对于这个API,我最开始的预想是从 '猫1猫2猫3猫4狗1狗2狗3狗4' 中分割出 '猫1猫2狗4狗1' 和 '猫4猫3狗2狗3' ,但是打印结果和我预想的不一样
数据集文件的存放路径如下图
测试代码如下
- import torch
- import torchvision
-
- transform = torchvision.transforms.Compose([
- torchvision.transforms.Resize((512,512)), # 调整图像大小为 224x224
- torchvision.transforms.ToTensor(), # 转换为张量
- torchvision.transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]) # 归一化
- ])
- dataset = torchvision.datasets.ImageFolder('C:\\Users\\ASUS\\PycharmProjects\\pythonProject1\\cats_and_dogs_train',
- transform=transform)
-
- val_ratio = 0.2
- val_size = int(len(dataset) * val_ratio)
- train_size = len(dataset) - val_size
- train_dataset, val_dataset = torch.utils.data.random_split(dataset, [train_size, val_size])
-
-
- cats_num = 0
- dogs_num = 0
- for x,y in train_dataset:
- if y == 0:
- cats_num += 1
- else:
- dogs_num += 1
-
- print("cats_num: ",cats_num)
- print("dogs_num: ",dogs_num)
-
- cats_num2 = 0
- dogs_num2 = 0
- for x,y in val_dataset:
- if y == 0:
- cats_num2 += 1
- else:
- dogs_num2 += 1
-
- print("cats_num2: ",cats_num2)
- print("dogs_num2: ",dogs_num2)
输出如下
可以看到总共25000张图片的数据集,分割后并不是cats_num:10000,dogs_num:10000,cats_num2:2500,dogs_num2:2500
也就是说,分割后的状况是猫狗的数量并不一定相等,如结果为 '猫1猫2猫4狗1' 和 '狗4猫3狗2狗3'