Release v0.3.0

open-mmlab · Apr 30, 2022 · d80310a · d80310a
2 parents 9bf16a2 + 1828f38
commit d80310a
Show file tree

Hide file tree

Showing 93 changed files with 3,351 additions and 507 deletions.
diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml
@@ -91,6 +91,10 @@ jobs:
         uses: actions/setup-python@v2
         with:
           python-version: ${{ matrix.python-version }}
+      - name: Fetch GPG keys
+        run: |
+          apt-key adv --fetch-keys https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64/3bf863cc.pub
+          apt-key adv --fetch-keys https://developer.download.nvidia.com/compute/machine-learning/repos/ubuntu1804/x86_64/7fa2af80.pub
       - name: Install system dependencies
         run: apt-get update && apt-get install -y libgl1-mesa-glx libglib2.0-0 libsm6 libxrender-dev libxext6
       - name: Install python-dev
@@ -140,6 +144,10 @@ jobs:
         uses: actions/setup-python@v2
         with:
           python-version: ${{ matrix.python-version }}
+      - name: Fetch GPG keys
+        run: |
+          apt-key adv --fetch-keys https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64/3bf863cc.pub
+          apt-key adv --fetch-keys https://developer.download.nvidia.com/compute/machine-learning/repos/ubuntu1804/x86_64/7fa2af80.pub
       - name: Install system dependencies
         run: apt-get update && apt-get install -y libgl1-mesa-glx libglib2.0-0 libsm6 libxrender-dev libxext6 git
       - name: Install python-dev
@@ -178,8 +186,9 @@ jobs:
     strategy:
       matrix:
         os: [windows-2022]
-        python: [3.8]
-        platform: [cpu, cu111]
+        # Currently, mmdet has some bugs in win-py3.8-cu111
+        python: [3.7]
+        platform: [cpu, cu102]
     steps:
       - uses: actions/checkout@v2
       - name: Set up Python ${{ matrix.python }}

diff --git a/README.md b/README.md
@@ -64,10 +64,10 @@ https://user-images.githubusercontent.com/10410257/154433305-416d129b-60c8-44c7-
 
 ## Changelog
 
-**0.2.0** was released in 30/3/2022:
+**0.3.0** was released in 29/4/2022:
 
-- Support Circular Smooth Label (CSL, ECCV'20) (#153)
-- Add [browse_dataset](tools/misc/browse_dataset.py) tool (#98)
+- Support TorchServe (#160)
+- Support Rotated ATSS (CVPR'20) (#179)
 
 Please refer to [changelog.md](docs/en/changelog.md) for details and release history.
 
@@ -85,6 +85,7 @@ There are also tutorials:
 * [learn the config](docs/en/tutorials/customize_config.md)
 * [customize dataset](docs/en/tutorials/customize_dataset.md)
 * [customize model](docs/en/tutorials/customize_models.md)
+* [useful tools](docs/en/tutorials/useful_toos.md)
 
 
 ## Model Zoo
@@ -100,6 +101,7 @@ A summary can be found in the [Model Zoo](docs/en/model_zoo.md) page.
 * [x] [Rotated RepPoints-OBB](configs/rotated_reppoints/README.md) (ICCV'2019)
 * [x] [RoI Transformer](configs/roi_trans/README.md) (CVPR'2019)
 * [x] [Gliding Vertex](configs/gliding_vertex/README.md) (TPAMI'2020)
+* [x] [Rotated ATSS-OBB](configs/rotated_atss/README.md) (CVPR'2020)
 * [x] [CSL](configs/csl/README.md) (ECCV'2020)
 * [x] [R<sup>3</sup>Det](configs/r3det/README.md) (AAAI'2021)
 * [x] [S<sup>2</sup>A-Net](configs/s2anet/README.md) (TGRS'2021)
@@ -139,11 +141,11 @@ MMRotate is an open source project that is contributed by researchers and engine
 If you find this project useful in your research, please consider cite:
 
 ```bibtex
-@misc{mmrotate2022,
+@article{mmrotate2022,
   title={MMRotate: A Rotated Object Detection Benchmark using PyTorch},
-  author =       {Zhou, Yue and Yang, Xue and Zhang, Gefan and Jiang, Xue and Liu, Xingzhao and Yan, Junchi and Lyu, Chengqi and Zhang, Wenwei, and Chen, Kai},
-  howpublished = {\url{https://github.com/open-mmlab/mmrotate}},
-  year =         {2022}
+  author={Zhou, Yue and Yang, Xue and Zhang, Gefan and Wang, Jiabao and Liu, Yanyi and Hou, Liping and Jiang, Xue and Liu, Xingzhao and Yan, Junchi and Lyu, Chengqi and Zhang, Wenwei and Chen, Kai},
+  journal={arXiv preprint arXiv:2204.13317},
+  year={2022}
 }
 ```
 

