Skip to content
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.

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

add new config sample and check scripts #2216

Merged
merged 43 commits into from
Mar 23, 2020
Merged

Conversation

xvjiarui
Copy link
Collaborator

@xvjiarui xvjiarui commented Mar 7, 2020

This PR introduces new config system wiht bases.
Check script will be deleted before merge.
To test configs in this PR, please refer use mmcv from here open-mmlab/mmcv#194

During refactor, the following principles are applied.

  • The base model (e.g. r50) of each method is composed of components.
  • The variations of base models are inherited from the closest base model.
  • For the inherited configs, only the updated key-value pairs are included.
  • _delete_ indicates the original dict will be deleted instead of updated, which is useful when two dicts have non-overlapped keys.

Notes:
faster_rcnn_r50_caffe_fpn_1x.py, guided_anchoring/ga_retinanet_r50_fpn_1x.py, guided_anchoring/ga_faster_r50_fpn_1x.py, retinanet_r50_caffe_fpn_1x.py, mask_rcnn_r50_caffe_fpn_1x.py, ms_rcnn/ms_rcnn_r50_fpn_1x.py, rpn_r50_caffe_fpn_1x.py, guided_anchoring/ga_rpn_r50_fpn_1x.py are not in the current configs. They are added for the convenience of inheritance.

@xvjiarui xvjiarui requested a review from hellock March 7, 2020 12:32
@xvjiarui
Copy link
Collaborator Author

Please refer to the updated PR first comment.

@xvjiarui xvjiarui changed the base branch from master to v2.0 March 21, 2020 10:29
@hellock hellock merged commit eeff0be into open-mmlab:v2.0 Mar 23, 2020
@xvjiarui xvjiarui deleted the config branch May 7, 2020 12:16
mike112223 pushed a commit to mike112223/mmdetection that referenced this pull request Aug 25, 2020
* add new config sample and check scripts

* context managere to prevent import

* refactor backbone, add caffe

* add fast rcnn

* all basci config done

* rm coco_proposal

* add scratch, wider_face, voc

* add reppoints

* delete device id, auto resume

* add libra_rcnn, ms_rcnn, nas_fpn

* add hrnet, fcos

* add free_anchor, gn, grid_rcnn, guided_anchoring, gcnet, ghm, gn+ws

* finished all, but some need refactor and unified logic

* fixed albu

* update ReseNet101

* reduce ResNet101, add norm_cfg, 4conv1fc

* refactor caffe backbone

* merge act_cfg, dcn from master

* rename 2fc head, add 4conv1fc head

* delete 4con1fc model

* rename components -> _base_

* flatten _base_

* refactor _base_ structure

* refactor config structure

* reduce _base/models

* rename all config

* add _coco inside configs

* fixed _coco in files

* fixed albu in test

* migrate to new sys

* fixed test

* fixed test

* rm cascade, fast_rcnn

* rm cascade, fast_rcnn from _base_

* fixed fcos_center

* rename from rule

* collopse third party model

* fixed test

* fixed some minor bug

* rename gn-neck_head -> gn-neck+head
chhluo added a commit to chhluo/mmdetection that referenced this pull request Aug 20, 2022
chhluo added a commit to chhluo/mmdetection that referenced this pull request Aug 22, 2022
ZwwWayne pushed a commit that referenced this pull request Aug 23, 2022
…8594)

* use mmengine's load_state_dict and load_checkpoint

* from mmengine import dump

* from mmengine import FileClient dump list_from_file

* remove redundant registry

* update

* update

* update

* replace _load_checkpoint with CheckpointLoad.load_checkpoint

* changes according to mmcv #2216

* changes due to mmengine #447

* changes due mmengine #447 and mmcv #2217

* changes due mmengine #447 and mmcv #2217

* update

* update

* update
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.

2 participants