qqsh0214

@AVCarreiro Maybe. I was in Linux.

I just change 'joints' in dataset.mat as follow: `joints = {[ ... 0, 175, 261; ... 1, 173, 178; ... 2, 144, 122; ... 3, 193, 124; ... ], [...

The code has updated. You can have a try once.

@Marcovaldong Thank you. @dragonfly90 I also agree.

@dragonfly90 I find that my previous error "simple bind error" is caused by mxnet with cpu version. I didn't realize it before. So I just start training from beginning. I...

@dragonfly90 OK, I will try batch_size=10. I refer to section 5 in https://arxiv.org/abs/1703.06870. I am trying implement mask rcnn for pose estimation based on faster rcnn in mxnet https://github.com/precedenceguo/mx-rcnn

@dragonfly90 I have worked on mask. I will try ROIAlign based on ROIPooling in mxnet with C++ source code. But I am a little confused about how to change codes...

@dragonfly90 I don't get result because I get the error： `ValueError: Too many slices. Some splits are empty.` and the training is terminated at around 4500 iterators. We have GPU...

@dragonfly90 It is trained for a day and terminate in the morning today. I don't know which image causes this error. I trained the training dataset and it is 210K....

@dragonfly90 I have not fixed the bug but I think it may be multi-gpu training and one of which don't work. I'm sorry that I go back home for the...