未验证 提交 43626835 编写于 作者: F Feng Ni 提交者: GitHub

[cherry-pick]update mot kitticars modelzoo (#4085)

上级 ed1016fe
......@@ -118,7 +118,7 @@ If you use a stronger detection model, you can get better results. Each txt is t
| 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/2.2/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/2.2/configs/mot/fairmot/fairmot_dla34_30e_1088x608.yml) |
### FairMOT Results on MOT-16 Test Set
......@@ -126,7 +126,7 @@ If you use a stronger detection model, you can get better results. Each txt is t
| 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/2.2/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/2.2/configs/mot/fairmot/fairmot_dla34_30e_1088x608.yml) |
**Notes:**
FairMOT used 2 GPUs for training and mini-batch size as 6 on each GPU, and trained for 30 epoches.
......@@ -151,7 +151,7 @@ If you use a stronger detection model, you can get better results. Each txt is t
| backbone | input shape | MOTA | FPS | download | config |
| :--------------| :------- | :-----: | :-----: | :------: | :----: |
| DLA-34 | 1088x608 | 67.9 | - |[model](https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_1088x608_kitticars.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.2/configs/mot/kitticars/fairmot_dla34_30e_1088x608_kitticars.yml) |
| DLA-34 | 1088x608 | 53.9 | - |[model](https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_1088x608_kitticars.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.2/configs/mot/kitticars/fairmot_dla34_30e_1088x608_kitticars.yml) |
## Dataset Preparation
......
......@@ -119,14 +119,14 @@ 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/2.2/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/2.2/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/2.2/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/2.2/configs/mot/fairmot/fairmot_dla34_30e_1088x608.yml) |
**注意:**
FairMOT使用2个GPU进行训练,每个GPU上batch size为6,训练30个epoch。
......@@ -151,7 +151,7 @@ wget https://dataset.bj.bcebos.com/mot/det_results_dir.zip
| 骨干网络 | 输入尺寸 | MOTA | FPS | 下载链接 | 配置文件 |
| :--------------| :------- | :-----: | :-----: | :------: | :----: |
| DLA-34 | 1088x608 | 67.9 | - |[下载链接](https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_1088x608_kitticars.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.2/configs/mot/kitticars/fairmot_dla34_30e_1088x608_kitticars.yml) |
| DLA-34 | 1088x608 | 53.9 | - |[下载链接](https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_1088x608_kitticars.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.2/configs/mot/kitticars/fairmot_dla34_30e_1088x608_kitticars.yml) |
## 数据集准备
......
......@@ -15,7 +15,7 @@
| 骨干网络 | 输入尺寸 | MOTA | FPS | 下载链接 | 配置文件 |
| :--------------| :------- | :-----: | :-----: | :------: | :----: |
| DLA-34 | 1088x608 | 67.9 | - |[下载链接](https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_1088x608_kitticars.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.2/configs/mot/kitticars/fairmot_dla34_30e_1088x608_kitticars.yml) |
| DLA-34 | 1088x608 | 53.9 | - |[下载链接](https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_1088x608_kitticars.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.2/configs/mot/kitticars/fairmot_dla34_30e_1088x608_kitticars.yml) |
**注意:**
FairMOT使用2个GPU进行训练,每个GPU上batch size为6,训练30个epoch。
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册