作用:主要对图片进行一些变化
python的用法 -》tensor数据类型(以ToTensor工具来讲解transforms的用法)
通过transforms.ToTensor去解决两个问题
1.transforms如何使用(在python中)
2.为什么需要Tensor数据类型
出现错误,波浪线时 alt+回车 可以查看解决方案
查看需要什么参数 Ctrl+p
# 绝对路径 C:\Users\11404\PycharmProjects\pytorch_learning\dataset2\train\ants_image\0013035.jpg
# 相对路径 dataset2/train/ants_image/0013035.jpg
img_path = "dataset2/train/ants_image/0013035.jpg"
img = Image.open(img_path)
writer = SummaryWriter("logs")
# 1.transforms如何使用(在python中)
# 创建一个具体的工具
tensor_trans = transforms.ToTensor()
# 使用工具
tensor_img = tensor_trans(img)
writer.add_image("Tensor_img", tensor_img)
writer.close()
常见的Transforms(学会查看官方文档
ToTensor使用
from PIL import Image
from torch.utils.tensorboard import SummaryWriter
from torchvision import transforms
writer = SummaryWriter("logs")
img = Image.open("image/0013035.jpg")
trans_totensor = transforms.ToTensor()
img_Tensor = trans_totensor(img)
writer.add_image("ToTensor", img_Tensor)
writer.close()
结果:
Normalize(归一化:
# Normalize
print(img_Tensor[0][0][0])
trans_nor = transforms.Normalize([0.5, 0.5, 0.5],[0.5, 0.5, 0.5])
img_norm = trans_nor(img_Tensor)
print(img_norm[0][0][0])
writer.add_image("Normalize", img_norm)
结果:
Resize(调整图像尺寸:
# Resize
print(img.size)
trans_resize = transforms.Resize((512,512))
img_resize = trans_resize(img)
print(img_resize)
img_resize = trans_totensor(img_resize)
print(img_resize)
writer.add_image("Resize", img_resize)
结果:
Compose(把不同的transforms类结合在一起:
# Compose
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", img_resize_2, 1)
结果:
RandomCrop(随机裁剪:
# RandomCrop
trans_random = transforms.RandomCrop(20, 40)
trans_compose_2 = transforms.Compose([trans_random, trans_totensor])
for i in range(10):
img_crop = trans_compose_2(img)
writer.add_image("RandomCropHW", img_crop, i)
结果:
总结使用方法
首先:关注输入和输出类型
其次: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