预训练模型放置位置

[cyc-aaa]

作者您好！我想问一下这个预训练模型应该放在哪个文件夹下呢？还有就是我想用我自己的数据集去训练出现了这个问题，您知道有方法解决嘛？问题如下Traceback (most recent call last):
File "train.py", line 319, in
main()
File "train.py", line 231, in main
for _, train_data in enumerate(train_loader):
File "/home/ubuntu/anaconda3/envs/irsde/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 630, in next
data = self._next_data()
File "/home/ubuntu/anaconda3/envs/irsde/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 673, in _next_data
data = self._dataset_fetcher.fetch(index) # may raise StopIteration
File "/home/ubuntu/anaconda3/envs/irsde/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 55, in fetch
return self.collate_fn(data)
File "/home/ubuntu/anaconda3/envs/irsde/lib/python3.8/site-packages/torch/utils/data/_utils/collate.py", line 317, in default_collate
return collate(batch, collate_fn_map=default_collate_fn_map)
File "/home/ubuntu/anaconda3/envs/irsde/lib/python3.8/site-packages/torch/utils/data/_utils/collate.py", line 155, in collate
clone.update({key: collate([d[key] for d in batch], collate_fn_map=collate_fn_map) for key in elem})
File "/home/ubuntu/anaconda3/envs/irsde/lib/python3.8/site-packages/torch/utils/data/_utils/collate.py", line 155, in
clone.update({key: collate([d[key] for d in batch], collate_fn_map=collate_fn_map) for key in elem})
File "/home/ubuntu/anaconda3/envs/irsde/lib/python3.8/site-packages/torch/utils/data/_utils/collate.py", line 142, in collate
return collate_fn_map[elem_type](batch, collate_fn_map=collate_fn_map)
File "/home/ubuntu/anaconda3/envs/irsde/lib/python3.8/site-packages/torch/utils/data/_utils/collate.py", line 214, in collate_tensor_fn
return torch.stack(batch, 0, out=out)
RuntimeError: stack expects each tensor to be equal size, but got [3, 126, 128] at entry 0 and [3, 128, 128] at entry 1

[Algolzw]

我通常是放在task目录下：如codes/config/deraining/pretrained_models/xxx.pth。看了下你的error应该是输入图像有小于128下28的，你可以试试使用更小的patch size。

[cyc-aaa]

尊敬的作者，还有个问题想问您一下 ，这个patch_size在哪个文件内是DIT_arch.py这个文件嘛，然后这个inpainting是相当于All-in-one的效果吗

[Algolzw]

patch_size应该是option里面设置哈。