Jingyun Liang

It depends on your image size. You can try it yourself.

`--tile 8 160 180` means frame=8, height=160 and width=180.

It crops the video into 8x160x180 clips for testing due to memory limit.

If you don't want to partition the video along the temporal dimension, you can use `--tile 0 160 90`. As for the runtimeerror, please refer to https://github.com/JingyunLiang/VRT/issues/24

Partition means partition the sequence into short clips. 0 means no partion.

It's a good idea. Our way is like using 1x1 patches. Using larger patch may reduce the computation cost significantly. However, I haven't tried it yet, because I personally believe...

According to my understanding, just as the authors said in Section 1, `efficient inference can be obtained as we can use master-net to perform recognition in the testing stage`, I...

I can run `demp.py` successfully. But when I try to debug the code, the same error comes. Slightly different with you: ``` Connected to pydev debugger (build 172.3968.37) Traceback (most...

Problem alleviated! You can refer to [https://github.com/pytorch/pytorch/issues/2575](https://github.com/pytorch/pytorch/issues/2575) for solutions. Good luck! @pranerd

You could comment these two lines and use `term_width=80`.