v1.0

ca8a762a · chenzk · ca8a762a · ca8a762a · ca8a762a
Commit ca8a762a authored Jan 23, 2024 by chenzk
3 changed files
--- a/configs/body_2d_keypoint/topdown_heatmap/coco/shufflenetv1_coco.yml
+++ b/configs/body_2d_keypoint/topdown_heatmap/coco/shufflenetv1_coco.yml
+Models:
+- Config: configs/body_2d_keypoint/topdown_heatmap/coco/td-hm_shufflenetv1_8xb64-210e_coco-256x192.py
+  In Collection: SimpleBaseline2D
+  Metadata:
+    Architecture: &id001
+    - SimpleBaseline2D
+    - ShufflenetV1
+    Training Data: COCO
+  Name: td-hm_shufflenetv1_8xb64-210e_coco-256x192
+  Results:
+  - Dataset: COCO
+    Metrics:
+      AP: 0.587
+      AP@0.5: 0.849
+      AP@0.75: 0.654
+      AR: 0.654
+      AR@0.5: 0.896
+    Task: Body 2D Keypoint
+  Weights: https://download.openmmlab.com/mmpose/v1/body_2d_keypoint/topdown_heatmap/coco/td-hm_shufflenetv1_8xb64-210e_coco-256x192-7a7ea4f4_20221013.pth
+- Config: configs/body_2d_keypoint/topdown_heatmap/coco/td-hm_shufflenetv1_8xb64-210e_coco-384x288.py
+  In Collection: SimpleBaseline2D
+  Metadata:
+    Architecture: *id001
+    Training Data: COCO
+  Name: td-hm_shufflenetv1_8xb64-210e_coco-384x288
+  Results:
+  - Dataset: COCO
+    Metrics:
+      AP: 0.626
+      AP@0.5: 0.862
+      AP@0.75: 0.696
+      AR: 0.687
+      AR@0.5: 0.903
+    Task: Body 2D Keypoint
+  Weights: https://download.openmmlab.com/mmpose/v1/body_2d_keypoint/topdown_heatmap/coco/td-hm_shufflenetv1_8xb64-210e_coco-384x288-8342f8ba_20221013.pth
--- a/configs/body_2d_keypoint/topdown_heatmap/coco/shufflenetv2_coco.md
+++ b/configs/body_2d_keypoint/topdown_heatmap/coco/shufflenetv2_coco.md
+<!-- [BACKBONE] -->
+
+<details>
+<summary align="right"><a href="http://openaccess.thecvf.com/content_ECCV_2018/html/Ningning_Light-weight_CNN_Architecture_ECCV_2018_paper.html">ShufflenetV2 (ECCV'2018)</a></summary>
+
+```bibtex
+@inproceedings{ma2018shufflenet,
+  title={Shufflenet v2: Practical guidelines for efficient cnn architecture design},
+  author={Ma, Ningning and Zhang, Xiangyu and Zheng, Hai-Tao and Sun, Jian},
+  booktitle={Proceedings of the European conference on computer vision (ECCV)},
+  pages={116--131},
+  year={2018}
+}
+```
+
+</details>
+
+<!-- [DATASET] -->
+
+<details>
+<summary align="right"><a href="https://link.springer.com/chapter/10.1007/978-3-319-10602-1_48">COCO (ECCV'2014)</a></summary>
+
+```bibtex
+@inproceedings{lin2014microsoft,
+  title={Microsoft coco: Common objects in context},
+  author={Lin, Tsung-Yi and Maire, Michael and Belongie, Serge and Hays, James and Perona, Pietro and Ramanan, Deva and Doll{\'a}r, Piotr and Zitnick, C Lawrence},
+  booktitle={European conference on computer vision},
+  pages={740--755},
+  year={2014},
+  organization={Springer}
+}
+```
+
+</details>
+
+Results on COCO val2017 with detector having human AP of 56.4 on COCO val2017 dataset
+
+| Arch                                          | Input Size |  AP   | AP<sup>50</sup> | AP<sup>75</sup> |  AR   | AR<sup>50</sup> |                     ckpt                      |                      log                      |
+| :-------------------------------------------- | :--------: | :---: | :-------------: | :-------------: | :---: | :-------------: | :-------------------------------------------: | :-------------------------------------------: |
+| [pose_shufflenetv2](/configs/body_2d_keypoint/topdown_heatmap/coco/td-hm_shufflenetv2_8xb64-210e_coco-256x192.py) |  256x192   | 0.602 |      0.857      |      0.672      | 0.668 |      0.902      | [ckpt](https://download.openmmlab.com/mmpose/v1/body_2d_keypoint/topdown_heatmap/coco/td-hm_shufflenetv2_8xb64-210e_coco-256x192-51fb931e_20221014.pth) | [log](https://download.openmmlab.com/mmpose/v1/body_2d_keypoint/topdown_heatmap/coco/td-hm_shufflenetv2_8xb64-210e_coco-256x192_20221014.log) |
+| [pose_shufflenetv2](/configs/body_2d_keypoint/topdown_heatmap/coco/td-hm_shufflenetv2_8xb64-210e_coco-384x288.py) |  384x288   | 0.638 |      0.866      |      0.707      | 0.699 |      0.910      | [ckpt](https://download.openmmlab.com/mmpose/v1/body_2d_keypoint/topdown_heatmap/coco/td-hm_shufflenetv2_8xb64-210e_coco-384x288-d30ab55c_20221014.pth) | [log](https://download.openmmlab.com/mmpose/v1/body_2d_keypoint/topdown_heatmap/coco/td-hm_shufflenetv2_8xb64-210e_coco-384x288_20221014.log) |
--- a/configs/body_2d_keypoint/topdown_heatmap/coco/shufflenetv2_coco.yml
+++ b/configs/body_2d_keypoint/topdown_heatmap/coco/shufflenetv2_coco.yml
+Models:
+- Config: configs/body_2d_keypoint/topdown_heatmap/coco/td-hm_shufflenetv2_8xb64-210e_coco-256x192.py
+  In Collection: SimpleBaseline2D
+  Metadata:
+    Architecture: &id001
+    - SimpleBaseline2D
+    - ShufflenetV2
+    Training Data: COCO
+  Name: td-hm_shufflenetv2_8xb64-210e_coco-256x192
+  Results:
+  - Dataset: COCO
+    Metrics:
+      AP: 0.602
+      AP@0.5: 0.857
+      AP@0.75: 0.672
+      AR: 0.668
+      AR@0.5: 0.902
+    Task: Body 2D Keypoint
+  Weights: https://download.openmmlab.com/mmpose/v1/body_2d_keypoint/topdown_heatmap/coco/td-hm_shufflenetv2_8xb64-210e_coco-256x192-51fb931e_20221014.pth
+- Config: configs/body_2d_keypoint/topdown_heatmap/coco/td-hm_shufflenetv2_8xb64-210e_coco-384x288.py
+  In Collection: SimpleBaseline2D
+  Metadata:
+    Architecture: *id001
+    Training Data: COCO
+  Name: td-hm_shufflenetv2_8xb64-210e_coco-384x288
+  Results:
+  - Dataset: COCO
+    Metrics:
+      AP: 0.638
+      AP@0.5: 0.866
+      AP@0.75: 0.707
+      AR: 0.699
+      AR@0.5: 0.91
+    Task: Body 2D Keypoint
+  Weights: https://download.openmmlab.com/mmpose/v1/body_2d_keypoint/topdown_heatmap/coco/td-hm_shufflenetv2_8xb64-210e_coco-384x288-d30ab55c_20221014.pth