From 676702996a9c2fd8d5ec5cc00e9b8bb2f7ac5348 Mon Sep 17 00:00:00 2001
From: Kai Chen <chenkaidev@gmail.com>
Date: Fri, 3 May 2019 22:35:25 -0700
Subject: [PATCH] reorg the model zoo
---
MODEL_ZOO.md | 47 +++++++------------
configs/dcn/README.md | 42 +++++++++++++++++
configs/gn/README.md | 27 +++++++++++
configs/{ => gn}/mask_rcnn_r101_fpn_gn_2x.py | 0
configs/{ => gn}/mask_rcnn_r50_fpn_gn_2x.py | 0
.../mask_rcnn_r50_fpn_gn_contrib_2x.py | 0
6 files changed, 85 insertions(+), 31 deletions(-)
create mode 100644 configs/dcn/README.md
create mode 100644 configs/gn/README.md
rename configs/{ => gn}/mask_rcnn_r101_fpn_gn_2x.py (100%)
rename configs/{ => gn}/mask_rcnn_r50_fpn_gn_2x.py (100%)
rename configs/{ => gn}/mask_rcnn_r50_fpn_gn_contrib_2x.py (100%)
diff --git a/MODEL_ZOO.md b/MODEL_ZOO.md
index 6c68e721..263850d6 100644
--- a/MODEL_ZOO.md
+++ b/MODEL_ZOO.md
@@ -148,7 +148,17 @@ More models with different backbones will be added to the model zoo.
### Hybrid Task Cascade (HTC)
-Please refer to [HTC](configs/htc/README.md) for details.
+| Backbone | Style | Lr schd | Mem (GB) | Train time (s/iter) | Inf time (fps) | box AP | mask AP | Download |
+|:---------:|:-------:|:-------:|:--------:|:-------------------:|:--------------:|:------:|:-------:|:--------:|
+| R-50-FPN | pytorch | 1x | 7.4 | 0.936 | 3.5 | 42.2 | 37.3 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/htc/htc_r50_fpn_1x_20190408-878c1712.pth) |
+| R-50-FPN | pytorch | 20e | - | - | - | 43.2 | 38.0 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/htc/htc_r50_fpn_20e_20190408-c03b7015.pth) |
+| R-101-FPN | pytorch | 20e | 9.3 | 1.051 | 3.4 | 44.9 | 39.4 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/htc/htc_r101_fpn_20e_20190408-a2e586db.pth) |
+| X-101-32x4d-FPN | pytorch |20e| 5.8 | 0.769 | 3.3 | 46.1 | 40.3 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/htc/htc_x101_32x4d_fpn_20e_20190408-9eae4d0b.pth) |
+| X-101-64x4d-FPN | pytorch |20e| 7.5 | 1.120 | 3.0 | 47.0 | 40.9 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/htc/htc_x101_64x4d_fpn_20e_20190408-497f2561.pth) |
+
+**Notes:**
+
+- Please refer to [Hybrid Task Cascade](configs/gn/README.md) for details and more a powerful model (50.7/43.9).
### SSD
@@ -172,41 +182,16 @@ Please refer to [HTC](configs/htc/README.md) for details.
### Group Normalization (GN)
-| Backbone | model | Lr schd | Mem (GB) | Train time (s/iter) | Inf time (fps) | box AP | mask AP | Download |
-|:-------------:|:----------:|:-------:|:--------:|:-------------------:|:--------------:|:------:|:-------:|:--------:|
-| R-50-FPN (d) | Mask R-CNN | 2x | 7.2 | 0.806 | 5.4 | 39.9 | 36.1 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/mask_rcnn_r50_fpn_gn_2x_20180113-86832cf2.pth) |
-| R-50-FPN (d) | Mask R-CNN | 3x | 7.2 | 0.806 | 5.4 | 40.2 | 36.5 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/mask_rcnn_r50_fpn_gn_3x_20180113-8e82f48d.pth) |
-| R-101-FPN (d) | Mask R-CNN | 2x | 9.9 | 0.970 | 4.8 | 41.6 | 37.1 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/mask_rcnn_r101_fpn_gn_2x_20180113-9598649c.pth) |
-| R-101-FPN (d) | Mask R-CNN | 3x | 9.9 | 0.970 | 4.8 | 41.7 | 37.3 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/mask_rcnn_r101_fpn_gn_3x_20180113-a14ffb96.pth) |
-| R-50-FPN (c) | Mask R-CNN | 2x | 7.2 | 0.806 | 5.4 | 39.7 | 35.9 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/mask_rcnn_r50_fpn_gn_contrib_2x_20180113-ec93305c.pth) |
-| R-50-FPN (c) | Mask R-CNN | 3x | 7.2 | 0.806 | 5.4 | 40.1 | 36.2 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/mask_rcnn_r50_fpn_gn_contrib_3x_20180113-9d230cab.pth) |
+Please refer to [Group Normalization](configs/gn/README.md) for details.
