Using OpenPose for getting skeleton data from ntu rgb videos

[jug971990]

Initially , I edited your read_xyz function to get 2D coordinates instead of 3D coordinates from the raw skeleton data downloaded from ntu dataset website. I used two classes "A44" and "A26". I changed the num_class to 2 and input_channels to 2. I trained the model and the evaluation accuracy was 99.5%.

Now for the same two classes, I extracted 2D skeleton data from OpenPose and preprocessed the data. When I ran the code for training the model , I see that the training and evaluation accuracy are around 45 - 50 %.

Please let me know why this is happening?

[huguyuehuhu]

Obtaining ~50% for a 2-class task means that 1) the model learned nothing but outputted a random guess, 2) OR More Likely, there is something wrong in your dataset (e.g, data and label are misaligned). You can change the HCN model into a simple 3 layers MLP to examine whether your data processing is correct. Please also refer to #12.