jihyongoh / demfi Goto Github PK

May I ask some questions about the test results?
Could you explain the meanings of the names:
Time, intp_testPSNR_prime, deblur_testPSNR_prime, intp_testPSNR, deblur_testPSNR.

Does this 'Time' represent the whole time for deblurring and interpolating 8 different images or for 1 image?
What is the difference between 'prime' and not prime?
Also, why are the results always followed by an (avg)? What is it?

For example:

I fail to download Adobe240 dataset from the provided dropbox links. Can you give Google Drive or Baidu Netdisk links or can you tell me how to make Adobe240 dataset from the original videos?

Thanks!

Hello, I noticed that the pretrained model weight link points to "https://www.dropbox.com/s/xj2ixvay0e5ldma/XVFInet_X4K1000FPS_exp1_latest.pt" rather than DeMFI-Net , would it be possible to correct the link?

The results I'm getting are not of the same quality as the examples shown. Are there any settings or parameters I can tweak to get results closer to the example clips shown?

https://drive.google.com/file/d/1zVtFCj7h2xa-f7cFMpaYtFr3U7N3Qz9y/view?usp=sharing

I need to change the type of the parameter multiple_MFI from type=list in the code to type=int.

Then I encountered the following error.

Traceback (most recent call last):
File "C:\Users\98mxr\Downloads\DeMFI\main.py", line 1198, in
main()
File "C:\Users\98mxr\Downloads\DeMFI\main.py", line 361, in main
test_custom(final_test_loader, model_net,args, device,
File "C:\Users\98mxr\Downloads\DeMFI\main.py", line 1137, in test_custom
patch_forward_DeFInet_itr(model_net, input_frames, None, t_value, num_update, patch,
File "C:\Users\98mxr\Downloads\DeMFI\utils.py", line 1403, in patch_forward_DeFInet_itr
Sharps_prime, Sharps_final, flow_predictions, occ0_predictions, two_blurry_inputs = model_net(input_frames[:, :, :, H_low_ind:H_high_ind, W_low_ind:W_high_ind],
File "C:\Users\98mxr\AppData\Local\Programs\Python\Python39\lib\site-packages\torch\nn\modules\module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "C:\Users\98mxr\Downloads\DeMFI\DeMFInet.py", line 78, in forward
Agg1 = self.Refine_Module(Agg1) + torch.cat(
File "C:\Users\98mxr\AppData\Local\Programs\Python\Python39\lib\site-packages\torch\nn\modules\module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "C:\Users\98mxr\Downloads\DeMFI\DeMFInet.py", line 598, in forward
out = torch.cat((out, enc1), dim=1)
RuntimeError: Sizes of tensors must match except in dimension 1. Expected size 224 but got size 225 for tensor number 1 in the list.

I am afraid I cannot solve this problem and submit it to the code owner for processing.

English is not my native language, please accept my apology if there is anything wrong with the above statement.

Thanks for sharing this fantastic work.
Would you consider making a google Colab notebook for the less technically inclined like myself to try this?

I'm getting this error when I attempt to run main.py.
"File "C:\Users\importon\Documents\DeMFI-main\utils.py", line 533, in init
raise (RuntimeError("Found 0 files in subfolders of: " + self.args.custom_path + "\n"))
RuntimeError: Found 0 files in subfolders of: './custom_path'"

I've put my blurry images in the "scene1" folder. Do I need to put anything in the "sceneN" folder?

Thank you for your contribution. Can you upload the source code containing the "Class Activation Map"

Where did you publish it or will you publish it?