Liang Dong

For unit2, run (do-demo2 'human) Warning: Cannot create a visible window. Using a virtual window instead?

New feature: post video

14

Currently, posting video is not supported by python sdk, but actually you can do it by python. Is it a good idea to add the function in sdks?

Reproduce evaluation issues

15

Hard to reproduce the result mentioned in Cao's original paper, they talk about it in the original implementation. https://github.com/ZheC/Realtime_Multi-Person_Pose_Estimation/issues/35 https://github.com/ZheC/Realtime_Multi-Person_Pose_Estimation/issues/68 https://github.com/ZheC/Realtime_Multi-Person_Pose_Estimation/issues/72 https://github.com/ZheC/Realtime_Multi-Person_Pose_Estimation/issues/74 The matlab version should be 0.577 Python I...

@kohillyang  

Does the demo has shape only preprocessing layer in inference?

1

As mentioned in section 4.2.1 of the supplementary material: The preprocessing layer. An even simpler option is to use a preprocessing stage that discards the appearance consistency information. Such preprocessing...

spread loss is not decreasing

3

I tried python3 train.py "mnist" with master version and the default parameters. But the spread loss is not decreasing, it jumps from 0.36 to 0.65 in 1200 iterations. However, the...

mask rcnn

1

@qqsh0214 It seems to be a good one to work on. https://github.com/TuSimple/mx-maskrcnn

Training loss

19

@qqsh0214 How is the training? I realize that it may better to set the batch_size larger.