Zygmunt Łenyk

Results 6 comments of Zygmunt Łenyk

@SergeyMilyaev , I'm running into similar issue. When I'm trying to run your example I'm getting: TypeError: initialize() got an unexpected keyword argument 'max_loss_scale' I downloaded apex a few days...

@kentang-mit could you clarify if you're scaling LR with batch size? Or are you using just LR = 1e-4 with AdamW for batch size of 32 (8GPUs * 4) Thank...

It sounds like voxels that they are talking about are in fact pillars with 1 per bev grid, but I'm not 100% sure. Another interesting question is what is the...

Bigger close-up at the beginning of training: ![image](https://user-images.githubusercontent.com/4385916/157031106-aaf2efff-961d-4b52-85d1-0043c5a428eb.png)

I'm using virtualenv and was facing the same issue. What worked for me: 1. Go to pyvenv.cfg of your venv 2. Change to: include-system-site-packages = true 3. Deactivate and activate...