pytorch-coviar

pytorch-coviar copied to clipboard

pytorch version

2

which version of Pytorch is used in this project?

tecmry

multiple GPUS

2

thanks for providing your code .when training,gpu id was set to 0 and 1.but it was occupied in my server.so i change ids to 1and 2 ,one error occured :all...

Rookielike

the code which make the avi to mp4 have a little iusse

3

``` ./reencode.sh hmdb51/videos/ hmdb51/mpeg4_videos/ ``` should change into ``` ./reencode.sh hmdb51/videos hmdb51/mpeg4_videos ```

SkySailing

How to visualize res information?

1

Hi, did you do any post processing to visualize res information? I think I got too many (128,128,128) which is grey and they look different with the examples in the...

luodezhao

Could not allocate video parser context

5

Hi！ I am facing this error when training,Could not allocate video parser context , Decoding video failed. Kindly please guide me. 

salt-fly

Can someone share the model's weights trained on UCF-101? PLEASE.

1

wolfeast

How to generate the train/test list for Kinetics dataset?

1

Thank you for your attention. My question is how to generate the train/test list for Kinetics dataset? Is there any file I can use to do this? Looking forward to...

ZealACMer

Optical flow

9

Hi, thanks for your suggestions, I already can reproduce your code, and I have a problem with the fusion of optical flow. I guess that your fusion to optical flow...

JGyoung33

To combine the results and calculate the final accuracy.

3

When I run combine.py, I am facing following error: Traceback (most recent call last): File "combine.py", line 48, in main() File "combine.py", line 24, in main with np.load(args.iframe) as iframe:...

manza-ari

Why we need --disable-yasm option to configure FFmpeg ?

1

Dear developer, I fail to see why we need to add the `--disable-yasm` option to configure FFmpeg. It will lose a lot of performance, won't it?

grasshopyx