Simplify mean and std computation
All threads resolved!
All threads resolved!
Closes #100 (closed)
Merge request reports
Activity
changed milestone to %DAN-P4: Improve data loading and preprocessing
added P2 label
I didn't use the same computation as in Doc-UFCN (https://gitlab.com/teklia/dla/doc-ufcn/-/blob/main/doc_ufcn/train/normalization_params.py#L20) since it's not the same average (micro vs macro). I kept the original average but simplified a bit the code
requested review from @starride
requested review from @schneider-y and removed review request for @starride
- Resolved by Yoann Schneider
Please register or sign in to reply