-**Notes:**
-- (d) means pretrained model converted from Detectron, and (c) means the contributed model pretrained by [@thangvubk](https://github.com/thangvubk).
-- The `3x` schedule is epoch [28, 34, 36].
+### Weight Standardization
-### Deformable Convolution v2
+Please refer to [Weight Standardization](configs/gn+ws/README.md) for details.
-| Backbone | Model | Style | Conv | Pool | Lr schd | Mem (GB) | Train time (s/iter) | Inf time (fps) | box AP | mask AP | Download |
-|:---------:|:------------:|:-------:|:-------------:|:------:|:-------:|:--------:|:-------------------:|:--------------:|:------:|:-------:|:--------:|
-| R-50-FPN | Faster | pytorch | dconv(c3-c5) | - | 1x | 3.9 | 0.594 | 10.2 | 40.0 | - | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/dcn/faster_rcnn_dconv_c3-c5_r50_fpn_1x_20190125-e41688c9.pth) |
-| R-50-FPN | Faster | pytorch | mdconv(c3-c5) | - | 1x | 3.7 | 0.598 | 10.0 | 40.3 | - | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/dcn/faster_rcnn_mdconv_c3-c5_r50_fpn_1x_20190125-1b768045.pth) |
-| R-50-FPN | Faster | pytorch | - | dpool | 1x | 4.6 | 0.714 | 8.7 | 37.9 | - | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/dcn/faster_rcnn_dpool_r50_fpn_1x_20190125-f4fc1d70.pth) |
-| R-50-FPN | Faster | pytorch | - | mdpool | 1x | 5.2 | 0.769 | 8.2 | 38.1 | - | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/dcn/faster_rcnn_mdpool_r50_fpn_1x_20190125-473d0f3d.pth) |
-| R-101-FPN | Faster | pytorch | dconv(c3-c5) | - | 1x | 5.8 | 0.811 | 8.0 | 42.1 | - | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/dcn/faster_rcnn_dconv_c3-c5_r101_fpn_1x_20190125-a7e31b65.pth) |
-| X-101-32x4d-FPN | Faster | pytorch | dconv(c3-c5) | - | 1x | 7.1 | 1.126 | 6.6 | 43.5 | - | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/dcn/faster_rcnn_dconv_c3-c5_x101_32x4d_fpn_1x_20190201-6d46376f.pth) |
-| R-50-FPN | Mask | pytorch | dconv(c3-c5) | - | 1x | 4.5 | 0.712 | 7.7 | 41.1 | 37.2 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/dcn/mask_rcnn_dconv_c3-c5_r50_fpn_1x_20190125-4f94ff79.pth) |
-| R-50-FPN | Mask | pytorch | mdconv(c3-c5) | - | 1x | 4.5 | 0.712 | 7.7 | 41.4 | 37.4 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/dcn/mask_rcnn_mdconv_c3-c5_r50_fpn_1x_20190125-c5601dc3.pth) |
-| R-101-FPN | Mask | pytorch | dconv(c3-c5) | - | 1x | 6.4 | 0.939 | 6.5 | 43.2 | 38.7 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/dcn/mask_rcnn_dconv_c3-c5_r101_fpn_1x_20190125-decb6db5.pth) |
-| R-50-FPN | Cascade | pytorch | dconv(c3-c5) | - | 1x | 4.4 | 0.660 | 7.6 | 44.1 | - | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/dcn/cascade_rcnn_dconv_c3-c5_r50_fpn_1x_20190125-dfa53166.pth) |
-| R-101-FPN | Cascade | pytorch | dconv(c3-c5) | - | 1x | 6.3 | 0.881 | 6.8 | 45.1 | - | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/dcn/cascade_rcnn_dconv_c3-c5_r101_fpn_1x_20190125-aaa877cc.pth) |
-| R-50-FPN | Cascade Mask | pytorch | dconv(c3-c5) | - | 1x | 6.6 | 0.942 | 5.7 | 44.5 | 38.3 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/dcn/cascade_mask_rcnn_dconv_c3-c5_r50_fpn_1x_20190125-09d8a443.pth) |
-| R-101-FPN | Cascade Mask | pytorch | dconv(c3-c5) | - | 1x | 8.5 | 1.156 | 5.1 | 45.8 | 39.5 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/dcn/cascade_mask_rcnn_dconv_c3-c5_r101_fpn_1x_20190125-0d62c190.pth) |
+### Deformable Convolution v2
-**Notes:**
+Please refer to [Deformable Convolutional Networks](configs/dcn/README.md) for details.
