - sparse_categorical_accuracy: 0.3208
24/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:17 1s/step - loss: 58.2546 - sparse_categorical_accuracy: 0.3219
25/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:16 1s/step - loss: 58.1921 - sparse_categorical_accuracy: 0.3226
26/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:15 1s/step - loss: 58.1254 - sparse_categorical_accuracy: 0.3234
27/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:13 1s/step - loss: 58.0712 - sparse_categorical_accuracy: 0.3242
28/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:12 1s/step - loss: 58.0117 - sparse_categorical_accuracy: 0.3251
29/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:11 1s/step - loss: 57.9476 - sparse_categorical_accuracy: 0.3258
30/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:10 1s/step - loss: 57.8802 - sparse_categorical_accuracy: 0.3267
31/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:09 1s/step - loss: 57.8106 - sparse_categorical_accuracy: 0.3275
32/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:08 1s/step - loss: 57.7397 - sparse_categorical_accuracy: 0.3282
33/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:07 1s/step - loss: 57.6674 - sparse_categorical_accuracy: 0.3289
34/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:06 1s/step - loss: 57.5958 - sparse_categorical_accuracy: 0.3295
35/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:05 1s/step - loss: 57.5233 - sparse_categorical_accuracy: 0.3300
36/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:04 1s/step - loss: 57.4506 - sparse_categorical_accuracy: 0.3304
37/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:03 1s/step - loss: 57.3774 - sparse_categorical_accuracy: 0.3307
38/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:02 1s/step - loss: 57.3046 - sparse_categorical_accuracy: 0.3310
39/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:02 1s/step - loss: 57.2337 - sparse_categorical_accuracy: 0.3311
40/100 ━━━━━━━━[37m━━━━━━━━━━━━ 1:01 1s/step - loss: 57.1629 - sparse_categorical_accuracy: 0.3312
41/100 ━━━━━━━━[37m━━━━━━━━━━━━ 1:00 1s/step - loss: 57.0945 - sparse_categorical_accuracy: 0.3312
42/100 ━━━━━━━━[37m━━━━━━━━━━━━ 59s 1s/step - loss: 57.0267 - sparse_categorical_accuracy: 0.3313
43/100 ━━━━━━━━[37m━━━━━━━━━━━━ 58s 1s/step - loss: 56.9828 - sparse_categorical_accuracy: 0.3314
44/100 ━━━━━━━━[37m━━━━━━━━━━━━ 57s 1s/step - loss: 56.9401 - sparse_categorical_accuracy: 0.3315
45/100 ━━━━━━━━━[37m━━━━━━━━━━━ 55s 1s/step - loss: 56.8960 - sparse_categorical_accuracy: 0.3317
46/100 ━━━━━━━━━[37m━━━━━━━━━━━ 54s 1s/step - loss: 56.8507 - sparse_categorical_accuracy: 0.3319
47/100 ━━━━━━━━━[37m━━━━━━━━━━━ 53s 1s/step - loss: 56.8044 - sparse_categorical_accuracy: 0.3322
48/100 ━━━━━━━━━[37m━━━━━━━━━━━ 52s 1s/step - loss: 56.7577 - sparse_categorical_accuracy: 0.3325
49/100 ━━━━━━━━━[37m━━━━━━━━━━━ 51s 1s/step - loss: 56.7108 - sparse_categorical_accuracy: 0.3327
50/100 ━━━━━━━━━━[37m━━━━━━━━━━ 50s 1s/step - loss: 56.6634 - sparse_categorical_accuracy: 0.3329
51/100 ━━━━━━━━━━[37m━━━━━━━━━━ 49s 1s/step - loss: 56.6159 - sparse_categorical_accuracy: 0.3331
52/100 ━━━━━━━━━━[37m━━━━━━━━━━ 48s 1s/step - loss: 56.5681 - sparse_categorical_accuracy: 0.3332
53/100 ━━━━━━━━━━[37m━━━━━━━━━━ 47s 1s/step - loss: 56.5206 - sparse_categorical_accuracy: 0.3333
54/100 ━━━━━━━━━━[37m━━━━━━━━━━ 46s 1s/step - loss: 56.4731 - sparse_categorical_accuracy: 0.3333
55/100 ━━━━━━━━━━━[37m━━━━━━━━━ 45s 1s/step - loss: 56.4286 - sparse_categorical_accuracy: 0.3334
56/100 ━━━━━━━━━━━[37m━━━━━━━━━ 44s 1s/step - loss: 56.3840 - sparse_categorical_accuracy: 0.3334
57/100 ━━━━━━━━━━━[37m━━━━━━━━━ 43s 1s/step - loss: 56.3394 - sparse_categorical_accuracy: 0.3334
58/100 ━━━━━━━━━━━[37m━━━━━━━━━ 42s 1s/step - loss: 56.3065 - sparse_categorical_accuracy: 0.3335
