updata fairmot modelzoo (#4270)

c3774746 · Feng Ni · GitHub · 4c09bff6 · c3774746 · c3774746
5 changed file
--- a/configs/mot/README.md
+++ b/configs/mot/README.md
@@ -113,7 +113,7 @@ Each txt is the detection result of all the pictures extracted from each video,
 | backbone       | input shape | MOTA | IDF1 |  IDS  |    FP   |   FN   |    FPS    | download | config |
 | :--------------| :------- | :----: | :----: | :----: | :----: | :----: | :------: | :----: |:-----: |
 | DLA-34(paper)  | 1088x608 |  83.3  |  81.9  |   544  |  3822  |  14095  |     -   |    -   |   -    |
-| DLA-34         | 1088x608 |  83.7  |  83.3  |   435  |  3829  |  13764  |     -   | [model](https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_1088x608.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.1/configs/mot/fairmot/fairmot_dla34_30e_1088x608.yml) |
+| DLA-34         | 1088x608 |  83.2  |  83.1  |   499  |  3861  |  14223  |     -   | [model](https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_1088x608.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.1/configs/mot/fairmot/fairmot_dla34_30e_1088x608.yml) |


 ### FairMOT Results on MOT-16 Test Set
@@ -121,10 +121,10 @@ Each txt is the detection result of all the pictures extracted from each video,
 | backbone       | input shape | MOTA | IDF1 |  IDS  |    FP   |   FN   |    FPS    | download | config |
 | :--------------| :------- | :----: | :----: | :----: | :----: | :----: | :------: | :----: |:-----: |
 | DLA-34(paper)  | 1088x608 |  74.9  |  72.8  |  1074  |    -   |    -   |   25.9   |    -   |   -    |
-| DLA-34         | 1088x608 |  74.8  |  74.4  |  930   |  7038  |  37994 |    -     | [model](https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_1088x608.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.1/configs/mot/fairmot/fairmot_dla34_30e_1088x608.yml) |
+| DLA-34         | 1088x608 |  75.0  |  74.7  |  919   |  7934  |  36747 |    -     | [model](https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_1088x608.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.1/configs/mot/fairmot/fairmot_dla34_30e_1088x608.yml) |

 **Notes:**
- FairMOT used 8 GPUs for training and mini-batch size as 6 on each GPU, and trained for 30 epoches.
+ FairMOT used 2 GPUs for training and mini-batch size as 6 on each GPU, and trained for 30 epoches.


 ## Dataset Preparation

--- a/configs/mot/README_cn.md
+++ b/configs/mot/README_cn.md
@@ -113,17 +113,17 @@ wget https://dataset.bj.bcebos.com/mot/det_results_dir.zip
 |    骨干网络      |  输入尺寸 |  MOTA  |  IDF1  |  IDS  |   FP  |   FN   |   FPS   |  下载链接 | 配置文件 |
 | :--------------| :------- | :----: | :----: | :---: | :----: | :---: | :------: | :----: |:----: |
 | DLA-34(paper)  | 1088x608 |  83.3  |  81.9  |  544  |  3822  | 14095 |    -     |   -   |   -   |
-| DLA-34         | 1088x608 |  83.7  |  83.3  |  435  |  3829  | 13764 |    -     |[下载链接](https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_1088x608.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.1/configs/mot/fairmot/fairmot_dla34_30e_1088x608.yml) |
+| DLA-34         | 1088x608 |  83.2  |  83.1  |  499  |  3861  | 14223 |    -     |[下载链接](https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_1088x608.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.1/configs/mot/fairmot/fairmot_dla34_30e_1088x608.yml) |

 ### FairMOT在MOT-16 Test Set上结果

 |    骨干网络      |  输入尺寸 |  MOTA  |  IDF1  |   IDS  |   FP   |   FN   |    FPS   |  下载链接  | 配置文件 |
 | :--------------| :------- | :----: | :----: | :----: | :----: | :----: |:-------: | :----: | :----: |
 | DLA-34(paper)  | 1088x608 |  74.9  |  72.8  |  1074  |    -   |    -   |   25.9   |    -   |   -    |
-| DLA-34         | 1088x608 |  74.8  |  74.4  |  930   |  7038  |  37994 |    -     |[下载链接](https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_1088x608.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.1/configs/mot/fairmot/fairmot_dla34_30e_1088x608.yml) |
+| DLA-34         | 1088x608 |  75.0  |  74.7  |  919   |  7934  |  36747 |    -     |[下载链接](https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_1088x608.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.1/configs/mot/fairmot/fairmot_dla34_30e_1088x608.yml) |

 **注意:**
- FairMOT使用8个GPU进行训练，每个GPU上batch size为6，训练30个epoch。
+ FairMOT使用2个GPU进行训练，每个GPU上batch size为6，训练30个epoch。


 ## 数据集准备

--- a/configs/mot/fairmot/README.md
+++ b/configs/mot/fairmot/README.md
@@ -19,7 +19,7 @@ English | [简体中文](README_cn.md)
 | backbone       | input shape | MOTA | IDF1 |  IDS  |    FP   |   FN   |    FPS    | download | config |
 | :--------------| :------- | :----: | :----: | :----: | :----: | :----: | :------: | :----: |:-----: |
 | DLA-34(paper)  | 1088x608 |  83.3  |  81.9  |   544  |  3822  |  14095  |     -   |    -   |   -    |
-| DLA-34         | 1088x608 |  83.7  |  83.3  |   435  |  3829  |  13764  |     -   | [model](https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_1088x608.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.1/configs/mot/fairmot/fairmot_dla34_30e_1088x608.yml) |
+| DLA-34         | 1088x608 |  83.2  |  83.1  |   499  |  3861  |  14223  |     -   | [model](https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_1088x608.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.1/configs/mot/fairmot/fairmot_dla34_30e_1088x608.yml) |


