Megvii-BaseDetection / Megvii-BaseDetection/YOLOX

Changing loss function

Open
#1,080 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
10.6k
Forks
2.5k
PR merge metrics
No merged PRs in 30d

Description

I would like to change the BCEWithLogitsLoss to CrossEntropyLoss, as I am working on a dataset with single-labels.
However, I have been unable to do so.

Would I need to change the format a lot for the classification part, or is this easy to implement?

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

No file or test is named. Start by locating the classification loss setup and comparing the expected targets for BCEWithLogitsLoss and CrossEntropyLoss; done means single-label datasets can use the requested loss without breaking the classification path, with coverage for the supported target format.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.