59/100 ━━━━━━━━━━━[37m━━━━━━━━━ 41s 1s/step - loss: 56.2731 - sparse_categorical_accuracy: 0.3336
60/100 ━━━━━━━━━━━━[37m━━━━━━━━ 40s 1s/step - loss: 56.2395 - sparse_categorical_accuracy: 0.3336
61/100 ━━━━━━━━━━━━[37m━━━━━━━━ 39s 1s/step - loss: 56.2054 - sparse_categorical_accuracy: 0.3337
62/100 ━━━━━━━━━━━━[37m━━━━━━━━ 38s 1s/step - loss: 56.1711 - sparse_categorical_accuracy: 0.3338
63/100 ━━━━━━━━━━━━[37m━━━━━━━━ 37s 1s/step - loss: 56.1365 - sparse_categorical_accuracy: 0.3339
64/100 ━━━━━━━━━━━━[37m━━━━━━━━ 36s 1s/step - loss: 56.1018 - sparse_categorical_accuracy: 0.3339
65/100 ━━━━━━━━━━━━━[37m━━━━━━━ 35s 1s/step - loss: 56.0668 - sparse_categorical_accuracy: 0.3339
66/100 ━━━━━━━━━━━━━[37m━━━━━━━ 34s 1s/step - loss: 56.0318 - sparse_categorical_accuracy: 0.3339
67/100 ━━━━━━━━━━━━━[37m━━━━━━━ 33s 1s/step - loss: 55.9968 - sparse_categorical_accuracy: 0.3339
68/100 ━━━━━━━━━━━━━[37m━━━━━━━ 32s 1s/step - loss: 55.9643 - sparse_categorical_accuracy: 0.3339
69/100 ━━━━━━━━━━━━━[37m━━━━━━━ 31s 1s/step - loss: 55.9317 - sparse_categorical_accuracy: 0.3340
70/100 ━━━━━━━━━━━━━━[37m━━━━━━ 30s 1s/step - loss: 55.8996 - sparse_categorical_accuracy: 0.3340
71/100 ━━━━━━━━━━━━━━[37m━━━━━━ 29s 1s/step - loss: 55.8673 - sparse_categorical_accuracy: 0.3341
72/100 ━━━━━━━━━━━━━━[37m━━━━━━ 28s 1s/step - loss: 55.8357 - sparse_categorical_accuracy: 0.3342
73/100 ━━━━━━━━━━━━━━[37m━━━━━━ 27s 1s/step - loss: 55.8041 - sparse_categorical_accuracy: 0.3343
74/100 ━━━━━━━━━━━━━━[37m━━━━━━ 26s 1s/step - loss: 55.7725 - sparse_categorical_accuracy: 0.3343
75/100 ━━━━━━━━━━━━━━━[37m━━━━━ 25s 1s/step - loss: 55.7424 - sparse_categorical_accuracy: 0.3344
76/100 ━━━━━━━━━━━━━━━[37m━━━━━ 24s 1s/step - loss: 55.7129 - sparse_categorical_accuracy: 0.3345
77/100 ━━━━━━━━━━━━━━━[37m━━━━━ 23s 1s/step - loss: 55.6835 - sparse_categorical_accuracy: 0.3346
78/100 ━━━━━━━━━━━━━━━[37m━━━━━ 22s 1s/step - loss: 55.6543 - sparse_categorical_accuracy: 0.3346
79/100 ━━━━━━━━━━━━━━━[37m━━━━━ 21s 1s/step - loss: 55.6249 - sparse_categorical_accuracy: 0.3347
80/100 ━━━━━━━━━━━━━━━━[37m━━━━ 20s 1s/step - loss: 55.5968 - sparse_categorical_accuracy: 0.3348
81/100 ━━━━━━━━━━━━━━━━[37m━━━━ 19s 1s/step - loss: 55.5756 - sparse_categorical_accuracy: 0.3348
82/100 ━━━━━━━━━━━━━━━━[37m━━━━ 18s 1s/step - loss: 55.5541 - sparse_categorical_accuracy: 0.3349
83/100 ━━━━━━━━━━━━━━━━[37m━━━━ 17s 1s/step - loss: 55.5328 - sparse_categorical_accuracy: 0.3349
84/100 ━━━━━━━━━━━━━━━━[37m━━━━ 16s 1s/step - loss: 55.5113 - sparse_categorical_accuracy: 0.3350
85/100 ━━━━━━━━━━━━━━━━━[37m━━━ 15s 1s/step - loss: 55.4897 - sparse_categorical_accuracy: 0.3351
86/100 ━━━━━━━━━━━━━━━━━[37m━━━ 14s 1s/step - loss: 55.4680 - sparse_categorical_accuracy: 0.3351
87/100 ━━━━━━━━━━━━━━━━━[37m━━━ 13s 1s/step - loss: 55.4463 - sparse_categorical_accuracy: 0.3351
88/100 ━━━━━━━━━━━━━━━━━[37m━━━ 12s 1s/step - loss: 55.4254 - sparse_categorical_accuracy: 0.3352
89/100 ━━━━━━━━━━━━━━━━━[37m━━━ 11s 1s/step - loss: 55.4044 - sparse_categorical_accuracy: 0.3352
90/100 ━━━━━━━━━━━━━━━━━━[37m━━ 10s 1s/step - loss: 55.3833 - sparse_categorical_accuracy: 0.3352
91/100 ━━━━━━━━━━━━━━━━━━[37m━━ 9s 1s/step - loss: 55.3620 - sparse_categorical_accuracy: 0.3352
92/100 ━━━━━━━━━━━━━━━━━━[37m━━ 8s 1s/step - loss: 55.3407 - sparse_categorical_accuracy: 0.3352
93/100 ━━━━━━━━━━━━━━━━━━[37m━━ 7s 1s/step - loss: 55.3192 - sparse_categorical_accuracy: 0.3352
94/100 ━━━━━━━━━━━━━━━━━━[37m━━ 6s 1s/step - loss: 55.2975 - sparse_categorical_accuracy: 0.3352
95/100 ━━━━━━━━━━━━━━━━━━━[37m━ 5s 1s/step - loss: 55.2758 - sparse_categorical_accuracy: 0.3352
96/100 ━━━━━━━━━━━━━━━━━━━[37m━ 4s 1s/step - loss: 55.2539 - sparse_categorical_accuracy: 0.3352
97/100 ━━━━━━━━━━━━━━━━━━━[37m━ 3s 1s/step - loss: 55.2319 - sparse_categorical_accuracy: 0.3352
