Keras 应用

import keras
from keras.applications.resnet50 import ResNet50
from keras.applications.resnet50 import preprocess_input, decode_predictions
import numpy as np

model = ResNet50(weights='imagenet')

img_path = 'elephant.jpg'
img = keras.utils.load_img(img_path, target_size=(224, 224))
x = keras.utils.img_to_array(img)
x = np.expand_dims(x, axis=0)
x = preprocess_input(x)

preds = model.predict(x)
# 将结果解码为元组列表（类别，描述，概率）
# （批次中每个样本一个这样的列表）
print('Predicted:', decode_predictions(preds, top=3)[0])
# Predicted: [(u'n02504013', u'Indian_elephant', 0.82658225), (u'n01871265', u'tusker', 0.1122357), (u'n02504458', u'African_elephant', 0.061040461)]

import keras
from keras.applications.vgg16 import VGG16
from keras.applications.vgg16 import preprocess_input
import numpy as np

model = VGG16(weights='imagenet', include_top=False)

img_path = 'elephant.jpg'
img = keras.utils.load_img(img_path, target_size=(224, 224))
x = keras.utils.img_to_array(img)
x = np.expand_dims(x, axis=0)
x = preprocess_input(x)

features = model.predict(x)

from keras.applications.vgg19 import VGG19
from keras.applications.vgg19 import preprocess_input
from keras.models import Model
import numpy as np

base_model = VGG19(weights='imagenet')
model = Model(inputs=base_model.input, outputs=base_model.get_layer('block4_pool').output)

img_path = 'elephant.jpg'
img = keras.utils.load_img(img_path, target_size=(224, 224))
x = keras.utils.img_to_array(img)
x = np.expand_dims(x, axis=0)
x = preprocess_input(x)

block4_pool_features = model.predict(x)

from keras.applications.inception_v3 import InceptionV3
from keras.models import Model
from keras.layers import Dense, GlobalAveragePooling2D

# 创建基础预训练模型
base_model = InceptionV3(weights='imagenet', include_top=False)

# 添加全局空间平均池化层
x = base_model.output
x = GlobalAveragePooling2D()(x)
# 添加一个全连接层
x = Dense(1024, activation='relu')(x)
# 添加一个逻辑层 -- 假设我们有 200 个类别
predictions = Dense(200, activation='softmax')(x)

# 这是我们将训练的模型
model = Model(inputs=base_model.input, outputs=predictions)

# 首先：只训练顶部层（这些层是随机初始化的）
# 即固定所有卷积 InceptionV3 层
for layer in base_model.layers:
    layer.trainable = False

# 编译模型（应在设置层为不可训练后进行）
model.compile(optimizer='rmsprop', loss='categorical_crossentropy')

# 在新数据上训练模型几轮
model.fit(...)

# 此时，顶部层训练良好，我们可以开始微调
# 从 inception V3 中的卷积层。我们将冻结底部 N 层
# 并训练剩余的顶部层。

# 可视化层名称和层索引以查看需要冻结多少层
for i, layer in enumerate(base_model.layers):
   print(i, layer.name)

# 我们选择训练前两个 inception 块，即我们将冻结
# 前 249 层并解冻其余层：
for layer in model.layers[:249]:
   layer.trainable = False
for layer in model.layers[249:]:
   layer.trainable = True

# 我们需要重新编译模型以使这些修改生效
# 我们使用学习率较低的 SGD
from keras.optimizers import SGD
model.compile(optimizer=SGD(lr=0.0001, momentum=0.9), loss='categorical_crossentropy')

# 我们再次训练模型（这次微调前两个 inception 块
# 以及顶部的 Dense 层
model.fit(...)

from keras.applications.inception_v3 import InceptionV3
from keras.layers import Input

# 这也可以是不同 Keras 模型或层的输出
input_tensor = Input(shape=(224, 224, 3))

model = InceptionV3(input_tensor=input_tensor, weights='imagenet', include_top=True)