pytorch-coviar
pytorch-coviar copied to clipboard
chaoyuaw
Compressed Video Action Recognition
I have a problem with "make clean" command, I'm getting those errors:  Using python 3.6.3
Data_loader
Hi I am facing this error while doing installation steps in data_loader folder  Kindly please guide me. How to Modify setup.py to use your FFmpeg path (${FFMPEG_INSTALL_PATH})?
how to execute ./data_loader/install.sh in Windows enviroment? and how to modify these paths: ./ffmpeg/include/, -L./ffmpeg/lib/, in Windows enviroment? or others need to be modified?
Rencently, I have a course about video action recognition and the deadline is coming, this coviar method is selected as a comparing method, but the training time is too long...
Hello,thanks for your awesome job! In geting_started,you said,"Currently we only support mpeg4 raw videos. Other codecs, e.g. H.264, coming soon. The mpeg4 raw videos can be obtained using FFmpeg" When...
Thanks for your awsome work. However, we have some other questions. If the gop size of compressed video is not 12, how can we extract the motion vector and residual...
https://github.com/chaoyuaw/pytorch-coviar/blob/4f0857a37ac9e283fcd9ebede950f33057d07eba/dataset.py#L151-L158 When creating val_dataloader, is_train is set as False. But color jittering is still enabled. This may end up with inconsistent test results.
Error: loading video data/hmdb51/mpeg4_videos/turn/SoundAndTheStory_turn_u_nm_np1_ba_med_1.mp4 failed. Could not allocate video parser context Decoding video failed.
I am using Python 3.7 and I run into a syntax error from the lines which include `target = target.cuda(async=True)`. Based on [this StackOverflow answer](https://stackoverflow.com/questions/53201534/calling-cuda-with-async-results-in-syntaxerror) I am guessing that `async=True`...
Hi, I met with several problems in the training process. ERROR: Unexpected segmentation fault encountered in worker. ERROR: Unexpected segmentation fault encountered in worker. [jpegls @ 0x562d3c3db340] Found EOI before...