98/100 ━━━━━━━━━━━━━━━━━━━[37m━ 2s 1s/step - loss: 55.2103 - sparse_categorical_accuracy: 0.3352
99/100 ━━━━━━━━━━━━━━━━━━━[37m━ 1s 1s/step - loss: 55.1890 - sparse_categorical_accuracy: 0.3352
100/100 ━━━━━━━━━━━━━━━━━━━━ 0s 1s/step - loss: 55.1664 - sparse_categorical_accuracy: 0.3351
100/100 ━━━━━━━━━━━━━━━━━━━━ 106s 1s/step - loss: 55.1443 - sparse_categorical_accuracy: 0.3351 - val_loss: 50221851662203486208.0000 - val_sparse_categorical_accuracy: 0.3242
Epoch 19/20
1/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:41 1s/step - loss: 48.0290 - sparse_categorical_accuracy: 0.2188
2/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:44 1s/step - loss: 48.0152 - sparse_categorical_accuracy: 0.2422
3/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:41 1s/step - loss: 48.0897 - sparse_categorical_accuracy: 0.2622
4/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:38 1s/step - loss: 48.2575 - sparse_categorical_accuracy: 0.2786
5/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:37 1s/step - loss: 48.2910 - sparse_categorical_accuracy: 0.2917
6/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:36 1s/step - loss: 48.2856 - sparse_categorical_accuracy: 0.3012
7/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:35 1s/step - loss: 48.2775 - sparse_categorical_accuracy: 0.3067
8/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:34 1s/step - loss: 48.2703 - sparse_categorical_accuracy: 0.3098
9/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:32 1s/step - loss: 48.2452 - sparse_categorical_accuracy: 0.3132
10/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:32 1s/step - loss: 48.2307 - sparse_categorical_accuracy: 0.3147
11/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:31 1s/step - loss: 48.2224 - sparse_categorical_accuracy: 0.3148
12/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:30 1s/step - loss: 48.2436 - sparse_categorical_accuracy: 0.3154
13/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:29 1s/step - loss: 48.4003 - sparse_categorical_accuracy: 0.3165
14/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:28 1s/step - loss: 48.5188 - sparse_categorical_accuracy: 0.3173
15/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:27 1s/step - loss: 48.6114 - sparse_categorical_accuracy: 0.3177
16/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:26 1s/step - loss: 48.6889 - sparse_categorical_accuracy: 0.3188
17/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:25 1s/step - loss: 48.8238 - sparse_categorical_accuracy: 0.3200
18/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:23 1s/step - loss: 48.9324 - sparse_categorical_accuracy: 0.3209
19/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:22 1s/step - loss: 49.0280 - sparse_categorical_accuracy: 0.3215
20/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:22 1s/step - loss: 49.1080 - sparse_categorical_accuracy: 0.3221
21/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:21 1s/step - loss: 49.1839 - sparse_categorical_accuracy: 0.3223
22/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:20 1s/step - loss: 49.2456 - sparse_categorical_accuracy: 0.3229
23/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:19 1s/step - loss: 49.3109 - sparse_categorical_accuracy: 0.3234
24/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:18 1s/step - loss: 49.3649 - sparse_categorical_accuracy: 0.3238
25/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:17 1s/step - loss: 49.4094 - sparse_categorical_accuracy: 0.3242
26/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:16 1s/step - loss: 49.4442 - sparse_categorical_accuracy: 0.3245
27/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:15 1s/step - loss: 49.4733 - sparse_categorical_accuracy: 0.3249
