Shubhendu-Jena

Nope. Still stuck where I was, unfortunately.

I see. Thanks for letting me know. I get 0.17m on KITTI with removed grounds. However, according to the paper, EPE is 0.211 with ground points and 0.122 without ground...

Same as above

Hi, Thanks for the quick response. Actually, it doesn't go to that line as args.eval_in_train evaluates to True in https://github.com/alievk/npbg/blob/355294b628c79b7d3b98ebe4ecd1e03c78adb8cb/train.py#L241 This is because in train_example.yaml, we have the following: https://github.com/alievk/npbg/blob/355294b628c79b7d3b98ebe4ecd1e03c78adb8cb/configs/train_example.yaml#L6

Just to clarify, the numbers reported in the paper are with train mode, right? And have you observed any difference in the evaluation results with train mode vs eval mode?

Thanks for the quick response and yes, it'd help me a great deal if you could check and let me know. Thanks again!