search

karolzak / conv3d-video-action-recognition

My experimentation around action recognition in videos. Contains Keras implementation for C3D network based on original paper "Learning Spatiotemporal Features with 3D Convolutional Networks", Tran et al. and it includes video processing pipelines coded using mPyPl package. Model is being benchmarked on popular UCF101 dataset and achieves results similar to those reported by authors
MIT License
53 stars 10 forks source link

'utf-8' codec can't decode byte 0x8c in position 1708: invalid start byte #3

Open SamueledelVescovo opened 3 years ago

SamueledelVescovo commented 3 years ago

Hi Karol, I am trying to use this library. When i call "videos_to_frames_pipe()" function i got this error : "'utf-8' codec can't decode byte 0x8c in position 1708: invalid start byte" on my own dataset (which includes some videos of Ucf-101 datasets).

I suppose there is some error in some videos, but I can't figure out which one. I thank you for your availability.

Bests Samuele

karolzak commented 3 years ago

Hi @SamueledelVescovo Yeah, I would guess there's something wrong with one of the files. You can try modifying that videos_to_frames_pipe() function to add something like below to the begining of the pipe:

...
| mp.iter('filename', lambda fn: print('Processing: ', fn))
...

That way you would at least print the filename before it throws exception maybe.

SamueledelVescovo commented 3 years ago

Hi Karol, thanks for your advice. I wish you good work.

Bests Samuele