Skip to content

feat: support multi-scale feature extraction. #643

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Merged
merged 32 commits into from
Jun 14, 2023
Merged

feat: support multi-scale feature extraction. #643

merged 32 commits into from
Jun 14, 2023

Conversation

DexterJZ
Copy link
Contributor

@DexterJZ DexterJZ commented May 5, 2023 •
edited
Loading

Support multi-scale feature extraction. The current design only supports ResNet, MobileNetV3, ConvNeXt, ResNeST, EfficientNet, RepVGG, HRNet, and ReXNet.

Thank you for your contribution to the MindCV repo.
Before submitting this PR, please make sure:

Motivation

Outputting multi-scale features is required by many downstream tasks, such as detection, OCR, and segmentation.

Test Plan

Test by running

pytest tests/modules/test_feature_extraction.py

Related Issues and PRs

Issue#639, PR#605

@DexterJZ DexterJZ closed this May 5, 2023
@DexterJZ DexterJZ deleted the extract_feature branch May 5, 2023 08:44
@DexterJZ DexterJZ restored the extract_feature branch May 5, 2023 08:49
@DexterJZ DexterJZ reopened this May 5, 2023
@DexterJZ DexterJZ changed the title Add multi-scale feature extraction for MobileNetV3, ConvNeXt, ResNeST, EfficientNet, RepVGG, and ReXNet Support multi-scale feature extraction. A more versatile design is in development. May 12, 2023
@DexterJZ DexterJZ mentioned this pull request May 12, 2023
Closed
4 tasks
@geniuspatrick geniuspatrick changed the title Support multi-scale feature extraction. A more versatile design is in development. [WIP] Support multi-scale feature extraction. A more versatile design is in development. May 17, 2023
@DexterJZ DexterJZ changed the title [WIP] Support multi-scale feature extraction. A more versatile design is in development. [WIP] Support multi-scale feature extraction. Jun 1, 2023
geniuspatrick
geniuspatrick suggested changes Jun 12, 2023
View reviewed changes
geniuspatrick
geniuspatrick approved these changes Jun 14, 2023
View reviewed changes
Copy link
Contributor

@geniuspatrick geniuspatrick left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

lgtm

@geniuspatrick geniuspatrick changed the title [WIP] Support multi-scale feature extraction. feat: support multi-scale feature extraction. Jun 14, 2023
@geniuspatrick geniuspatrick merged commit fc1f000 into mindspore-lab:main Jun 14, 2023
@geniuspatrick geniuspatrick mentioned this pull request Jun 16, 2023
Closed
@DexterJZ DexterJZ self-assigned this Jul 21, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@SamitHuang SamitHuang SamitHuang approved these changes

+1 more reviewer

@geniuspatrick geniuspatrick geniuspatrick approved these changes

Reviewers whose approvals may not affect merge requirements
Assignees

@DexterJZ DexterJZ

Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@DexterJZ @SamitHuang @geniuspatrick