PyTorch整理(三)：变换

3 变换

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。我们使用转换来对数据进行一些操作并使其适合训练。

所有 TorchVision 数据集都有两个参数 -transform修改特征和 target_transform修改标签 - 接受包含转换逻辑的可调用对象。该torchvision.transforms模块提供几种常用的变换开箱。

FashionMNIST 特征采用 PIL Image 格式，标签为整数。对于训练，我们需要将特征作为归一化张量，将标签作为单热编码张量。为了进行这些转换，我们使用ToTensor和Lambda。

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))
)

结果：

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
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
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
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
Extracting data/FashionMNIST/raw/t10k-labels-idx1-ubyte.gz to data/FashionMNIST/raw

3.1 ToTensor()

ToTensor 将 PIL 图像或 NumPyndarray转换为FloatTensor. 并在 [0., 1.] 范围内缩放图像的像素强度值

3.2 Lambda 变换

Lambda 转换适用于任何用户定义的 lambda 函数。在这里，我们定义了一个函数来将整数转换为单热编码的张量。它首先创建一个大小为 10（我们数据集中的标签数量）的零张量，并调用 scatter_，它value=1在标签给定的索引上分配 a y。

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