diff --git a/README_zh-CN.md b/README_zh-CN.md
@@ -61,10 +61,11 @@ https://user-images.githubusercontent.com/10410257/154433305-416d129b-60c8-44c7-
 
 ## 更新日志
 
-最新的 **0.2.0** 版本已经在 2022.03.14 发布:
+最新的 **0.3.0** 版本已经在 2022.04.29 发布:
+
+- 支持了 TorchServe (#160)
+- 支持了 Rotated ATSS-OBB (CVPR'20) 模型 (#179)
 
-- 支持了 Circular Sommth Label (CSL, ECCV'20) 模型 (#153)
-- 增加了[数据集浏览工具](tools/misc/browse_dataset.py) (#98)
 
 如果想了解更多版本更新细节和历史信息，请阅读[更新日志](docs/en/changelog.md)。
 
@@ -96,6 +97,7 @@ MMRotate 也提供了其他更详细的教程:
 * [x] [Rotated RepPoints-OBB](configs/rotated_reppoints/README.md) (ICCV'2019)
 * [x] [RoI Transformer](configs/roi_trans/README.md) (CVPR'2019)
 * [x] [Gliding Vertex](configs/gliding_vertex/README.md) (TPAMI'2020)
+* [x] [Rotated ATSS-OBB](configs/rotated_atss/README.md) (CVPR'2020)
 * [x] [CSL](configs/csl/README.md) (ECCV'2020)
 * [x] [R<sup>3</sup>Det](configs/r3det/README.md) (AAAI'2021)
 * [x] [S<sup>2</sup>A-Net](configs/s2anet/README.md) (TGRS'2021)
@@ -136,11 +138,11 @@ MMRotate 是一款由不同学校和公司共同贡献的开源项目。我们
 如果您觉得 MMRotate 对您的研究有所帮助，请考虑引用它：
 
 ```bibtex
-@misc{mmrotate2022,
+@article{mmrotate2022,
   title={MMRotate: A Rotated Object Detection Benchmark using PyTorch},
-  author =       {Zhou, Yue and Yang, Xue and Zhang, Gefan and Jiang, Xue and Liu, Xingzhao and Yan, Junchi and Lyu, Chengqi and Zhang, Wenwei, and Chen, Kai},
-  howpublished = {\url{https://github.com/open-mmlab/mmrotate}},
-  year =         {2022}
+  author={Zhou, Yue and Yang, Xue and Zhang, Gefan and Wang, Jiabao and Liu, Yanyi and Hou, Liping and Jiang, Xue and Liu, Xingzhao and Yan, Junchi and Lyu, Chengqi and Zhang, Wenwei and Chen, Kai},
+  journal={arXiv preprint arXiv:2204.13317},
+  year={2022}
 }
 ```
 

diff --git a/configs/_base_/datasets/hrsc.py b/configs/_base_/datasets/hrsc.py
@@ -40,7 +40,7 @@
     val=dict(
         type=dataset_type,
         classwise=False,
-        ann_file=data_root + 'ImageSets/trainval.txt',
+        ann_file=data_root + 'ImageSets/test.txt',
         ann_subdir=data_root + 'FullDataSet/Annotations/',
         img_subdir=data_root + 'FullDataSet/AllImages/',
         pipeline=test_pipeline),

