search

ChenyangLEI / All-In-One-Deflicker

[CVPR2023] Blind Video Deflickering by Neural Filtering with a Flawed Atlas
686 stars 41 forks source link

bug,AssertionError: the number of style frames is different from the number of content frames #15

Closed yifenglv46 closed 1 year ago

yifenglv46 commented 1 year ago

something wrong

199 17.87025058686584 100% 10001/10001 [19:51<00:00, 8.39it/s] Namespace(ckpt_filter='./pretrained_weights/neural_filter.pth', ckpt_local='./pretrained_weights/local_refinement_net.pth', fps=10, video_name='2023-05-19_20-10-50', gpu=0) Load ./pretrained_weights/local_refinement_net.pth Traceback (most recent call last): File "/content/All-In-One-Deflicker/src/neural_filter_and_refinement.py", line 73, in assert len(style_names) == len(content_names), "the number of style frames is different from the number of content frames" AssertionError: the number of style frames is different from the number of content frames

yifenglv46 commented 1 year ago

The input is 203 pictures but it exits after processing to 199

xrenaa commented 1 year ago

Hi, please refer to "Suggestions for Choosing the Hyperparameters":

Maximum number of frames: We set the maximum_number_of_frames to 200. The performance for longer videos is not evaluated. It is recommended to split long videos into several shorter sequences.