Shortcuts

学习基础知识 || 快速入门 || 张量 || 数据集和数据加载器 || 变换 || 构建模型 || 自动求导 || 优化 || 保存和加载模型

转换

创建日期:2021年2月9日 | 最后更新:2021年8月11日 | 最后验证:未验证

数据并不总是以训练机器学习算法所需的最终处理形式出现。我们使用transforms来对数据进行一些操作,使其适合训练。

所有TorchVision数据集都有两个参数 -transform 用于修改特征和 target_transform 用于修改标签 - 这些参数接受包含转换逻辑的可调用对象。 torchvision.transforms 模块提供了 几种常用的转换功能。

FashionMNIST 的特征是 PIL 图像格式,标签是整数。 对于训练,我们需要将特征转换为归一化的张量,并将标签转换为 one-hot 编码的张量。 为了进行这些转换,我们使用 ToTensorLambda

import torch
from torchvision import datasets
from torchvision.transforms import ToTensor, Lambda

ds = datasets.FashionMNIST(
    root="data",
    train=True,
    download=True,
    transform=ToTensor(),
    target_transform=Lambda(lambda y: torch.zeros(10, dtype=torch.float).scatter_(0, torch.tensor(y), value=1))
)
Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/train-images-idx3-ubyte.gz
Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/train-images-idx3-ubyte.gz to data/FashionMNIST/raw/train-images-idx3-ubyte.gz

  0%|          | 0.00/26.4M [00:00<?, ?B/s]
  0%|          | 65.5k/26.4M [00:00<01:12, 364kB/s]
  1%|          | 229k/26.4M [00:00<00:38, 685kB/s]
  4%|3         | 950k/26.4M [00:00<00:11, 2.20MB/s]
 15%|#4        | 3.83M/26.4M [00:00<00:02, 7.65MB/s]
 37%|###7      | 9.90M/26.4M [00:00<00:00, 17.0MB/s]
 59%|#####9    | 15.7M/26.4M [00:01<00:00, 22.1MB/s]
 82%|########1 | 21.7M/26.4M [00:01<00:00, 30.1MB/s]
 95%|#########5| 25.1M/26.4M [00:01<00:00, 26.7MB/s]
100%|##########| 26.4M/26.4M [00:01<00:00, 19.4MB/s]
Extracting data/FashionMNIST/raw/train-images-idx3-ubyte.gz to data/FashionMNIST/raw

Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/train-labels-idx1-ubyte.gz
Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/train-labels-idx1-ubyte.gz to data/FashionMNIST/raw/train-labels-idx1-ubyte.gz

  0%|          | 0.00/29.5k [00:00<?, ?B/s]
100%|##########| 29.5k/29.5k [00:00<00:00, 322kB/s]
Extracting data/FashionMNIST/raw/train-labels-idx1-ubyte.gz to data/FashionMNIST/raw

Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/t10k-images-idx3-ubyte.gz
Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/t10k-images-idx3-ubyte.gz to data/FashionMNIST/raw/t10k-images-idx3-ubyte.gz

  0%|          | 0.00/4.42M [00:00<?, ?B/s]
  1%|1         | 65.5k/4.42M [00:00<00:12, 363kB/s]
  5%|5         | 229k/4.42M [00:00<00:06, 681kB/s]
 19%|#9        | 852k/4.42M [00:00<00:01, 2.42MB/s]
 44%|####3     | 1.93M/4.42M [00:00<00:00, 4.13MB/s]
100%|##########| 4.42M/4.42M [00:00<00:00, 6.08MB/s]
Extracting data/FashionMNIST/raw/t10k-images-idx3-ubyte.gz to data/FashionMNIST/raw

Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/t10k-labels-idx1-ubyte.gz
Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/t10k-labels-idx1-ubyte.gz to data/FashionMNIST/raw/t10k-labels-idx1-ubyte.gz

  0%|          | 0.00/5.15k [00:00<?, ?B/s]
100%|##########| 5.15k/5.15k [00:00<00:00, 34.0MB/s]
Extracting data/FashionMNIST/raw/t10k-labels-idx1-ubyte.gz to data/FashionMNIST/raw

ToTensor()

ToTensor 将PIL图像或NumPy ndarray转换为FloatTensor,并将图像的像素强度值缩放到[0., 1.]范围内。

Lambda 转换

Lambda 转换应用任何用户定义的 lambda 函数。在这里,我们定义了一个函数将整数转换为 one-hot 编码的张量。它首先创建一个大小为 10 的零张量(我们数据集中的标签数量),并调用 scatter_,它在由标签 y 给出的索引上分配 value=1

target_transform = Lambda(lambda y: torch.zeros(
    10, dtype=torch.float).scatter_(dim=0, index=torch.tensor(y), value=1))