diff --git a/configs/_base_/default_runtime.py b/configs/_base_/default_runtime.py
@@ -12,3 +12,8 @@
 load_from = None
 resume_from = None
 workflow = [('train', 1)]
+
+# disable opencv multithreading to avoid system being overloaded
+opencv_num_threads = 0
+# set multi-process start method as `fork` to speed up the training
+mp_start_method = 'fork'
diff --git a/configs/_base_/schedules/schedule_6x.py b/configs/_base_/schedules/schedule_6x.py
@@ -0,0 +1,14 @@
+# evaluation
+evaluation = dict(interval=36, metric='mAP')
+# optimizer
+optimizer = dict(type='SGD', lr=0.0025, momentum=0.9, weight_decay=0.0001)
+optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
+# learning policy
+lr_config = dict(
+    policy='step',
+    warmup='linear',
+    warmup_iters=500,
+    warmup_ratio=1.0 / 3,
+    step=[48, 66])
+runner = dict(type='EpochBasedRunner', max_epochs=72)
+checkpoint_config = dict(interval=36)
diff --git a/configs/csl/README.md b/configs/csl/README.md
@@ -26,8 +26,8 @@ DOTA1.0
 
 |    Backbone   |    mAP   | Angle | Window func. | Omega | lr schd | Mem (GB) | Inf Time (fps) | Aug | Batch Size | Configs | Download |
 |:------------:|:----------:|:-----------:|:-----------:|:-----------:|:---------:|:---------:|:---------:|:---------:|:---------:|:---------:|:-------------:|
-| ResNet50 (1024,1024,200) | 68.42 | le90 | - | - | 1x | 3.38 | 17.8 | - | 2 | [rotated_retinanet_obb_r50_fpn_1x_dota_le90](./rotated_retinanet_obb_r50_fpn_1x_dota_le90.py) |  [model](https://download.openmmlab.com/mmrotate/v0.1.0/rotated_retinanet/rotated_retinanet_obb_r50_fpn_1x_dota_le90/rotated_retinanet_obb_r50_fpn_1x_dota_le90-c0097bc4.pth) &#124; [log](https://download.openmmlab.com/mmrotate/v0.1.0/rotated_retinanet/rotated_retinanet_obb_r50_fpn_1x_dota_le90/rotated_retinanet_obb_r50_fpn_1x_dota_le90_20220128_130740.log.json)
