There is no "demo.py"

[MandyDongrs]

I wonder how different stages of results are ensembled in this method. This part of the code is not given, which should be very important according to the paper. Even in the evaluation and test stage, the loss is an average of loss in different stages, but not the loss of a final estimated result. I don't think this is reasonable.

[stupidZZ]

Our code has already include the ensemble results. Please refer to #19 .

[MandyDongrs]

Thank you. Sorry for my carelessness. I am also looking forward to your code for the visualization of the final results.

[abhigoku10]

@MandyDongrs did u find the code for visualization ?