search

ChenyangLEI / All-In-One-Deflicker

[CVPR2023] Blind Video Deflickering by Neural Filtering with a Flawed Atlas
700 stars 43 forks source link

AssertionError: the number of style frames is different from the number of content frames #32

Open mycomedico opened 7 months ago

mycomedico commented 7 months ago

I set this up and ran on google colab. The example script executed perfectly, however when I tried it on my own longer video there was the following error:

Namespace(ckpt_filter='./pretrained_weights/neural_filter.pth', ckpt_local='./pretrained_weights/local_refinement_net.pth', fps=10, video_name='neathaz_color001', 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 <module> 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

gvonkreisler commented 5 months ago

Simple disable the if in code