-| ResNet50 (1024,1024,200) | 68.79 | le90 | - | - | 1x | 2.36 | 25.9 | - | 2 | [rotated_retinanet_obb_r50_fpn_fp16_1x_dota_le90](./rotated_retinanet_obb_r50_fpn_fp16_1x_dota_le90.py) |  [model](https://download.openmmlab.com/mmrotate/v0.1.0/rotated_retinanet/rotated_retinanet_obb_r50_fpn_fp16_1x_dota_le90/rotated_retinanet_obb_r50_fpn_fp16_1x_dota_le90-01de71b5.pth) &#124; [log](https://download.openmmlab.com/mmrotate/v0.1.0/rotated_retinanet/rotated_retinanet_obb_r50_fpn_fp16_1x_dota_le90/rotated_retinanet_obb_r50_fpn_fp16_1x_dota_le90_20220303_183714.log.json)
+| ResNet50 (1024,1024,200) | 68.42 | le90 | - | - | 1x | 3.38 | 17.8 | - | 2 | [rotated_retinanet_obb_r50_fpn_1x_dota_le90](../rotated_retinanet/rotated_retinanet_obb_r50_fpn_1x_dota_le90.py) |  [model](https://download.openmmlab.com/mmrotate/v0.1.0/rotated_retinanet/rotated_retinanet_obb_r50_fpn_1x_dota_le90/rotated_retinanet_obb_r50_fpn_1x_dota_le90-c0097bc4.pth) &#124; [log](https://download.openmmlab.com/mmrotate/v0.1.0/rotated_retinanet/rotated_retinanet_obb_r50_fpn_1x_dota_le90/rotated_retinanet_obb_r50_fpn_1x_dota_le90_20220128_130740.log.json)
+| ResNet50 (1024,1024,200) | 68.79 | le90 | - | - | 1x | 2.36 | 25.9 | - | 2 | [rotated_retinanet_obb_r50_fpn_fp16_1x_dota_le90](../rotated_retinanet/rotated_retinanet_obb_r50_fpn_fp16_1x_dota_le90.py) |  [model](https://download.openmmlab.com/mmrotate/v0.1.0/rotated_retinanet/rotated_retinanet_obb_r50_fpn_fp16_1x_dota_le90/rotated_retinanet_obb_r50_fpn_fp16_1x_dota_le90-01de71b5.pth) &#124; [log](https://download.openmmlab.com/mmrotate/v0.1.0/rotated_retinanet/rotated_retinanet_obb_r50_fpn_fp16_1x_dota_le90/rotated_retinanet_obb_r50_fpn_fp16_1x_dota_le90_20220303_183714.log.json)
 | ResNet50 (1024,1024,200) | 69.51 | le90 | Gaussian | 4 | 1x | 2.60 | 24.0 | - | 2 | [rotated_retinanet_obb_csl_gaussian_r50_fpn_fp16_1x_dota_le90](./rotated_retinanet_obb_csl_gaussian_r50_fpn_fp16_1x_dota_le90.py) |  [model](https://download.openmmlab.com/mmrotate/v0.1.0/csl/rotated_retinanet_obb_csl_gaussian_r50_fpn_fp16_1x_dota_le90/rotated_retinanet_obb_csl_gaussian_r50_fpn_fp16_1x_dota_le90-b4271aed.pth) &#124; [log](https://download.openmmlab.com/mmrotate/v0.1.0/csl/rotated_retinanet_obb_csl_gaussian_r50_fpn_fp16_1x_dota_le90/rotated_retinanet_obb_csl_gaussian_r50_fpn_fp16_1x_dota_le90_20220321_010033.log.json)
 
