This repository has been archived by the owner on Oct 31, 2023. It is now read-only.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
The files are located at: object_detection/detectron2.
Summary of the files modified/added:
object_detection/detectron2/models/backbones/config.py
add_convnext_config(cfg)
to be imported and called during config build process.object_detection/detectron2/models/backbones/convnext.py
BACKBONE.NAME
tobuild_convnext_fpn_backbone
in config file for using ConvNeXt as backbone.object_detection/detectron2/models/configs/Base-RCNN-FPN.yaml
object_detection/detectron2/models/configs/convnext_mask_rcnn_fpn_1x.yaml
Faster-RCNN
orMask-RCNN
.I have tested the backbone with standard detectron2 project for training along with Mask-RCNN. As the project already exists at the Detectron2 repository, I only added the required module files to the pull request.
Kindly accept the PR if the changes follow the guidelines and helps in any way. Thanks!.