pytorch-coviar
pytorch-coviar copied to clipboard
chaoyuaw
Compressed Video Action Recognition
I do not know why I fail to get residual from mp4: ``` (base) jingtun@winnie:~/mvff-sideversions$ sudo python3 VID_MV_Extractor.py ffmpeg version N-90418-g74c6a6d Copyright (c) 2000-2018 the FFmpeg developers built with gcc...
./install.sh
Hi Sir, Kindly check this error? how can I resolve this? 
Hello @chaoyuaw . I have successfully installed the module. But while importing coviar module, I am getting this error. Can you please tell me if there's something I am missing?...
Hey, I just copied the options and settings when I trained coviar on UCF101-split1, but I only got 57% acc (validation) when training. Is there something wrong? Any help? Thanks.
I had issues during the build procedure. The linker could not find some symbols. So, it's better to use pkgconfig to let the pkgconfig files decide which additional libraries to...
After I converted the hmdb51 and ucf101 data sets according to the "reencode.sh", some mp4 videos could not be recognized during training, but some mp4 videos success. And the unrecognizable...
Hi, I followed the instructions till ./install.sh in dataloader. But after that I am confused where should the `from coviar import load` run? When I run it from dataloader file,...
While doing the step ./install.h in the data loader, I get the following set of errors: coviar_data_loader.c:431:9: error: void function 'count_frames' should not return a value [-Wreturn-type] return -1; ^...
I am having some issues with GPU-RAM issues and hence needing to reduce batch size during testing. Is there a way I can do so? Thanks