-- `dconv` and `mdconv` denote (modulated) deformable convolution, `c3-c5` means adding dconv in resnet stage 3 to 5. `dpool` and `mdpool` denote (modulated) deformable roi pooling.
-- The dcn ops are modified from https://github.com/chengdazhi/Deformable-Convolution-V2-PyTorch, which should be more memory efficient and slightly faster.
## Comparison with Detectron and maskrcnn-benchmark
diff --git a/configs/dcn/README.md b/configs/dcn/README.md
new file mode 100644
index 00000000..4b2a36da
--- /dev/null
+++ b/configs/dcn/README.md
@@ -0,0 +1,42 @@
+# Deformable Convolutional Networks
+
+# Introduction
+
+```
+@inproceedings{dai2017deformable,
+ title={Deformable Convolutional Networks},
+ author={Dai, Jifeng and Qi, Haozhi and Xiong, Yuwen and Li, Yi and Zhang, Guodong and Hu, Han and Wei, Yichen},
+ booktitle={Proceedings of the IEEE international conference on computer vision},
+ year={2017}
+}
+
+@article{zhu2018deformable,
+ title={Deformable ConvNets v2: More Deformable, Better Results},
+ author={Zhu, Xizhou and Hu, Han and Lin, Stephen and Dai, Jifeng},
+ journal={arXiv preprint arXiv:1811.11168},
+ year={2018}
+}
+```
+
+## Results and Models
+
+| Backbone | Model | Style | Conv | Pool | Lr schd | Mem (GB) | Train time (s/iter) | Inf time (fps) | box AP | mask AP | Download |
+|:---------:|:------------:|:-------:|:-------------:|:------:|:-------:|:--------:|:-------------------:|:--------------:|:------:|:-------:|:--------:|
+| R-50-FPN | Faster | pytorch | dconv(c3-c5) | - | 1x | 3.9 | 0.594 | 10.2 | 40.0 | - | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/dcn/faster_rcnn_dconv_c3-c5_r50_fpn_1x_20190125-e41688c9.pth) |
+| R-50-FPN | Faster | pytorch | mdconv(c3-c5) | - | 1x | 3.7 | 0.598 | 10.0 | 40.3 | - | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/dcn/faster_rcnn_mdconv_c3-c5_r50_fpn_1x_20190125-1b768045.pth) |
+| R-50-FPN | Faster | pytorch | - | dpool | 1x | 4.6 | 0.714 | 8.7 | 37.9 | - | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/dcn/faster_rcnn_dpool_r50_fpn_1x_20190125-f4fc1d70.pth) |
+| R-50-FPN | Faster | pytorch | - | mdpool | 1x | 5.2 | 0.769 | 8.2 | 38.1 | - | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/dcn/faster_rcnn_mdpool_r50_fpn_1x_20190125-473d0f3d.pth) |
+| R-101-FPN | Faster | pytorch | dconv(c3-c5) | - | 1x | 5.8 | 0.811 | 8.0 | 42.1 | - | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/dcn/faster_rcnn_dconv_c3-c5_r101_fpn_1x_20190125-a7e31b65.pth) |
+| X-101-32x4d-FPN | Faster | pytorch | dconv(c3-c5) | - | 1x | 7.1 | 1.126 | 6.6 | 43.5 | - | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/dcn/faster_rcnn_dconv_c3-c5_x101_32x4d_fpn_1x_20190201-6d46376f.pth) |
+| R-50-FPN | Mask | pytorch | dconv(c3-c5) | - | 1x | 4.5 | 0.712 | 7.7 | 41.1 | 37.2 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/dcn/mask_rcnn_dconv_c3-c5_r50_fpn_1x_20190125-4f94ff79.pth) |
+| R-50-FPN | Mask | pytorch | mdconv(c3-c5) | - | 1x | 4.5 | 0.712 | 7.7 | 41.4 | 37.4 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/dcn/mask_rcnn_mdconv_c3-c5_r50_fpn_1x_20190125-c5601dc3.pth) |
+| R-101-FPN | Mask | pytorch | dconv(c3-c5) | - | 1x | 6.4 | 0.939 | 6.5 | 43.2 | 38.7 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/dcn/mask_rcnn_dconv_c3-c5_r101_fpn_1x_20190125-decb6db5.pth) |
+| R-50-FPN | Cascade | pytorch | dconv(c3-c5) | - | 1x | 4.4 | 0.660 | 7.6 | 44.1 | - | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/dcn/cascade_rcnn_dconv_c3-c5_r50_fpn_1x_20190125-dfa53166.pth) |
+| R-101-FPN | Cascade | pytorch | dconv(c3-c5) | - | 1x | 6.3 | 0.881 | 6.8 | 45.1 | - | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/dcn/cascade_rcnn_dconv_c3-c5_r101_fpn_1x_20190125-aaa877cc.pth) |
+| R-50-FPN | Cascade Mask | pytorch | dconv(c3-c5) | - | 1x | 6.6 | 0.942 | 5.7 | 44.5 | 38.3 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/dcn/cascade_mask_rcnn_dconv_c3-c5_r50_fpn_1x_20190125-09d8a443.pth) |
+| R-101-FPN | Cascade Mask | pytorch | dconv(c3-c5) | - | 1x | 8.5 | 1.156 | 5.1 | 45.8 | 39.5 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/dcn/cascade_mask_rcnn_dconv_c3-c5_r101_fpn_1x_20190125-0d62c190.pth) |
+
+**Notes:**
+
+- `dconv` and `mdconv` denote (modulated) deformable convolution, `c3-c5` means adding dconv in resnet stage 3 to 5. `dpool` and `mdpool` denote (modulated) deformable roi pooling.