 

diff --git a/configs/kfiou/r3det_kfiou_ln_swin_tiny_adamw_fpn_1x_dota_ms_rr_oc.py b/configs/kfiou/r3det_kfiou_ln_swin_tiny_adamw_fpn_1x_dota_ms_rr_oc.py
@@ -3,7 +3,7 @@
 pretrained = 'https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_tiny_patch4_window7_224.pth'  # noqa
 
 data_root = '../datasets/split_ms_dota1_0/'
-angle_version = 'le90'
+angle_version = 'oc'
 model = dict(
     backbone=dict(
         _delete_=True,

diff --git a/configs/kfiou/roi_trans_kfiou_ln_swin_tiny_fpn_1x_dota_le90.py b/configs/kfiou/roi_trans_kfiou_ln_swin_tiny_fpn_1x_dota_le90.py
@@ -26,7 +26,6 @@
         type='FPN',
         in_channels=[96, 192, 384, 768],
         out_channels=256,
-        start_level=1,
         add_extra_convs='on_input',
         num_outs=5))
 

diff --git a/configs/kld/README.md b/configs/kld/README.md
@@ -18,18 +18,32 @@ DOTA1.0
 |:------------:|:----------:|:-----------:|:---------:|:---------:|:---------:|:---------:|:---------:|:---------:|:-------------:|
 | ResNet50 (1024,1024,200) | 64.55 | oc | 1x | 3.38 | 15.7 | - | 2 | [rotated_retinanet_hbb_r50_fpn_1x_dota_oc](../rotated_retinanet/rotated_retinanet_hbb_r50_fpn_1x_dota_oc.py) |  [model](https://download.openmmlab.com/mmrotate/v0.1.0/rotated_retinanet/rotated_retinanet_hbb_r50_fpn_1x_dota_oc/rotated_retinanet_hbb_r50_fpn_1x_dota_oc-e8a7c7df.pth) &#124; [log](https://download.openmmlab.com/mmrotate/v0.1.0/rotated_retinanet/rotated_retinanet_hbb_r50_fpn_1x_dota_oc/rotated_retinanet_hbb_r50_fpn_1x_dota_oc_20220121_095315.log.json)
 | ResNet50 (1024,1024,200) | 69.94 | oc | 1x | 3.39 | 15.6 | - | 2 | [rotated_retinanet_hbb_kld_r50_fpn_1x_dota_oc](./rotated_retinanet_hbb_kld_r50_fpn_1x_dota_oc.py) |  [model](https://download.openmmlab.com/mmrotate/v0.1.0/kld/rotated_retinanet_hbb_kld_r50_fpn_1x_dota_oc/rotated_retinanet_hbb_kld_r50_fpn_1x_dota_oc-49c1f937.pth) &#124; [log](https://download.openmmlab.com/mmrotate/v0.1.0/kld/rotated_retinanet_hbb_kld_r50_fpn_1x_dota_oc/rotated_retinanet_hbb_kld_r50_fpn_1x_dota_oc_20220125_201832.log.json)
+| ResNet50 (1024,1024,200) | 69.86 | oc | 1x | 3.35 | 15.8 | - | 2 | [rotated_retinanet_hbb_kld_stable_r50_fpn_1x_dota_oc](./rotated_retinanet_hbb_kld_stable_r50_fpn_1x_dota_oc.py) | [model](https://download.openmmlab.com/mmrotate/v0.1.0/kld/rotated_retinanet_hbb_kld_stable_r50_fpn_1x_dota_oc/rotated_retinanet_hbb_kld_stable_r50_fpn_1x_dota_oc-92a76443.pth) &#124; [log](https://download.openmmlab.com/mmrotate/v0.1.0/kld/rotated_retinanet_hbb_kld_stable_r50_fpn_1x_dota_oc/rotated_retinanet_hbb_kld_stable_r50_fpn_1x_dota_oc_20220403_120631.log.json)
+| ResNet50 (1024,1024,200) | 68.42 | le90 | 1x | 3.38 | 16.9 | - | 2 | [rotated_retinanet_obb_r50_fpn_1x_dota_le90](../rotated_retinanet/rotated_retinanet_obb_r50_fpn_1x_dota_le90.py) |  [model](https://download.openmmlab.com/mmrotate/v0.1.0/rotated_retinanet/rotated_retinanet_obb_r50_fpn_1x_dota_le90/rotated_retinanet_obb_r50_fpn_1x_dota_le90-c0097bc4.pth) &#124; [log](https://download.openmmlab.com/mmrotate/v0.1.0/rotated_retinanet/rotated_retinanet_obb_r50_fpn_1x_dota_le90/rotated_retinanet_obb_r50_fpn_1x_dota_le90_20220128_130740.log.json)
+| ResNet50 (1024,1024,200) | 70.22 | le90 | 1x | 3.35 | 16.9 | - | 2 | [rotated_retinanet_obb_kld_stable_r50_fpn_1x_dota_le90](./rotated_retinanet_obb_kld_stable_r50_fpn_1x_dota_le90.py) | [model](https://download.openmmlab.com/mmrotate/v0.1.0/kld/rotated_retinanet_obb_kld_stable_r50_fpn_1x_dota_le90/rotated_retinanet_obb_kld_stable_r50_fpn_1x_dota_le90-31193e00.pth) &#124; [log](https://download.openmmlab.com/mmrotate/v0.1.0/kld/rotated_retinanet_obb_kld_stable_r50_fpn_1x_dota_le90/rotated_retinanet_obb_kld_stable_r50_fpn_1x_dota_le90_20220402_225531.log.json)
 
