如何使一个batch内加载不同大小的数据

解决:自定义dataloader内的collate_fn函数
做法: batch内大小可变的输入

import torch
from torch.utils.data import DataLoader
from torchvision import transforms
import torchvision.datasets as datasets
import matplotlib.pyplot as plt

# a simple custom collate function, just to show the idea
def my_collate(batch):
    data = [item[0] for item in batch]
    target = [item[1] for item in batch]
    target = torch.LongTensor(target)
    return [data, target]


#  do not do randomCrop to show that the custom collate_fn can handle images of different size
train_transforms = transforms.Compose([transforms.Scale(size = 224),
                                       transforms.ToTensor(),
                                       ])

# change root to valid dir in your system, see ImageFolder documentation for more info
train_dataset = datasets.ImageFolder(root="/hd1/jdhao/toyset",
                                     transform=train_transforms)

train_detaloader = DataLoader(dataset=train_dataset,
                      batch_size=4,
                      shuffle=True,
                      collate_fn=my_collate, # use custom collate function here
                      pin_memory=True)

batch内的多张图像(或多个label),表示为一个list,每个元素为读入的大小不等的图像.