我正在使用PyTorch处理一个以图像作为输入的数据分类问题。我希望使用imgaug库，但不幸的是我不断遇到错误。以下是我的代码。
#导入必要的库from torch import nnfrom torchvision import modelsimport imgaug as iaimport imgaug.augmenters as iaafrom torchvision import datasetsfrom torch.utils.data.dataloader import DataLoaderfrom torchvision import transformsfrom torch import optimimport numpy as npfrom PIL import Imageimport globfrom matplotlib import image#预处理图像#创建数据转换器seq = iaa.Sequential([iaa.Sometimes(0.5,iaa.GaussianBlur(sigma=(0,3.0))), iaa.Sometimes(0.5,iaa.LinearContrast((0.75,1.5))), iaa.AdditiveGaussianNoise(loc=0,scale=(0.0,0.05*255),per_channel=0.5), iaa.Sometimes(0.5,iaa.Affine( scale={"x": (0.8, 1.2), "y": (0.8, 1.2)}, translate_percent={"x": (-0.2, 0.2), "y": (-0.2, 0.2)}, rotate=(-25, 25), shear=(-8, 8)))],random_order=True) train_transformation = transforms.Compose([transforms.RandomResizedCrop(300), seq, transforms.ToTensor()])train_data = datasets.ImageFolder(root = 'train')train_loader = DataLoader(train_data,shuffle = True,batch_size = 32,num_workers = 0)train_iter = iter(train_loader)train_iter.next()----TypeError Traceback (most recent call last) in 20 train_loader = DataLoader(train_data,shuffle = True,batch_size = 32,num_workers = 0) 21 train_iter = iter(train_loader)---> 22 train_iter.next()TypeError(default_collate_err_msg_format.format(elem_type))TypeError: default_collate: batch must contain tensors, numpy arrays, numbers, dicts or lists; found 我知道imgaug转换器的输入必须是numpy数组，但我不知道如何将其整合到我的transform.compose中（如果可以的话）。当imgaug seq不在transform.compose中时，它可以正常工作。
谢谢你的帮助！
回答：
查看PyTorch中transforms的文档可以给我们一些提示如何操作：https://pytorch.org/docs/stable/torchvision/transforms.html#generic-transforms
我会尝试这样做：
train_transformation = transforms.Compose([transforms.RandomResizedCrop(300), transforms.Lambda(lambda x: seq(x)), transforms.ToTensor()])