TIBHannover / MSVA

Deep learning model for supervised video summarization called Multi Source Visual Attention (MSVA)
MIT License
41 stars 18 forks source link

How did you extract the motion features for the datasets? #11

Open StevRamos opened 3 years ago

StevRamos commented 3 years ago

Hi, I tried to replicate the render part of your project, specifically the motion feature extraction. I couldn't do it because the code version "https://github.com/deepmind/kinetics-i3d/tree/master/data/checkpoints/rgb_imagenet" is out of date. Thanks in advance!

shineYuSong commented 2 years ago

have You solved it ? i have download the checkpoint successfully, while the model seems not fit the checkpoint with the error "Key Conv3d_1a_7x7/batch_norm/beta not found in checkpoint"

Junaid112 commented 2 years ago

see the issue #13 , hope that will help. Kind of same issue