torchvision自带的transforms.to_tensor用法

import torch
import torchvision.transforms as tf
import numpy as np
raw_input = np.ones((224,224,3),dtype=np.uint8)
tt_tf = tf.ToTensor()
# tt_tf = torch.as_tensor
output_ = tt_tf(raw_input)

官方解释：

Convert a PIL Image or numpy.ndarray to tensor：
Converts a PIL Image or numpy.ndarray (H x W x C) in the range [0, 255] to a torch.FloatTensor of shape (C x H x W) in the range [0.0, 1.0] if the PIL Image belongs to one of the modes (L, LA, P, I, F, RGB, YCbCr, RGBA, CMYK, 1) or if the numpy.ndarray has dtype = np.uint8.

In the other cases, tensors are returned without scaling.

通俗解释：

1. 转换为torch.FloatTensor
2. 将通道提前
3. 可以将特定类型的图片或者uint8的ndarray归一化（除255），其他不做归一化

tip：如果想只是转换为tensor，不做其他改变，可以使用 torch.as_array()