+- The dcn ops are modified from https://github.com/chengdazhi/Deformable-Convolution-V2-PyTorch, which should be more memory efficient and slightly faster.
\ No newline at end of file
diff --git a/configs/gn/README.md b/configs/gn/README.md
new file mode 100644
index 00000000..3f43f598
--- /dev/null
+++ b/configs/gn/README.md
@@ -0,0 +1,27 @@
+# Group Normalization
+
+## Introduction
+
+```
+@inproceedings{wu2018group,
+ title={Group Normalization},
+ author={Wu, Yuxin and He, Kaiming},
+ booktitle={Proceedings of the European Conference on Computer Vision (ECCV)},
+ year={2018}
+}
+```
+
+## Results and Models
+
+| Backbone | model | Lr schd | Mem (GB) | Train time (s/iter) | Inf time (fps) | box AP | mask AP | Download |
+|:-------------:|:----------:|:-------:|:--------:|:-------------------:|:--------------:|:------:|:-------:|:--------:|
+| R-50-FPN (d) | Mask R-CNN | 2x | 7.2 | 0.806 | 5.4 | 39.9 | 36.1 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/mask_rcnn_r50_fpn_gn_2x_20180113-86832cf2.pth) |
+| R-50-FPN (d) | Mask R-CNN | 3x | 7.2 | 0.806 | 5.4 | 40.2 | 36.5 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/mask_rcnn_r50_fpn_gn_3x_20180113-8e82f48d.pth) |
+| R-101-FPN (d) | Mask R-CNN | 2x | 9.9 | 0.970 | 4.8 | 41.6 | 37.1 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/mask_rcnn_r101_fpn_gn_2x_20180113-9598649c.pth) |
+| R-101-FPN (d) | Mask R-CNN | 3x | 9.9 | 0.970 | 4.8 | 41.7 | 37.3 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/mask_rcnn_r101_fpn_gn_3x_20180113-a14ffb96.pth) |
+| R-50-FPN (c) | Mask R-CNN | 2x | 7.2 | 0.806 | 5.4 | 39.7 | 35.9 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/mask_rcnn_r50_fpn_gn_contrib_2x_20180113-ec93305c.pth) |
+| R-50-FPN (c) | Mask R-CNN | 3x | 7.2 | 0.806 | 5.4 | 40.1 | 36.2 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/mask_rcnn_r50_fpn_gn_contrib_3x_20180113-9d230cab.pth) |
+
+**Notes:**
+- (d) means pretrained model converted from Detectron, and (c) means the contributed model pretrained by [@thangvubk](https://github.com/thangvubk).
+- The `3x` schedule is epoch [28, 34, 36].
\ No newline at end of file
diff --git a/configs/mask_rcnn_r101_fpn_gn_2x.py b/configs/gn/mask_rcnn_r101_fpn_gn_2x.py
similarity index 100%
rename from configs/mask_rcnn_r101_fpn_gn_2x.py
rename to configs/gn/mask_rcnn_r101_fpn_gn_2x.py
diff --git a/configs/mask_rcnn_r50_fpn_gn_2x.py b/configs/gn/mask_rcnn_r50_fpn_gn_2x.py
similarity index 100%
rename from configs/mask_rcnn_r50_fpn_gn_2x.py
rename to configs/gn/mask_rcnn_r50_fpn_gn_2x.py
diff --git a/configs/mask_rcnn_r50_fpn_gn_contrib_2x.py b/configs/gn/mask_rcnn_r50_fpn_gn_contrib_2x.py
similarity index 100%
rename from configs/mask_rcnn_r50_fpn_gn_contrib_2x.py
rename to configs/gn/mask_rcnn_r50_fpn_gn_contrib_2x.py
--
GitLab