数据读取

[liu0619]

/home/lyl/MixDehazeNet-main/MixDehazeNet/data/outdoor/train/hazy/68553.jpg loss = train(train_loader, network, criterion, optimizer, scaler) File "/home/lyl/MixDehazeNet-main/MixDehazeNet/train.py", line 41, in train for batch in train_loader: File "/home/fang/anaconda3/envs/lyl/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 517, in next data = self._next_data() File "/home/fang/anaconda3/envs/lyl/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 1179, in _next_data return self._process_data(data) File "/home/fang/anaconda3/envs/lyl/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 1225, in _process_data data.reraise() File "/home/fang/anaconda3/envs/lyl/lib/python3.6/site-packages/torch/_utils.py", line 429, in reraise raise self.exc_type(msg) TypeError: Caught TypeError in DataLoader worker process 1. Original Traceback (most recent call last): File "/home/fang/anaconda3/envs/lyl/lib/python3.6/site-packages/torch/utils/data/_utils/worker.py", line 202, in _worker_loop data = fetcher.fetch(index) File "/home/fang/anaconda3/envs/lyl/lib/python3.6/site-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch data = [self.dataset[idx] for idx in possibly_batched_index] File "/home/fang/anaconda3/envs/lyl/lib/python3.6/site-packages/torch/utils/data/_utils/fetch.py", line 44, in data = [self.dataset[idx] for idx in possibly_batched_index] File "/home/lyl/MixDehazeNet-main/MixDehazeNet/datasets/loader.py", line 78, in getitem source_img = read_img(os.path.join(self.root_dir, 'hazy', img_name)) * 2 - 1 File "/home/lyl/MixDehazeNet-main/MixDehazeNet/datasets/common.py", line 50, in read_img return img[:, :, ::-1].astype('float32') / 255.0 TypeError: 'NoneType' object is not subscriptable 您好，这行一直报错，但是已经检查过数据路径没有问题，这是什么原因呢？

[AmeryXiong]

我最近两天会检查代码，之前一直比较忙。

[AlvinMLee]

您好，解决了吗

[AmeryXiong]

你们好，这个错误已经知道原因了，是因为我的代码主要参考DehazeFormer，DehazeFormer数据集中图片名称是经过修改的，你们可以去DehazeFormer下载数据集，这样就不会运行出错。

[AmeryXiong]

具体可以参考刚才更新的readme.