pytorch / pytorch/vision

Add support for VOC on detection references

Open
#6,037 3 comments 2 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

enhancement module: reference scripts topic: object detection
Dominant language
Python
Stars
17.9k
Forks
7.3k
Avg merge
1d 15h
Merged PRs (30d)
13

Description

The segmentation references already support VOC and COCO

https://github.com/pytorch/vision/blob/08c8f0e0b68195a4a5a21cdd3f86106f59c2e854/references/segmentation/train.py#L20-L24

Unfortunately, the detection references only support COCO

https://github.com/pytorch/vision/blob/a1232c212d7cf84806189910ba83bc36bcea916c/references/detection/train.py#L37

There was a first push for this in #1216 by @lpuglia. We can probably salvage some parts from the PR.

We are currently reworking the datasets and transforms, and in turn the reference scripts will change quite a bit. Thus, we should only go for this after they are stable-ish again.

cc @datumbox @YosuaMichael

Contributor guide

Open the contributing guide

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

Start by comparing references/detection/train.py with references/segmentation/train.py, especially the linked dataset-support sections, and review the salvageable parts of PR #1216. Wait for the datasets and transforms rework to stabilize, then verify that the detection reference supports VOC as well as COCO without breaking the existing reference workflow.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
computer-vision, machine-learning
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
30/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.