28/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:14 1s/step - loss: 49.4992 - sparse_categorical_accuracy: 0.3254
29/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:13 1s/step - loss: 49.5312 - sparse_categorical_accuracy: 0.3259
30/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:12 1s/step - loss: 49.5580 - sparse_categorical_accuracy: 0.3263
31/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:11 1s/step - loss: 49.5893 - sparse_categorical_accuracy: 0.3266
32/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:10 1s/step - loss: 49.6143 - sparse_categorical_accuracy: 0.3269
33/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:09 1s/step - loss: 49.6356 - sparse_categorical_accuracy: 0.3271
34/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:08 1s/step - loss: 49.6533 - sparse_categorical_accuracy: 0.3274
35/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:07 1s/step - loss: 49.6677 - sparse_categorical_accuracy: 0.3276
36/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:06 1s/step - loss: 49.6871 - sparse_categorical_accuracy: 0.3280
37/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:05 1s/step - loss: 49.7037 - sparse_categorical_accuracy: 0.3283
38/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:04 1s/step - loss: 49.7168 - sparse_categorical_accuracy: 0.3287
39/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:03 1s/step - loss: 49.7293 - sparse_categorical_accuracy: 0.3290
40/100 ━━━━━━━━[37m━━━━━━━━━━━━ 1:02 1s/step - loss: 49.7390 - sparse_categorical_accuracy: 0.3293
41/100 ━━━━━━━━[37m━━━━━━━━━━━━ 1:01 1s/step - loss: 49.7459 - sparse_categorical_accuracy: 0.3296
42/100 ━━━━━━━━[37m━━━━━━━━━━━━ 1:00 1s/step - loss: 49.7542 - sparse_categorical_accuracy: 0.3298
43/100 ━━━━━━━━[37m━━━━━━━━━━━━ 59s 1s/step - loss: 49.7604 - sparse_categorical_accuracy: 0.3300
44/100 ━━━━━━━━[37m━━━━━━━━━━━━ 57s 1s/step - loss: 49.7769 - sparse_categorical_accuracy: 0.3302
45/100 ━━━━━━━━━[37m━━━━━━━━━━━ 57s 1s/step - loss: 49.7948 - sparse_categorical_accuracy: 0.3304
46/100 ━━━━━━━━━[37m━━━━━━━━━━━ 55s 1s/step - loss: 49.8099 - sparse_categorical_accuracy: 0.3306
47/100 ━━━━━━━━━[37m━━━━━━━━━━━ 54s 1s/step - loss: 49.8228 - sparse_categorical_accuracy: 0.3307
48/100 ━━━━━━━━━[37m━━━━━━━━━━━ 53s 1s/step - loss: 49.8335 - sparse_categorical_accuracy: 0.3307
49/100 ━━━━━━━━━[37m━━━━━━━━━━━ 52s 1s/step - loss: 49.8428 - sparse_categorical_accuracy: 0.3308
50/100 ━━━━━━━━━━[37m━━━━━━━━━━ 51s 1s/step - loss: 49.8501 - sparse_categorical_accuracy: 0.3308
51/100 ━━━━━━━━━━[37m━━━━━━━━━━ 50s 1s/step - loss: 49.8558 - sparse_categorical_accuracy: 0.3308
52/100 ━━━━━━━━━━[37m━━━━━━━━━━ 49s 1s/step - loss: 49.8601 - sparse_categorical_accuracy: 0.3308
53/100 ━━━━━━━━━━[37m━━━━━━━━━━ 48s 1s/step - loss: 49.8642 - sparse_categorical_accuracy: 0.3308
54/100 ━━━━━━━━━━[37m━━━━━━━━━━ 47s 1s/step - loss: 49.8671 - sparse_categorical_accuracy: 0.3309
55/100 ━━━━━━━━━━━[37m━━━━━━━━━ 46s 1s/step - loss: 49.8689 - sparse_categorical_accuracy: 0.3310
56/100 ━━━━━━━━━━━[37m━━━━━━━━━ 45s 1s/step - loss: 49.8703 - sparse_categorical_accuracy: 0.3311
57/100 ━━━━━━━━━━━[37m━━━━━━━━━ 44s 1s/step - loss: 49.8753 - sparse_categorical_accuracy: 0.3312
58/100 ━━━━━━━━━━━[37m━━━━━━━━━ 43s 1s/step - loss: 49.8791 - sparse_categorical_accuracy: 0.3313
59/100 ━━━━━━━━━━━[37m━━━━━━━━━ 42s 1s/step - loss: 49.8816 - sparse_categorical_accuracy: 0.3315
60/100 ━━━━━━━━━━━━[37m━━━━━━━━ 41s 1s/step - loss: 49.8859 - sparse_categorical_accuracy: 0.3316
61/100 ━━━━━━━━━━━━[37m━━━━━━━━ 40s 1s/step - loss: 49.8905 - sparse_categorical_accuracy: 0.3317
62/100 ━━━━━━━━━━━━[37m━━━━━━━━ 39s 1s/step - loss: 49.8946 - sparse_categorical_accuracy: 0.3318
63/100 ━━━━━━━━━━━━[37m━━━━━━━━ 38s 1s/step - loss: 49.8977 - sparse_categorical_accuracy: 0.3319
