Double-Z

@nbei On my PC, all passed: ```sh pre-commit run --all-files flake8...................................................................Passed seed isort known_third_party.............................................Passed isort....................................................................Passed yapf.....................................................................Passed Trim Trailing Whitespace.................................................Passed Check Yaml...............................................................Passed Fix End of Files.........................................................Passed Fix requirements.txt.....................................................Passed Fix double quoted...

Because Pandar64 lidar laser beams' vertical angle step are not even. Yout should try its vetical angle spreads as your proj_x generation. https://github.com/scaleapi/pandaset-devkit/issues/67#issuecomment-674403708

@Xiuyu-Li Any progress of adaptive matrix multiplication grouping yet?

Hi, @dachengxiaocheng I have the same problem with you, no matter how large the lr_mult I set the loss are same always. How do you fix this? Thank you!

same issue. PR approval.

Have you solve this problem?

I think the filters been pruned should restore previous value that before it been pruned, and keep other non-pruned filters their current value, then use `null_space = self.qr_find_null(W2d.cpu().detach().numpy())` to find...

Another question: what if all filters of a layer are pruned?(this could happen sometime)\ This will lead to the data forward through this layer all come out with zeros...