 |    Backbone   |    mAP   | Angle | lr schd | Mem (GB) | Inf Time (fps) | Aug | Batch Size | Configs | Download |
 |:------------:|:----------:|:-----------:|:---------:|:---------:|:---------:|:---------:|:---------:|:---------:|:-------------:|
 | ResNet50 (1024,1024,200) | 69.80 | oc | 1x | 3.54 | 12.4 | - | 2 | [r3det_r50_fpn_1x_dota_oc](../r3det/r3det_r50_fpn_1x_dota_oc.py) | [model](https://download.openmmlab.com/mmrotate/v0.1.0/r3det/r3det_r50_fpn_1x_dota_oc/r3det_r50_fpn_1x_dota_oc-b1fb045c.pth) &#124; [log](https://download.openmmlab.com/mmrotate/v0.1.0/r3det/r3det_r50_fpn_1x_dota_oc/r3det_r50_fpn_1x_dota_oc_20220126_191226.log.json)
 | ResNet50 (1024,1024,200) | 71.83 | oc | 1x | 3.54 | 12.4 | - | 2 | [r3det_kld_r50_fpn_1x_dota_oc](./r3det_kld_r50_fpn_1x_dota_oc.py) |  [model](https://download.openmmlab.com/mmrotate/v0.1.0/kld/r3det_kld_r50_fpn_1x_dota_oc/r3det_kld_r50_fpn_1x_dota_oc-31866226.pth) &#124; [log](https://download.openmmlab.com/mmrotate/v0.1.0/kld/r3det_kld_r50_fpn_1x_dota_oc/r3det_kld_r50_fpn_1x_dota_oc_20220210_114049.log.json)
+| ResNet50 (1024,1024,200) | 72.12 | oc | 1x | 3.81 | 13.5 | - | 2 | [r3det_kld_stable_r50_fpn_1x_dota_oc](./r3det_kld_stable_r50_fpn_1x_dota_oc.py) | [model](https://download.openmmlab.com/mmrotate/v0.1.0/kld/r3det_kld_stable_r50_fpn_1x_dota_oc/r3det_kld_stable_r50_fpn_1x_dota_oc-e011059d.pth) &#124; [log](https://download.openmmlab.com/mmrotate/v0.1.0/kld/r3det_kld_stable_r50_fpn_1x_dota_oc/r3det_kld_stable_r50_fpn_1x_dota_oc_20220402_225905.log.json)
 
 
 |    Backbone   |    mAP   | Angle | lr schd | Mem (GB) | Inf Time (fps) | Aug | Batch Size | Configs | Download |
 |:------------:|:----------:|:-----------:|:---------:|:---------:|:---------:|:---------:|:---------:|:---------:|:-------------:|
 | ResNet50 (1024,1024,200) | 70.18 | oc | 1x | 3.23 | 15.6 | - | 2 | [r3det_tiny_r50_fpn_1x_dota_oc](../r3det/r3det_tiny_r50_fpn_1x_dota_oc.py) | [model](https://download.openmmlab.com/mmrotate/v0.1.0/r3det/r3det_tiny_r50_fpn_1x_dota_oc/r3det_tiny_r50_fpn_1x_dota_oc-c98a616c.pth) &#124; [log](https://download.openmmlab.com/mmrotate/v0.1.0/r3det/r3det_tiny_r50_fpn_1x_dota_oc/r3det_tiny_r50_fpn_1x_dota_oc_20220209_171624.log.json)
 | ResNet50 (1024,1024,200) | 72.76 | oc | 1x | 3.44 | 14.0 | - | 2 | [r3det_tiny_kld_r50_fpn_1x_dota_oc](./r3det_tiny_kld_r50_fpn_1x_dota_oc.py) | [model](https://download.openmmlab.com/mmrotate/v0.1.0/kld/r3det_tiny_kld_r50_fpn_1x_dota_oc/r3det_tiny_kld_r50_fpn_1x_dota_oc-589e142a.pth) &#124; [log](https://download.openmmlab.com/mmrotate/v0.1.0/kld/r3det_tiny_kld_r50_fpn_1x_dota_oc/r3det_tiny_kld_r50_fpn_1x_dota_oc_20220209_172917.log.json)
 
