Fred Fang

Hi，the first command is not correct since you used the coco config. You should use the smpl config for 3d inference. In the second one, it seems the pytorch meet...

Hi, thanks for your interest. In fact we are about to write the paper, but not yet 😂

The gluoncv code should work properly. We have worked for a long time on that PR. It's a bit different.

Hi, the paper is public at http://arxiv.org/abs/2211.03375 Thanks for your interest!

Hi, can you see if this help: https://discuss.pytorch.org/t/issue-with-multiprocessing-semaphore-tracking/22943/6 ?

It's pretty weird. Does enable --sp flag help?

you need to visualize the output to check if the tracking if correct.

It works on my side. Try using the absolute path to the image dir and list img name in the txt file

Oh, great! But it should work with xxxx.png aaaa.png See here: https://github.com/MVIG-SJTU/WSHP/blob/master/parsing_network/deeplab_resnet/image_reader.py#L88

I mean the .txt can also format xxxx.png aaaa.png