常见代码书写
from torchvision import transforms
data_transform = {"train": transforms.Compose([
transforms.RandomResizedCrop(224),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])}
transforms.RandomResizedCrop()
""" A crop of random size (default: of 0.08 to 1.0) of the original size and a random aspect ratio (default: of 3/4 to 4/3) of the original aspect ratio is made. This crop is finally resized to given size. This is popularly used to train the Inception networks. """
将图像进行随机裁剪为不同大小的高宽比，然后将裁剪后的图像缩放的指定的大小。
默认缩放区间为 scale(0.08, 1.0) ，高宽比例为（3/4 到 4/3）
from PIL import Image
import matplotlib.pyplot as plt
img = Image.open('./img.png')
img.size
plt.imshow(img)
img2 = transforms.RandomResizedCrop(224)(img) plt.imshow(img2)transforms.RandomHorizontalFlip()
"""Horizontally flip the given image randomly with a given probability.
If the image is torch Tensor, it is expected
to have [..., H, W] shape, where ... means an arbitrary number of leading
dimensions
Args:
p (float): probability of the image being flipped. Default value is 0.5
"""
以给定的概率随机水平翻转给定的PIL的图像，默认概率为0.5
img3 = transforms.RandomHorizontalFlip()(img) img3.size, plt.imshow(img3)transforms.ToTensor()
"""
Convert a ``PIL Image`` or ``numpy.ndarray`` to tensor. This transform does not support torchscript.
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.
.. note::
Because the input image is scaled to [0.0, 1.0], this transformation should not be used when
transforming target image masks. See the `references`_ for implementing the transforms for image masks.
"""
- 将 numpy 的 ndarray 或 PIL.Image 读的图片转换成形状为（C, H, W）的 Tensor 格式；
- 然后将数值除以255，缩放到 [0, 1.0] 之间
- 图片的通道顺序跟数据的读取方式有关。例如 cv2 : (B, G, R)；PIL.Image:（R, G, B）
print(transforms.ToTensor()(img))transforms.Normalize()
"""
Normalize a tensor image with mean and standard deviation.
This transform does not support PIL Image.
Given mean: ``(mean[1],...,mean[n])`` and std: ``(std[1],..,std[n])`` for ``n``
channels, this transform will normalize each channel of the input
``torch.*Tensor`` i.e.,
``output[channel] = (input[channel] - mean[channel]) / std[channel]``
.. note::
This transform acts out of place, i.e., it does not mutate the input tensor.
Args:
mean (sequence): Sequence of means for each channel.
std (sequence): Sequence of standard deviations for each channel.
inplace(bool,optional): Bool to make this operation in-place.
"""
使用均值和标准差对图像的每个通道进行操作，支持 Tensor 格式
参数：
mean ：各个通道的平均值；
std ：各个通道的标准差；
inplace ：是否原地操作
print(transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))(transforms.ToTensor()(img)))
这里将图像的数值缩放到了 [-1, 1] 区间，这样经过 mean 和 std 处理后可以让数据符合正态分布。
