alibaba / alibaba/easyrobust

About the information of BN layer.

Open
#16 3 comments 0 reactions 0 assignees View on GitHub
Dominant language
Jupyter Notebook
Stars
339
Forks
38
PR merge metrics
No merged PRs in 30d

Description

It seems that the method doesn't use the information of BN layer in the code of BATS. Maybe I miss something. In addition, I'm curious about the selection of hyperparameter, such as lam = 1.05 for ImageNet.

Contributor guide

No contributing guide indexed for this repository

Research direction

Start by locating the BATS implementation and its handling of the BN layer. Check whether BN information is used and trace how the ImageNet value of lam = 1.05 is selected. Done means documenting the BN behavior and the rationale or source for the hyperparameter, with any relevant references identified.

Written by the indexing model from the issue text.

Assessment

Tech stack
jupyter-notebook, pytorch
Domain
computer-vision, machine-learning
Issue type
Documentation
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.