64/100 ━━━━━━━━━━━━[37m━━━━━━━━ 37s 1s/step - loss: 49.9000 - sparse_categorical_accuracy: 0.3320
65/100 ━━━━━━━━━━━━━[37m━━━━━━━ 36s 1s/step - loss: 49.9015 - sparse_categorical_accuracy: 0.3321
66/100 ━━━━━━━━━━━━━[37m━━━━━━━ 35s 1s/step - loss: 49.9024 - sparse_categorical_accuracy: 0.3322
67/100 ━━━━━━━━━━━━━[37m━━━━━━━ 34s 1s/step - loss: 49.9043 - sparse_categorical_accuracy: 0.3322
68/100 ━━━━━━━━━━━━━[37m━━━━━━━ 32s 1s/step - loss: 49.9063 - sparse_categorical_accuracy: 0.3322
69/100 ━━━━━━━━━━━━━[37m━━━━━━━ 31s 1s/step - loss: 49.9077 - sparse_categorical_accuracy: 0.3323
70/100 ━━━━━━━━━━━━━━[37m━━━━━━ 30s 1s/step - loss: 49.9082 - sparse_categorical_accuracy: 0.3323
71/100 ━━━━━━━━━━━━━━[37m━━━━━━ 29s 1s/step - loss: 49.9081 - sparse_categorical_accuracy: 0.3323
72/100 ━━━━━━━━━━━━━━[37m━━━━━━ 28s 1s/step - loss: 49.9074 - sparse_categorical_accuracy: 0.3323
73/100 ━━━━━━━━━━━━━━[37m━━━━━━ 27s 1s/step - loss: 49.9060 - sparse_categorical_accuracy: 0.3323
74/100 ━━━━━━━━━━━━━━[37m━━━━━━ 26s 1s/step - loss: 49.9042 - sparse_categorical_accuracy: 0.3323
75/100 ━━━━━━━━━━━━━━━[37m━━━━━ 25s 1s/step - loss: 49.9035 - sparse_categorical_accuracy: 0.3323
76/100 ━━━━━━━━━━━━━━━[37m━━━━━ 24s 1s/step - loss: 49.9023 - sparse_categorical_accuracy: 0.3323
77/100 ━━━━━━━━━━━━━━━[37m━━━━━ 23s 1s/step - loss: 49.9021 - sparse_categorical_accuracy: 0.3323
78/100 ━━━━━━━━━━━━━━━[37m━━━━━ 22s 1s/step - loss: 49.9030 - sparse_categorical_accuracy: 0.3323
79/100 ━━━━━━━━━━━━━━━[37m━━━━━ 21s 1s/step - loss: 49.9032 - sparse_categorical_accuracy: 0.3322
80/100 ━━━━━━━━━━━━━━━━[37m━━━━ 20s 1s/step - loss: 49.9029 - sparse_categorical_accuracy: 0.3322
81/100 ━━━━━━━━━━━━━━━━[37m━━━━ 19s 1s/step - loss: 49.9061 - sparse_categorical_accuracy: 0.3322
82/100 ━━━━━━━━━━━━━━━━[37m━━━━ 18s 1s/step - loss: 49.9088 - sparse_categorical_accuracy: 0.3322
83/100 ━━━━━━━━━━━━━━━━[37m━━━━ 17s 1s/step - loss: 49.9109 - sparse_categorical_accuracy: 0.3321
84/100 ━━━━━━━━━━━━━━━━[37m━━━━ 16s 1s/step - loss: 49.9124 - sparse_categorical_accuracy: 0.3321
85/100 ━━━━━━━━━━━━━━━━━[37m━━━ 15s 1s/step - loss: 49.9136 - sparse_categorical_accuracy: 0.3321
86/100 ━━━━━━━━━━━━━━━━━[37m━━━ 14s 1s/step - loss: 49.9143 - sparse_categorical_accuracy: 0.3321
87/100 ━━━━━━━━━━━━━━━━━[37m━━━ 13s 1s/step - loss: 49.9144 - sparse_categorical_accuracy: 0.3320
88/100 ━━━━━━━━━━━━━━━━━[37m━━━ 12s 1s/step - loss: 49.9143 - sparse_categorical_accuracy: 0.3320
89/100 ━━━━━━━━━━━━━━━━━[37m━━━ 11s 1s/step - loss: 49.9138 - sparse_categorical_accuracy: 0.3320
90/100 ━━━━━━━━━━━━━━━━━━[37m━━ 10s 1s/step - loss: 49.9136 - sparse_categorical_accuracy: 0.3319
91/100 ━━━━━━━━━━━━━━━━━━[37m━━ 9s 1s/step - loss: 49.9129 - sparse_categorical_accuracy: 0.3319
92/100 ━━━━━━━━━━━━━━━━━━[37m━━ 8s 1s/step - loss: 49.9119 - sparse_categorical_accuracy: 0.3318
93/100 ━━━━━━━━━━━━━━━━━━[37m━━ 7s 1s/step - loss: 49.9104 - sparse_categorical_accuracy: 0.3318
94/100 ━━━━━━━━━━━━━━━━━━[37m━━ 6s 1s/step - loss: 49.9085 - sparse_categorical_accuracy: 0.3317
95/100 ━━━━━━━━━━━━━━━━━━━[37m━ 5s 1s/step - loss: 49.9062 - sparse_categorical_accuracy: 0.3317
96/100 ━━━━━━━━━━━━━━━━━━━[37m━ 4s 1s/step - loss: 49.9041 - sparse_categorical_accuracy: 0.3317
97/100 ━━━━━━━━━━━━━━━━━━━[37m━ 3s 1s/step - loss: 49.9024 - sparse_categorical_accuracy: 0.3317
98/100 ━━━━━━━━━━━━━━━━━━━[37m━ 2s 1s/step - loss: 49.9033 - sparse_categorical_accuracy: 0.3317
99/100 ━━━━━━━━━━━━━━━━━━━[37m━ 1s 1s/step - loss: 49.9038 - sparse_categorical_accuracy: 0.3317
100/100 ━━━━━━━━━━━━━━━━━━━━ 0s 1s/step - loss: 49.9019 - sparse_categorical_accuracy: 0.3317
100/100 ━━━━━━━━━━━━━━━━━━━━ 108s 1s/step - loss: 49.9001 - sparse_categorical_accuracy: 0.3317 - val_loss: 69256328.0000 - val_sparse_categorical_accuracy: 0.3579
Epoch 20/20
