Skip to content

Add balanced hard-negative batch sampling for detection training.#1393

Closed
bw4sz wants to merge 1 commit into
weecology:mainfrom
bw4sz:feature/balanced-detection-batch-sampling
Closed

Add balanced hard-negative batch sampling for detection training.#1393
bw4sz wants to merge 1 commit into
weecology:mainfrom
bw4sz:feature/balanced-detection-batch-sampling

Conversation

@bw4sz
Copy link
Copy Markdown
Collaborator

@bw4sz bw4sz commented May 22, 2026

Optional train.positive_batch_fraction fixes annotated vs empty images per batch and subsamples large negative pools.

Description

Related Issue(s)

AI-Assisted Development

  • I used AI tools (e.g., GitHub Copilot, ChatGPT, etc.) in developing this PR
  • I understand all the code I'm submitting
  • I have reviewed and validated all AI-generated code

AI tools used (if applicable):

Optional train.positive_batch_fraction fixes annotated vs empty images per batch and subsamples large negative pools.

Co-authored-by: Cursor <cursoragent@cursor.com>
@bw4sz bw4sz closed this May 22, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant