kohillyang
kohillyang
I suggest several operators for reference: 1. CTC Loss, this OP is supported by mxnet, but before PyTorch 1.0, users must compile by themselves. 2. Deformable Convolution (and also DCNV2),...
I tried another network named deeplab, which converged quickly. I think, if you use the original openpose network, you must begin from a pretrained model, or you may found it...
Well, I just replace the network to deeplab network, all code can be found in folder deeplab, their is also a file named readme.md which describe the training process
It has been normalized by a coefficient, or you can say the learning rate is very small.
In fact, in my test, the result is not so good. MASK must be used, because it can make the model converge more easily. augment data can import accuracy. learning...
As I said, the mask is very import, but in this demo, mask was be replaced by all 1 if there is no available MASK information. The MASK I used...
[click me to see the MASK generator](https://github.com/dragonfly90/mxnet_Realtime_Multi-Person_Pose_Estimation/blob/a0e7b52a8412f2f98fca9b1eff5d8108df3b497c/generateLabelCPM.py#L356)@dragonfly90
@dragonfly90 using OKS(Object Keypoint Similarit) as score method, I got a score of about 0.145, but there are some method which can achieve over 0.51.
I used your code, but I only used your model file, and wrote my own mpi parser code,for the result was not so good, I didn't wrote any augmentation code...
The code is here: