leonlulu

> @levi0809 Are you using multiple GPUs? The pre-trained weights are saved using only one GPU! I think this is a PyTorch limitation that doesn't allow loading pre-trained weights into...

When I run the example "ski" image, I got exactly the same result as @guist . How should I modify to make the result right? Many Thanks

Thanks for the quick reply @ybai62868 I didn't change anything in 'test_pose.py' before I ran the test shell. So let me see... The padding value I use is 0 and...

So I could just use the same image mean and variance as MSCOCO. It converges faster but maybe training the network from scratch will get a better result. After all,...

The CNKI dataset was provided by the company we were working with. Actually the company is called "CNKI" so we just called this dataset CNKI dataset for convenience.

For annotating the bounding boxes in images, I found a very useful tool called "labelimg". Hope it helps. https://github.com/tzutalin/labelImg

I added the citation of the paper in README file. Sorry we cannot make the code open source.