search

supersupercong / UHDformer

[AAAI-24] Correlation Matching Transformation Transformers for UHD Image Restoration
Other
40 stars 1 forks source link

question about code #6

Open xiaozibuqi opened 1 month ago

xiaozibuqi commented 1 month ago

An error occurs when I run the code: Traceback (most recent call last): File "basicsr/train.py", line 266, in train_pipeline(root_path) File "basicsr/train.py", line 211, in train_pipeline model.optimize_parameters(current_iter) File "/opt/data/private/wyh/UHDformer-main/basicsr/models/femasr_model.py", line 148, in optimize_parameters l_g_total.mean().backward() File "/root/anaconda3/envs/wdgan/lib/python3.6/site-packages/torch/_tensor.py", line 307, in backward torch.autograd.backward(self, gradient, retain_graph, create_graph, inputs=inputs) File "/root/anaconda3/envs/wdgan/lib/python3.6/site-packages/torch/autograd/init.py", line 156, in backward allow_unreachable=True, accumulate_grad=True) # allow_unreachable flag RuntimeError: element 0 of tensors does not require grad and does not have a grad_fn How do I fix it?

supersupercong commented 1 month ago

Please check your environment since there is not any issues in our environment.