pytorch学习|深度学习pytorch代码: transforms结构及用法常见的transforms 机器学习|python|图像处理|pyto

transforms.py 工具箱

totensor
resize

图片-------->工具(transforms)---------->结果
|
使用工具创建具体的工具
transforms.ToTensor()
使用工具：
输入：图片
【pytorch学习|深度学习pytorch代码: transforms结构及用法常见的transforms】输出：result = tool(图片)

from PIL import Image as imim from tensorboardX import SummaryWriter from torchvision import transforms # python的用法 -》 tensor的数据类型 # 通过transform.ToTensor解决两个问题 # 1.transforms该如何让使用(python) # 2.为什么需要ToTensor类型img_path = r"C:\Users\123\Desktop\python4.7\hymenoptera_data\train\ants\6240338_93729615ec.jpg" img = imim.open(img_path) # print(img)writer = SummaryWriter ("logs") tensor_trans = transforms.ToTensor() tensor_img = tensor_trans(img)# ctrl+p查看需要填入的类型 # print(tensor_img) writer.add_image("Tensor_img", tensor_img) writer.close()

常见的Transforms
* PIL* Image.open()
* tensor* ToTensor()
* narray* cv.imread()
注意事项：

关注输入和输出类型
多看官方文档
关注方法需要什么参数
不知道返回值的时候print / print(type()) / debug

from PIL import Image from tensorboardX import SummaryWriter from torchvision import transformswriter = SummaryWriter("logs") img = Image.open(r"C:\Users\123\Desktop\python4.7\flower.jpg") print(img)# ToTensor的使用 trans_totensor = transforms.ToTensor()# 创建对象 img_tensor = trans_totensor(img)# 调用方法 writer.add_image("ToTensor", img_tensor)# Normalize # output[channel] = (input[channel] - mean[channel]) / std[channel]均值和方差 print(img_tensor[0][0][0])# 像素的第一层第一行第一列 trans_norm = transforms.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5]) img_norm = trans_norm(img_tensor) print(img_norm[0][0][0]) writer.add_image("Normalize", img_norm)# 绘制图片# resize - 1 print(img.size) trans_resize = transforms.Resize(512, 512) # img PIL -> resize -> img_resize PIL img_resize = trans_resize(img) # img_resize PIL -> totensor -> img_resize tensor image_resize = trans_totensor(img_resize) print(img_resize) writer.add_image("Resize-1", img_resize, 0) print(img_resize)# Compose - resize - 2 trans_resize_2 = transforms.Resize(512) # PIL -> PIL -> tensor trans_compose = transforms.Compose( [trans_resize_2, trans_totensor] ) img_resize_2 = trans_compose(img) writer.add_image("Resize-2", img_resize_2, 1)# RandomCrop trans_random = transforms.RandomCrop(512) trans_compose_2 = transforms.Compose([trans_random, trans_totensor]) for i in range(10):# 裁剪10个 img_crop = trans_compose_2(img) writer.add_image("RandomCrop", img_crop, i)writer.close()