 ### FairMOT Results on MOT-16 Test Set
@@ -27,7 +27,7 @@ English | [简体中文](README_cn.md)
 | backbone       | input shape | MOTA | IDF1 |  IDS  |    FP   |   FN   |    FPS    | download | config |
 | :--------------| :------- | :----: | :----: | :----: | :----: | :----: | :------: | :----: |:-----: |
 | DLA-34(paper)  | 1088x608 |  74.9  |  72.8  |  1074  |    -   |    -   |   25.9   |    -   |   -    |
-| DLA-34         | 1088x608 |  74.8  |  74.4  |  930   |  7038  |  37994 |    -     | [model](https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_1088x608.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.1/configs/mot/fairmot/fairmot_dla34_30e_1088x608.yml) |
+| DLA-34         | 1088x608 |  75.0  |  74.7  |  919   |  7934  |  36747 |    -     | [model](https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_1088x608.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.1/configs/mot/fairmot/fairmot_dla34_30e_1088x608.yml) |

 **Notes:**
 FairMOT used 8 GPUs for training and mini-batch size as 6 on each GPU, and trained for 30 epoches.
@@ -36,10 +36,10 @@ English | [简体中文](README_cn.md)

 ### 1. Training

-Training FairMOT on 8 GPUs with following command
+Training FairMOT on 2 GPUs with following command

 ```bash
-python -m paddle.distributed.launch --log_dir=./fairmot_dla34_30e_1088x608/ --gpus 0,1,2,3,4,5,6,7 tools/train.py -c configs/mot/fairmot/fairmot_dla34_30e_1088x608.yml
+python -m paddle.distributed.launch --log_dir=./fairmot_dla34_30e_1088x608/ --gpus 0,1 tools/train.py -c configs/mot/fairmot/fairmot_dla34_30e_1088x608.yml
 ```



--- a/configs/mot/fairmot/README_cn.md
+++ b/configs/mot/fairmot/README_cn.md
@@ -19,17 +19,17 @@
 |    骨干网络      |  输入尺寸 |  MOTA  |  IDF1  |  IDS  |   FP  |   FN   |   FPS   |  下载链接 | 配置文件 |
 | :--------------| :------- | :----: | :----: | :---: | :----: | :---: | :------: | :----: |:----: |
 | DLA-34(paper)  | 1088x608 |  83.3  |  81.9  |  544  |  3822  | 14095 |    -     |   -   |   -   |
-| DLA-34         | 1088x608 |  83.7  |  83.3  |  435  |  3829  | 13764 |    -     |[下载链接](https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_1088x608.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.1/configs/mot/fairmot/fairmot_dla34_30e_1088x608.yml) |
+| DLA-34         | 1088x608 |  83.2  |  83.1  |  499  |  3861  | 14223 |    -     |[下载链接](https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_1088x608.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.1/configs/mot/fairmot/fairmot_dla34_30e_1088x608.yml) |

 ### FairMOT在MOT-16 Test Set上结果

 |    骨干网络      |  输入尺寸 |  MOTA  |  IDF1  |   IDS  |   FP   |   FN   |    FPS   |  下载链接  | 配置文件 |
 | :--------------| :------- | :----: | :----: | :----: | :----: | :----: |:-------: | :----: | :----: |
 | DLA-34(paper)  | 1088x608 |  74.9  |  72.8  |  1074  |    -   |    -   |   25.9   |    -   |   -    |
-| DLA-34         | 1088x608 |  74.8  |  74.4  |  930   |  7038  |  37994 |    -     |[下载链接](https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_1088x608.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.1/configs/mot/fairmot/fairmot_dla34_30e_1088x608.yml) |
+| DLA-34         | 1088x608 |  75.0  |  74.7  |  919   |  7934  |  36747 |    -     |[下载链接](https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_1088x608.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.1/configs/mot/fairmot/fairmot_dla34_30e_1088x608.yml) |

 **注意:**
- FairMOT使用8个GPU进行训练，每个GPU上batch size为6，训练30个epoch。
+ FairMOT使用2个GPU进行训练，每个GPU上batch size为6，训练30个epoch。

 ## 快速开始

@@ -38,7 +38,7 @@
 使用8GPU通过如下命令一键式启动训练

 ```bash
-python -m paddle.distributed.launch --log_dir=./fairmot_dla34_30e_1088x608/ --gpus 0,1,2,3,4,5,6,7 tools/train.py -c configs/mot/fairmot/fairmot_dla34_30e_1088x608.yml
+python -m paddle.distributed.launch --log_dir=./fairmot_dla34_30e_1088x608/ --gpus 0,1 tools/train.py -c configs/mot/fairmot/fairmot_dla34_30e_1088x608.yml
 ```

 ### 2. 评估

--- a/configs/mot/fairmot/_base_/optimizer_30e.yml
+++ b/configs/mot/fairmot/_base_/optimizer_30e.yml
 epoch: 30

 LearningRate:
-  base_lr: 0.0004
+  base_lr: 0.0001
  schedulers:
  - !PiecewiseDecay
    gamma: 0.1