1/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:42 1s/step - loss: 45.8100 - sparse_categorical_accuracy: 0.4062
2/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:37 990ms/step - loss: 45.8442 - sparse_categorical_accuracy: 0.4062
3/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:37 1s/step - loss: 45.8131 - sparse_categorical_accuracy: 0.3993
4/100 [37m━━━━━━━━━━━━━━━━━━━━ 1:36 1s/step - loss: 45.8064 - sparse_categorical_accuracy: 0.3913
5/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:35 1s/step - loss: 45.8227 - sparse_categorical_accuracy: 0.3868
6/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:35 1s/step - loss: 45.8191 - sparse_categorical_accuracy: 0.3831
7/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:34 1s/step - loss: 45.8214 - sparse_categorical_accuracy: 0.3762
8/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:33 1s/step - loss: 45.8634 - sparse_categorical_accuracy: 0.3702
9/100 ━[37m━━━━━━━━━━━━━━━━━━━ 1:31 1s/step - loss: 45.8982 - sparse_categorical_accuracy: 0.3634
10/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:31 1s/step - loss: 45.9172 - sparse_categorical_accuracy: 0.3589
11/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:30 1s/step - loss: 45.9713 - sparse_categorical_accuracy: 0.3560
12/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:28 1s/step - loss: 46.0114 - sparse_categorical_accuracy: 0.3548
13/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:28 1s/step - loss: 46.0793 - sparse_categorical_accuracy: 0.3535
14/100 ━━[37m━━━━━━━━━━━━━━━━━━ 1:27 1s/step - loss: 46.1364 - sparse_categorical_accuracy: 0.3520
15/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:26 1s/step - loss: 46.1765 - sparse_categorical_accuracy: 0.3509
16/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:25 1s/step - loss: 46.2080 - sparse_categorical_accuracy: 0.3504
17/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:24 1s/step - loss: 46.2316 - sparse_categorical_accuracy: 0.3498
18/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:23 1s/step - loss: 46.2481 - sparse_categorical_accuracy: 0.3491
19/100 ━━━[37m━━━━━━━━━━━━━━━━━ 1:22 1s/step - loss: 46.2610 - sparse_categorical_accuracy: 0.3484
20/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:21 1s/step - loss: 46.2706 - sparse_categorical_accuracy: 0.3473
21/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:20 1s/step - loss: 46.2769 - sparse_categorical_accuracy: 0.3465
22/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:19 1s/step - loss: 46.2793 - sparse_categorical_accuracy: 0.3458
23/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:18 1s/step - loss: 46.2795 - sparse_categorical_accuracy: 0.3452
24/100 ━━━━[37m━━━━━━━━━━━━━━━━ 1:17 1s/step - loss: 46.2889 - sparse_categorical_accuracy: 0.3452
25/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:16 1s/step - loss: 46.2960 - sparse_categorical_accuracy: 0.3454
26/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:15 1s/step - loss: 46.3007 - sparse_categorical_accuracy: 0.3455
27/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:14 1s/step - loss: 46.3038 - sparse_categorical_accuracy: 0.3455
28/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:13 1s/step - loss: 46.3053 - sparse_categorical_accuracy: 0.3455
29/100 ━━━━━[37m━━━━━━━━━━━━━━━ 1:12 1s/step - loss: 46.3057 - sparse_categorical_accuracy: 0.3454
30/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:11 1s/step - loss: 46.3050 - sparse_categorical_accuracy: 0.3453
31/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:10 1s/step - loss: 46.3095 - sparse_categorical_accuracy: 0.3451
32/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:09 1s/step - loss: 46.3201 - sparse_categorical_accuracy: 0.3449
33/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:08 1s/step - loss: 46.3293 - sparse_categorical_accuracy: 0.3446