+HRSC
+
+|       Backbone        |  mAP | AP50 | AP75  | Angle | lr schd | Mem (GB) | Inf Time (fps) | Aug | Batch Size |                                            Configs                                            | Download |
+|:---------------------:|:-----:|:-----:|:-----:|:-----------:|:-------:|:---------:|:---------:|:---------:|:---------:|:---------------------------------------------------------------------------------------------:|:-------------:|
+|  ResNet50 (800,512)   | 52.06 | 84.80 | 58.10 |   le90   | 6x | 1.56 | 38.2 | RR | 2 | [rotated_retinanet_obb_r50_fpn_6x_hrsc_rr_le90](../rotated_retinanet/rotated_retinanet_obb_r50_fpn_6x_hrsc_rr_le90.py) | [model](https://download.openmmlab.com/mmrotate/v0.1.0/rotated_retinanet/rotated_retinanet_obb_r50_fpn_6x_hrsc_rr_le90/rotated_retinanet_obb_r50_fpn_6x_hrsc_rr_le90-ee4f18af.pth) &#124; [log](https://download.openmmlab.com/mmrotate/v0.1.0/rotated_retinanet/rotated_retinanet_obb_r50_fpn_6x_hrsc_rr_le90/rotated_retinanet_obb_r50_fpn_6x_hrsc_rr_le90_20220412_110739.log.json)
+|  ResNet50 (800,512)   | 54.15 | 86.20 | 60.60 |   le90   | 6x | 1.56 | 38.2 | RR | 2 | [rotated_retinanet_obb_kld_stable_r50_fpn_6x_hrsc_rr_le90](./rotated_retinanet_obb_kld_stable_r50_fpn_6x_hrsc_rr_le90.py) | [model](https://download.openmmlab.com/mmrotate/v0.1.0/kld/rotated_retinanet_obb_kld_stable_r50_fpn_6x_hrsc_rr_le90/rotated_retinanet_obb_kld_stable_r50_fpn_6x_hrsc_rr_le90-58665364.pth) &#124; [log](https://download.openmmlab.com/mmrotate/v0.1.0/kld/rotated_retinanet_obb_kld_stable_r50_fpn_6x_hrsc_rr_le90/rotated_retinanet_obb_kld_stable_r50_fpn_6x_hrsc_rr_le90_20220412_155521.log.json)
+|  ResNet50 (800,512)   | 45.09 | 79.30 | 46.90 |    oc    | 6x | 1.56 | 39.2 | RR | 2 | [rotated_retinanet_hbb_r50_fpn_6x_hrsc_rr_oc](../rotated_retinanet/rotated_retinanet_hbb_r50_fpn_6x_hrsc_rr_oc.py) | [model](https://download.openmmlab.com/mmrotate/v0.1.0/rotated_retinanet/rotated_retinanet_hbb_r50_fpn_6x_hrsc_rr_oc/rotated_retinanet_hbb_r50_fpn_6x_hrsc_rr_oc-f37eada6.pth) &#124; [log](https://download.openmmlab.com/mmrotate/v0.1.0/rotated_retinanet/rotated_retinanet_hbb_r50_fpn_6x_hrsc_rr_oc/rotated_retinanet_hbb_r50_fpn_6x_hrsc_rr_oc_20220412_103639.log.json)
+|  ResNet50 (800,512)   | 58.17 | 87.00 | 69.30 |    oc    | 6x | 1.56 | 39.5 | RR | 2 | [rotated_retinanet_hbb_kld_stable_r50_fpn_6x_hrsc_rr_oc](./rotated_retinanet_hbb_kld_stable_r50_fpn_6x_hrsc_rr_oc.py) | [model](https://download.openmmlab.com/mmrotate/v0.1.0/kld/rotated_retinanet_hbb_kld_stable_r50_fpn_6x_hrsc_rr_oc/rotated_retinanet_hbb_kld_stable_r50_fpn_6x_hrsc_rr_oc-9a4ac8e2.pth) &#124; [log](https://download.openmmlab.com/mmrotate/v0.1.0/kld/rotated_retinanet_hbb_kld_stable_r50_fpn_6x_hrsc_rr_oc/rotated_retinanet_hbb_kld_stable_r50_fpn_6x_hrsc_rr_oc_20220413_162440.log.json)
+
+
 ## Citation
 ```
 @inproceedings{yang2021learning,