open-mmlab / open-mmlab/mmengine

Classification target semantic instances need these trainings and configs

Open
#528 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
1.5k
Forks
464
PR merge metrics
No merged PRs in 30d

Description

Describe the feature

Motivation

It integrates image classification, object detection, semantic segmentation and instance segmentation in the visual field

Classification target semantic instances
need these trainings and configs

I want to do all model training through mmengine

It is recommended to add the configs folder in mmengine

It contains the classification target semantic instances folder

Respective model scripts

Related resources
https://github.com/PaddlePaddle/PaddleX
https://github.com/PaddlePaddle/PaddleX/tree/develop/tutorials/train

Additional context
Add any other context or screenshots about the feature request here.
If you would like to implement the feature and create a PR, please leave a comment here and that would be much appreciated.

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 reviewing the proposed configs folder in mmengine and the related PaddleX tutorials/train resources. Identify the required training configurations and model scripts for classification, object detection, semantic segmentation, and instance segmentation. Done means these visual tasks can be trained through mmengine with the requested configs.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
computer-vision, 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.