34/100 ━━━━━━[37m━━━━━━━━━━━━━━ 1:07 1s/step - loss: 46.3368 - sparse_categorical_accuracy: 0.3444
35/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:06 1s/step - loss: 46.3819 - sparse_categorical_accuracy: 0.3445
36/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:05 1s/step - loss: 46.4228 - sparse_categorical_accuracy: 0.3445
37/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:04 1s/step - loss: 46.4597 - sparse_categorical_accuracy: 0.3446
38/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:03 1s/step - loss: 46.4928 - sparse_categorical_accuracy: 0.3446
39/100 ━━━━━━━[37m━━━━━━━━━━━━━ 1:02 1s/step - loss: 46.5227 - sparse_categorical_accuracy: 0.3448
40/100 ━━━━━━━━[37m━━━━━━━━━━━━ 1:01 1s/step - loss: 46.5496 - sparse_categorical_accuracy: 0.3448
41/100 ━━━━━━━━[37m━━━━━━━━━━━━ 1:00 1s/step - loss: 46.5741 - sparse_categorical_accuracy: 0.3447
42/100 ━━━━━━━━[37m━━━━━━━━━━━━ 59s 1s/step - loss: 46.5961 - sparse_categorical_accuracy: 0.3447
43/100 ━━━━━━━━[37m━━━━━━━━━━━━ 58s 1s/step - loss: 46.6158 - sparse_categorical_accuracy: 0.3446
44/100 ━━━━━━━━[37m━━━━━━━━━━━━ 57s 1s/step - loss: 46.6335 - sparse_categorical_accuracy: 0.3445
45/100 ━━━━━━━━━[37m━━━━━━━━━━━ 56s 1s/step - loss: 46.6635 - sparse_categorical_accuracy: 0.3444
46/100 ━━━━━━━━━[37m━━━━━━━━━━━ 55s 1s/step - loss: 46.6909 - sparse_categorical_accuracy: 0.3442
47/100 ━━━━━━━━━[37m━━━━━━━━━━━ 54s 1s/step - loss: 46.7195 - sparse_categorical_accuracy: 0.3439
48/100 ━━━━━━━━━[37m━━━━━━━━━━━ 53s 1s/step - loss: 46.7477 - sparse_categorical_accuracy: 0.3437
49/100 ━━━━━━━━━[37m━━━━━━━━━━━ 51s 1s/step - loss: 46.7799 - sparse_categorical_accuracy: 0.3435
50/100 ━━━━━━━━━━[37m━━━━━━━━━━ 50s 1s/step - loss: 46.8102 - sparse_categorical_accuracy: 0.3434
51/100 ━━━━━━━━━━[37m━━━━━━━━━━ 49s 1s/step - loss: 46.8381 - sparse_categorical_accuracy: 0.3432
52/100 ━━━━━━━━━━[37m━━━━━━━━━━ 48s 1s/step - loss: 46.8639 - sparse_categorical_accuracy: 0.3430
53/100 ━━━━━━━━━━[37m━━━━━━━━━━ 47s 1s/step - loss: 46.8877 - sparse_categorical_accuracy: 0.3429
54/100 ━━━━━━━━━━[37m━━━━━━━━━━ 46s 1s/step - loss: 46.9095 - sparse_categorical_accuracy: 0.3428
55/100 ━━━━━━━━━━━[37m━━━━━━━━━ 45s 1s/step - loss: 46.9390 - sparse_categorical_accuracy: 0.3427
56/100 ━━━━━━━━━━━[37m━━━━━━━━━ 44s 1s/step - loss: 46.9676 - sparse_categorical_accuracy: 0.3425
57/100 ━━━━━━━━━━━[37m━━━━━━━━━ 43s 1s/step - loss: 46.9940 - sparse_categorical_accuracy: 0.3423
58/100 ━━━━━━━━━━━[37m━━━━━━━━━ 42s 1s/step - loss: 47.0190 - sparse_categorical_accuracy: 0.3422
59/100 ━━━━━━━━━━━[37m━━━━━━━━━ 41s 1s/step - loss: 47.0420 - sparse_categorical_accuracy: 0.3421
60/100 ━━━━━━━━━━━━[37m━━━━━━━━ 40s 1s/step - loss: 47.0631 - sparse_categorical_accuracy: 0.3421
61/100 ━━━━━━━━━━━━[37m━━━━━━━━ 39s 1s/step - loss: 47.0824 - sparse_categorical_accuracy: 0.3420
62/100 ━━━━━━━━━━━━[37m━━━━━━━━ 38s 1s/step - loss: 47.1005 - sparse_categorical_accuracy: 0.3419
63/100 ━━━━━━━━━━━━[37m━━━━━━━━ 37s 1s/step - loss: 47.1221 - sparse_categorical_accuracy: 0.3419
64/100 ━━━━━━━━━━━━[37m━━━━━━━━ 36s 1s/step - loss: 47.1436 - sparse_categorical_accuracy: 0.3418
65/100 ━━━━━━━━━━━━━[37m━━━━━━━ 35s 1s/step - loss: 47.1636 - sparse_categorical_accuracy: 0.3417
66/100 ━━━━━━━━━━━━━[37m━━━━━━━ 34s 1s/step - loss: 47.1827 - sparse_categorical_accuracy: 0.3417
67/100 ━━━━━━━━━━━━━[37m━━━━━━━ 33s 1s/step - loss: 47.2009 - sparse_categorical_accuracy: 0.3417
68/100 ━━━━━━━━━━━━━[37m━━━━━━━ 32s 1s/step - loss: 47.2186 - sparse_categorical_accuracy: 0.3417
69/100 ━━━━━━━━━━━━━[37m━━━━━━━ 31s 1s/step - loss: 47.2351 - sparse_categorical_accuracy: 0.3418
70/100 ━━━━━━━━━━━━━━[37m━━━━━━ 30s 1s/step - loss: 47.2515 - sparse_categorical_accuracy: 0.3418
