王小奇

loss.backward() File "E:\conda\lib\site-packages\torch\_tensor.py", line 307, in backward torch.autograd.backward(self, gradient, retain_graph, create_graph, inputs=inputs) File "E:\conda\lib\site-packages\torch\autograd\__init__.py", line 154, in backward Variable._execution_engine.run_backward( RuntimeError: Function NumpyOpWrapperBackward returned an invalid gradient at index 0 -...

Hi, does this support GPU versions with more than 7.5 computing capacity, such as NVIDIA RTX 3090 or Tesla A100?

1

Hi, does this support GPU versions with more than 7.5 computing capacity, such as NVIDIA RTX 3090 or Tesla A100?

Hi, as seen in the train.py and ckdn.py files, the test phase also used reference images that were inconsistent with the original paper description. Or did I miss the right?

About alignment metric

2

I would like to confirm whether the paper evaluates the alignment metric by calculating the score for all samples, or 80% for training and 20% for testing.

I encountered an error "NotImplementedError: Check Alignment" when submitting my test results for PIPAL-NTIRE22 challenge. Could you please help look into what might be causing this issue?

Clarification on the division of 20k test images in "generic_test.jpgl"

1

How are the 20k test images in "generic_test.jpgl" divided? I'd like to follow the same method for 5-fold cross-validation. Different splits seem to affect model performance, and I want to...