Closed ShichenLiu closed 3 years ago
@ShichenLiu were you able to reproduce their results?
Hi @alekseynp No I am not. Also I tried their kitti15 code, and the val error was far from their performance on the leaderboard (D1-all 2.3% vs 1.6%). I am not sure if there is any additional training steps or arguments.
Hi @ShichenLiu, could you please tell me what all changes you made to the original code to get 2.3%? I am getting 6.47% validation error with the default parameters.
Hi,
I am wondering how to reproduce the sceneflow results. I followed the author's scripts that train the architecture searched for 20 epochs with a fixed learning rate of 0.001. The results were far from the reported numbers in the paper (1.01EPE against 0.78EPE). So I would like to know any learning rate scheduling that could reproduce the sceneflow results (also any checkpoint available? It seems the sceneflow checkpoint is missing)
Thanks!