71/100 ━━━━━━━━━━━━━━[37m━━━━━━ 29s 1s/step - loss: 47.2666 - sparse_categorical_accuracy: 0.3418
72/100 ━━━━━━━━━━━━━━[37m━━━━━━ 28s 1s/step - loss: 47.2820 - sparse_categorical_accuracy: 0.3418
73/100 ━━━━━━━━━━━━━━[37m━━━━━━ 27s 1s/step - loss: 47.2965 - sparse_categorical_accuracy: 0.3419
74/100 ━━━━━━━━━━━━━━[37m━━━━━━ 26s 1s/step - loss: 47.3101 - sparse_categorical_accuracy: 0.3419
75/100 ━━━━━━━━━━━━━━━[37m━━━━━ 25s 1s/step - loss: 47.3227 - sparse_categorical_accuracy: 0.3419
76/100 ━━━━━━━━━━━━━━━[37m━━━━━ 24s 1s/step - loss: 47.3343 - sparse_categorical_accuracy: 0.3419
77/100 ━━━━━━━━━━━━━━━[37m━━━━━ 23s 1s/step - loss: 47.3463 - sparse_categorical_accuracy: 0.3418
78/100 ━━━━━━━━━━━━━━━[37m━━━━━ 22s 1s/step - loss: 47.3574 - sparse_categorical_accuracy: 0.3418
79/100 ━━━━━━━━━━━━━━━[37m━━━━━ 21s 1s/step - loss: 47.3678 - sparse_categorical_accuracy: 0.3418
80/100 ━━━━━━━━━━━━━━━━[37m━━━━ 20s 1s/step - loss: 47.3773 - sparse_categorical_accuracy: 0.3417
81/100 ━━━━━━━━━━━━━━━━[37m━━━━ 19s 1s/step - loss: 47.3878 - sparse_categorical_accuracy: 0.3417
82/100 ━━━━━━━━━━━━━━━━[37m━━━━ 18s 1s/step - loss: 47.3974 - sparse_categorical_accuracy: 0.3417
83/100 ━━━━━━━━━━━━━━━━[37m━━━━ 17s 1s/step - loss: 47.4062 - sparse_categorical_accuracy: 0.3416
84/100 ━━━━━━━━━━━━━━━━[37m━━━━ 16s 1s/step - loss: 47.4142 - sparse_categorical_accuracy: 0.3416
85/100 ━━━━━━━━━━━━━━━━━[37m━━━ 15s 1s/step - loss: 47.4216 - sparse_categorical_accuracy: 0.3415
86/100 ━━━━━━━━━━━━━━━━━[37m━━━ 14s 1s/step - loss: 47.4285 - sparse_categorical_accuracy: 0.3414
87/100 ━━━━━━━━━━━━━━━━━[37m━━━ 13s 1s/step - loss: 47.4351 - sparse_categorical_accuracy: 0.3414
88/100 ━━━━━━━━━━━━━━━━━[37m━━━ 12s 1s/step - loss: 47.4411 - sparse_categorical_accuracy: 0.3413
89/100 ━━━━━━━━━━━━━━━━━[37m━━━ 11s 1s/step - loss: 47.4466 - sparse_categorical_accuracy: 0.3412
90/100 ━━━━━━━━━━━━━━━━━━[37m━━ 10s 1s/step - loss: 47.4517 - sparse_categorical_accuracy: 0.3411
91/100 ━━━━━━━━━━━━━━━━━━[37m━━ 9s 1s/step - loss: 47.4563 - sparse_categorical_accuracy: 0.3410
92/100 ━━━━━━━━━━━━━━━━━━[37m━━ 8s 1s/step - loss: 47.4604 - sparse_categorical_accuracy: 0.3410
93/100 ━━━━━━━━━━━━━━━━━━[37m━━ 7s 1s/step - loss: 47.4641 - sparse_categorical_accuracy: 0.3409
94/100 ━━━━━━━━━━━━━━━━━━[37m━━ 6s 1s/step - loss: 47.4688 - sparse_categorical_accuracy: 0.3409
95/100 ━━━━━━━━━━━━━━━━━━━[37m━ 5s 1s/step - loss: 47.4731 - sparse_categorical_accuracy: 0.3408
96/100 ━━━━━━━━━━━━━━━━━━━[37m━ 4s 1s/step - loss: 47.4771 - sparse_categorical_accuracy: 0.3407
97/100 ━━━━━━━━━━━━━━━━━━━[37m━ 3s 1s/step - loss: 47.4814 - sparse_categorical_accuracy: 0.3406
98/100 ━━━━━━━━━━━━━━━━━━━[37m━ 2s 1s/step - loss: 47.4854 - sparse_categorical_accuracy: 0.3406
99/100 ━━━━━━━━━━━━━━━━━━━[37m━ 1s 1s/step - loss: 47.4889 - sparse_categorical_accuracy: 0.3405
100/100 ━━━━━━━━━━━━━━━━━━━━ 0s 1s/step - loss: 47.4901 - sparse_categorical_accuracy: 0.3404
100/100 ━━━━━━━━━━━━━━━━━━━━ 106s 1s/step - loss: 47.4913 - sparse_categorical_accuracy: 0.3404 - val_loss: 1814011445248.0000 - val_sparse_categorical_accuracy: 0.3592
<keras.src.callbacks.history.History at 0x7f596cb7b8e0>
可视化预测
我们可以使用 matplotlib 可视化我们训练的模型性能。
data = test_dataset.take(1)
points, labels = list(data)[0]
points = points[:8, ...]
labels = labels[:8, ...]
# 通过模型运行测试数据
preds = model.predict(points)
preds = ops.argmax(preds, -1)
points = points.numpy()
# 绘制带有预测类和标签的点
fig = plt.figure(figsize=(15, 10))
for i in range(8):
ax = fig.add_subplot(2, 4, i + 1, projection="3d")
ax.scatter(points[i, :, 0], points[i, :, 1], points[i, :, 2])
ax.set_title(
"pred: {:}, label: {:}".format(
CLASS_MAP[preds[i].numpy()], CLASS_MAP[labels.numpy()[i]]
)
)
ax.set_axis_off()
plt.show()
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 404ms/step
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 405ms/step
