coordxyz

In my case, I solve the same issue by fixing the error labels of my own dataset.

> A keypoint’s location is modeled as a one-hot mask. In this way, you can easily train landmark estimation network with your framework. Instead of predicting K masks for K...

> hello @bhyzhao , need you help.... > when i cd /extensions/AE and run python build.py install i meet the bug: > cffi.VerificationError: CompileError: command 'gcc' failed with exit status...

> I want to know why use so small weights(1e-3), it is best ? I tried to adjust it to higher value but failed, e.g. 1e-2. It seems 1e-3 just...

@dong-x16 Could you please share your training details, such as training and validation loss, total iterations, input/output size, etc? Thanks a lot.

@SoraDevin It works for me. Thanks~ BTW，tensorflow 1.15 uses cuda10.0 just in case anyone is stuck in "Could not load dynamic library 'libcudart.so.10.0'; dlerror: libcudart.so.10.0: cannot open shared object file:...