【Pytorch】Transform的使用 - 学习笔记

新年快乐~
惯例视频

总体结构

1 - Transform的用法

看一下整个页面~

1.1 PIL读取

from PIL import Image
from torchvision import transforms

# python的用法-> Tensor数据类型
# 通过transform.ToTensor去解决
# 1、transform如何使用（python）
# 2、为什么我们需要Tensor数据类型

# 绝对路径 D:\研究生\代码尝试\dataset\hymenoptera_data\train\ants_image\0013035.jpg
# 相对路径 dataset/hymenoptera_data/train/ants_image/0013035.jpg
img_path ="dataset/hymenoptera_data/train/ants_image/0013035.jpg"
# img_path_abs = "D:\研究生\代码尝试\dataset\hymenoptera_data\train\ants_image\0013035.jpg"
# 使用相对路径的原因是，绝对路径没法当作字符串
# Image是python内置的库
img = Image.open(img_path)
# print(img)
# 1、transform如何使用（python）
tensor_trans = transforms.ToTensor()
# ctrl+p查看参数
tensor_img = tensor_trans(img)

print(tensor_img)

输出结果为

tensor([[[0.3137, 0.3137, 0.3137,  ..., 0.3176, 0.3098, 0.2980],
         [0.3176, 0.3176, 0.3176,  ..., 0.3176, 0.3098, 0.2980],
         [0.3216, 0.3216, 0.3216,  ..., 0.3137, 0.3098, 0.3020],
         ...,
         [0.3412, 0.3412, 0.3373,  ..., 0.1725, 0.3725, 0.3529],
         [0.3412, 0.3412, 0.3373,  ..., 0.3294, 0.3529, 0.3294],
         [0.3412, 0.3412, 0.3373,  ..., 0.3098, 0.3059, 0.3294]],

        [[0.5922, 0.5922, 0.5922,  ..., 0.5961, 0.5882, 0.5765],
         [0.5961, 0.5961, 0.5961,  ..., 0.5961, 0.5882, 0.5765],
         [0.6000, 0.6000, 0.6000,  ..., 0.5922, 0.5882, 0.5804],
         ...,
         [0.6275, 0.6275, 0.6235,  ..., 0.3608, 0.6196, 0.6157],
         [0.6275, 0.6275, 0.6235,  ..., 0.5765, 0.6275, 0.5961],
         [0.6275, 0.6275, 0.6235,  ..., 0.6275, 0.6235, 0.6314]],

        [[0.9137, 0.9137, 0.9137,  ..., 0.9176, 0.9098, 0.8980],
         [0.9176, 0.9176, 0.9176,  ..., 0.9176, 0.9098, 0.8980],
         [0.9216, 0.9216, 0.9216,  ..., 0.9137, 0.9098, 0.9020],
         ...,
         [0.9294, 0.9294, 0.9255,  ..., 0.5529, 0.9216, 0.8941],
         [0.9294, 0.9294, 0.9255,  ..., 0.8863, 1.0000, 0.9137],
         [0.9294, 0.9294, 0.9255,  ..., 0.9490, 0.9804, 0.9137]]])

进程已结束，退出代码为 0

1.2 OpenCV读取

import cv2
cv_img = cv2.imread(img_path)

1.3 Tensorboard显示图片

from PIL import Image
from torch.utils.tensorboard import SummaryWriter
from torchvision import transforms

# python的用法-> Tensor数据类型
# 通过transform.ToTensor去解决
# 1、transform如何使用（python）
# 2、为什么我们需要Tensor数据类型

# 绝对路径 D:\研究生\代码尝试\dataset\hymenoptera_data\train\ants_image\0013035.jpg
# 相对路径 dataset/hymenoptera_data/train/ants_image/0013035.jpg
img_path ="dataset/hymenoptera_data/train/ants_image/0013035.jpg"
# img_path_abs = "D:\研究生\代码尝试\dataset\hymenoptera_data\train\ants_image\0013035.jpg"
# 使用相对路径的原因是，绝对路径没法当作字符串
# Image是python内置的库
img = Image.open(img_path)
# print(img)

writer = SummaryWriter("logs")

# 1、transform如何使用（python）
tensor_trans = transforms.ToTensor()
# ctrl+p查看参数
tensor_img = tensor_trans(img)

# print(tensor_img)
# 2、为什么我们需要Tensor数据类型
# Tensor里面包含了一些神经网络反向传播里面使用到的参数

writer.add_image("Tensor_img", tensor_img)
writer.close()

打开Tensorboard
在终端输入

(pytorch) D:\研究生\代码尝试>tensorboard --logdir=logs