cwlinghk

Results 10 comments of cwlinghk

I met the same error also with RTX 3070

https://github.com/thuyngch/Human-Segmentation-PyTorch/issues/28

> We are faced with the same problem. Can you help us please ? I found that the original implementation loaded the image with PIL and use torch.totensor. As PIL...

any ways to do this? thanks

access denied when getting lihkg api v2

Is anyway to increase the speed on CPU inference? mobilenet v2 ssd in Tensorflow is also about 200ms What are the bottlenecks of speed for pytorch version? Thanks

Where can I find the pretrained mobilenet models? Thank you very much.