Skip to content
Snippets Groups Projects
Unverified Commit bb6457d4 authored by Cao Yuhang's avatar Cao Yuhang Committed by GitHub
Browse files

Bump to v2.4.0 (#3663)


* Bump to v2.4.0

* update change log and benchmark

* reformat

* fix typo

* resolve comments

* Update requirement in doc

Co-authored-by: default avatarZwwWayne <wayne.zw@outlook.com>
parent ae3b3c3f
No related branches found
No related tags found
No related merge requests found
......@@ -30,7 +30,8 @@ basic_arch_root = [
'cascade_rcnn', 'double_heads', 'fcos', 'foveabox', 'free_anchor',
'grid_rcnn', 'guided_anchoring', 'htc', 'libra_rcnn', 'atss', 'mask_rcnn',
'ms_rcnn', 'nas_fpn', 'reppoints', 'retinanet', 'ssd', 'gn', 'ghm', 'fsaf',
'point_rend', 'nas_fcos', 'pisa', 'dynamic_rcnn'
'point_rend', 'nas_fcos', 'pisa', 'dynamic_rcnn', 'gfl', 'sabl', 'paa',
'yolo'
]
datasets_root = ['wider_face', 'pascal_voc', 'cityscapes', 'mask_rcnn']
......@@ -90,7 +91,11 @@ benchmark_pool = [
'configs/pascal_voc/ssd300_voc0712.py',
'configs/nas_fpn/retinanet_r50_nasfpn_crop640_50e_coco.py',
'configs/mask_rcnn/mask_rcnn_r50_caffe_fpn_mstrain-poly_1x_coco.py',
'configs/gn+ws/mask_rcnn_r50_fpn_gn_ws-all_2x_coco.py'
'configs/gn+ws/mask_rcnn_r50_fpn_gn_ws-all_2x_coco.py',
'configs/gfl/gfl_r50_fpn_1x_coco.py',
'configs/paa/paa_r50_fpn_1x_coco.py',
'configs/sabl/sabl_retinanet_r50_fpn_1x_coco.py',
'configs/yolo/yolov3_d53_320_273e_coco.py'
]
......
......@@ -42,7 +42,7 @@ This project is released under the [Apache 2.0 license](LICENSE).
## Changelog
v2.3.0 was released in 5/8/2020.
v2.4.0 was released in 5/9/2020.
Please refer to [changelog.md](docs/changelog.md) for details and release history.
A comparison between v1.x and v2.0 codebases can be found in [compatibility.md](docs/compatibility.md).
......
## Changelog
### v2.4.0 (5/9/2020)
**Highlights**
- Fix lots of issues/bugs and reorganize the trouble shooting page
- Support new methods [SABL](https://arxiv.org/abs/1912.04260), [YOLOv3](https://arxiv.org/abs/1804.02767), and [PAA Assign](https://arxiv.org/abs/2007.08103)
- Support Batch Inference
- Start to publish `mmdet` package to PyPI since v2.3.0
- Switch model zoo to download.openmmlab.com
**Bug Fixes**
- Fix default mean/std for onnx (#3491)
- Fix coco evaluation and add metric items (#3497)
- Fix typo for install.md (#3516)
- Fix atss when sampler per gpu is 1 (#3528)
- Fix import of fuse_conv_bn (#3529)
- Fix bug of gaussian_target, update unittest of heatmap (#3543)
- Fixed VOC2012 evaluate (#3553)
- Fix scale factor bug of rescale (#3566)
- Fix with_xxx_attributes in base detector (#3567)
- Fix boxes scaling when number is 0 (#3575)
- Fix rfp check when neck config is a list (#3591)
- Fix import of fuse conv bn in benchmark.py (#3606)
- Fix webcam demo (#3634)
- Fix typo and itemize issues in tutorial (#3658)
- Fix error in distributed training when some levels of FPN are not assigned with bounding boxes (#3670)
**New Features**
- Support Cutout augmentation (#3521)
- Support evaluation on multiple datasets through ConcatDataset (#3522)
- Support [PAA assign](https://arxiv.org/abs/2007.08103) #(3547)
- Support eval metric with pickle results (#3607)
- Support [YOLOv3](https://arxiv.org/abs/1804.02767) (#3083)
- Support [SABL](https://arxiv.org/abs/1912.04260) (#3603)
- Support Batch Inference (#3564)
- Support to publish to Pypi in github-action (#3510)
- Support RandomFlip with horizontal/vertical/diagonal direction (#3608)
**Improvements**
- Refactor common issues in documentation (#3530)
- Add pytorch 1.6 to CI config (#3532)
- Add config to runner meta (#3534)
- Add eval-option flag for testing (#3537)
- Add init_eval to evaluation hook (#3550)
- Add include_bkg in ClassBalancedDataset (#3577)
- Using config's loading in inference_detector (#3611)
- Add atss 101 (#3639)
- Support custom imports (#3641)
- Update urls to download.openmmlab.com (#3665)
### v2.3.0 (5/8/2020)
**Highlights**
......
......@@ -72,7 +72,8 @@ pip install mmcv-full
| MMDetection version | MMCV version |
|:-------------------:|:-------------------:|
| master | mmcv-full>=1.0.5, <=1.1.1|
| master | mmcv-full>=1.1.1, <=1.2|
| 2.4.0 | mmcv-full>=1.1.1, <=1.2|
| 2.3.0 | mmcv-full==1.0.5|
| 2.3.0rc0 | mmcv-full>=1.0.2 |
| 2.2.1 | mmcv==0.6.2 |
......
......@@ -16,7 +16,7 @@ def digit_version(version_str):
mmcv_minimum_version = '1.1.1'
mmcv_maximum_version = '1.1.1'
mmcv_maximum_version = '1.2'
mmcv_version = digit_version(mmcv.__version__)
......
# Copyright (c) Open-MMLab. All rights reserved.
__version__ = '2.3.0'
__version__ = '2.4.0'
short_version = __version__
......
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment