未验证 提交 0eb6f21d 编写于 作者: F Feng Ni 提交者: GitHub

[MOT] add small scale fairmot (#4252)

* add small scale config

* add model zoo

* remove metric type
上级 554ac428
......@@ -119,6 +119,8 @@ If you use a stronger detection model, you can get better results. Each txt is t
| :--------------| :------- | :----: | :----: | :----: | :----: | :----: | :------: | :----: |:-----: |
| DLA-34(paper) | 1088x608 | 83.3 | 81.9 | 544 | 3822 | 14095 | - | - | - |
| 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/develop/configs/mot/fairmot/fairmot_dla34_30e_1088x608.yml) |
| DLA-34 | 864x480 | 80.8 | 81.1 | 561 | 3643 | 16967 | - |[model](https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_864x480.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/mot/fairmot/fairmot_dla34_30e_864x480.yml) |
| DLA-34 | 576x320 | 74.0 | 76.1 | 640 | 4989 | 23034 | - |[model](https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_576x320.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/mot/fairmot/fairmot_dla34_30e_576x320.yml) |
### FairMOT Results on MOT-16 Test Set
......@@ -127,9 +129,11 @@ If you use a stronger detection model, you can get better results. Each txt is t
| :--------------| :------- | :----: | :----: | :----: | :----: | :----: | :------: | :----: |:-----: |
| DLA-34(paper) | 1088x608 | 74.9 | 72.8 | 1074 | - | - | 25.9 | - | - |
| 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/develop/configs/mot/fairmot/fairmot_dla34_30e_1088x608.yml) |
| DLA-34 | 864x480 | 73.0 | 72.6 | 977 | 7578 | 40601 | - |[model](https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_864x480.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/mot/fairmot/fairmot_dla34_30e_864x480.yml) |
| DLA-34 | 576x320 | 69.9 | 70.2 | 1044 | 8869 | 44898 | - |[model](https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_576x320.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/mot/fairmot/fairmot_dla34_30e_576x320.yml) |
**Notes:**
FairMOT used 2 GPUs for training and mini-batch size as 6 on each GPU, and trained for 30 epoches.
FairMOT DLA-34 used 2 GPUs for training and mini-batch size as 6 on each GPU, and trained for 30 epoches.
## Feature Tracking Model
......
......@@ -120,6 +120,8 @@ wget https://dataset.bj.bcebos.com/mot/det_results_dir.zip
| :--------------| :------- | :----: | :----: | :---: | :----: | :---: | :------: | :----: |:----: |
| DLA-34(paper) | 1088x608 | 83.3 | 81.9 | 544 | 3822 | 14095 | - | - | - |
| 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/develop/configs/mot/fairmot/fairmot_dla34_30e_1088x608.yml) |
| DLA-34 | 864x480 | 80.8 | 81.1 | 561 | 3643 | 16967 | - |[下载链接](https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_864x480.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/mot/fairmot/fairmot_dla34_30e_864x480.yml) |
| DLA-34 | 576x320 | 74.0 | 76.1 | 640 | 4989 | 23034 | - |[下载链接](https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_576x320.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/mot/fairmot/fairmot_dla34_30e_576x320.yml) |
### FairMOT在MOT-16 Test Set上结果
......@@ -127,9 +129,11 @@ wget https://dataset.bj.bcebos.com/mot/det_results_dir.zip
| :--------------| :------- | :----: | :----: | :----: | :----: | :----: |:-------: | :----: | :----: |
| DLA-34(paper) | 1088x608 | 74.9 | 72.8 | 1074 | - | - | 25.9 | - | - |
| 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/develop/configs/mot/fairmot/fairmot_dla34_30e_1088x608.yml) |
| DLA-34 | 864x480 | 73.0 | 72.6 | 977 | 7578 | 40601 | - |[下载链接](https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_864x480.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/mot/fairmot/fairmot_dla34_30e_864x480.yml) |
| DLA-34 | 576x320 | 69.9 | 70.2 | 1044 | 8869 | 44898 | - |[下载链接](https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_576x320.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/mot/fairmot/fairmot_dla34_30e_576x320.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。
FairMOT DLA-34均使用2个GPU进行训练,每个GPU上batch size为6,训练30个epoch。
## 特色垂类跟踪模型
......
......@@ -20,6 +20,8 @@ English | [简体中文](README_cn.md)
| :--------------| :------- | :----: | :----: | :----: | :----: | :----: | :------: | :----: |:-----: |
| DLA-34(paper) | 1088x608 | 83.3 | 81.9 | 544 | 3822 | 14095 | - | - | - |
| 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/develop/configs/mot/fairmot/fairmot_dla34_30e_1088x608.yml) |
| DLA-34 | 864x480 | 80.8 | 81.1 | 561 | 3643 | 16967 | - |[model](https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_864x480.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/mot/fairmot/fairmot_dla34_30e_864x480.yml) |
| DLA-34 | 576x320 | 74.0 | 76.1 | 640 | 4989 | 23034 | - |[model](https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_576x320.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/mot/fairmot/fairmot_dla34_30e_576x320.yml) |
### FairMOT Results on MOT-16 Test Set
......@@ -28,9 +30,11 @@ English | [简体中文](README_cn.md)
| :--------------| :------- | :----: | :----: | :----: | :----: | :----: | :------: | :----: |:-----: |
| DLA-34(paper) | 1088x608 | 74.9 | 72.8 | 1074 | - | - | 25.9 | - | - |
| 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/develop/configs/mot/fairmot/fairmot_dla34_30e_1088x608.yml) |
| DLA-34 | 864x480 | 73.0 | 72.6 | 977 | 7578 | 40601 | - |[model](https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_864x480.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/mot/fairmot/fairmot_dla34_30e_864x480.yml) |
| DLA-34 | 576x320 | 69.9 | 70.2 | 1044 | 8869 | 44898 | - |[model](https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_576x320.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/mot/fairmot/fairmot_dla34_30e_576x320.yml) |
**Notes:**
FairMOT used 2 GPUs for training and mini-batch size as 6 on each GPU, and trained for 30 epoches.
FairMOT DLA-34 used 2 GPUs for training and mini-batch size as 6 on each GPU, and trained for 30 epoches.
## Getting Start
......
......@@ -20,6 +20,8 @@
| :--------------| :------- | :----: | :----: | :---: | :----: | :---: | :------: | :----: |:----: |
| DLA-34(paper) | 1088x608 | 83.3 | 81.9 | 544 | 3822 | 14095 | - | - | - |
| 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/develop/configs/mot/fairmot/fairmot_dla34_30e_1088x608.yml) |
| DLA-34 | 864x480 | 80.8 | 81.1 | 561 | 3643 | 16967 | - |[下载链接](https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_864x480.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/mot/fairmot/fairmot_dla34_30e_864x480.yml) |
| DLA-34 | 576x320 | 74.0 | 76.1 | 640 | 4989 | 23034 | - |[下载链接](https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_576x320.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/mot/fairmot/fairmot_dla34_30e_576x320.yml) |
### FairMOT在MOT-16 Test Set上结果
......@@ -27,9 +29,11 @@
| :--------------| :------- | :----: | :----: | :----: | :----: | :----: |:-------: | :----: | :----: |
| DLA-34(paper) | 1088x608 | 74.9 | 72.8 | 1074 | - | - | 25.9 | - | - |
| 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/develop/configs/mot/fairmot/fairmot_dla34_30e_1088x608.yml) |
| DLA-34 | 864x480 | 73.0 | 72.6 | 977 | 7578 | 40601 | - |[下载链接](https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_864x480.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/mot/fairmot/fairmot_dla34_30e_864x480.yml) |
| DLA-34 | 576x320 | 69.9 | 70.2 | 1044 | 8869 | 44898 | - |[下载链接](https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_576x320.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/mot/fairmot/fairmot_dla34_30e_576x320.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。
FairMOT DLA-34均使用2个GPU进行训练,每个GPU上batch size为6,训练30个epoch。
## 快速开始
......
worker_num: 4
TrainReader:
inputs_def:
image_shape: [3, 320, 576]
sample_transforms:
- Decode: {}
- RGBReverse: {}
- AugmentHSV: {}
- LetterBoxResize: {target_size: [320, 576]}
- MOTRandomAffine: {reject_outside: False}
- RandomFlip: {}
- BboxXYXY2XYWH: {}
- NormalizeBox: {}
- NormalizeImage: {mean: [0, 0, 0], std: [1, 1, 1]}
- RGBReverse: {}
- Permute: {}
batch_transforms:
- Gt2FairMOTTarget: {}
batch_size: 6
shuffle: True
drop_last: True
use_shared_memory: True
EvalMOTReader:
sample_transforms:
- Decode: {}
- LetterBoxResize: {target_size: [320, 576]}
- NormalizeImage: {mean: [0, 0, 0], std: [1, 1, 1]}
- Permute: {}
batch_size: 1
TestMOTReader:
inputs_def:
image_shape: [3, 320, 576]
sample_transforms:
- Decode: {}
- LetterBoxResize: {target_size: [320, 576]}
- NormalizeImage: {mean: [0, 0, 0], std: [1, 1, 1]}
- Permute: {}
batch_size: 1
worker_num: 4
TrainReader:
inputs_def:
image_shape: [3, 480, 864]
sample_transforms:
- Decode: {}
- RGBReverse: {}
- AugmentHSV: {}
- LetterBoxResize: {target_size: [480, 864]}
- MOTRandomAffine: {reject_outside: False}
- RandomFlip: {}
- BboxXYXY2XYWH: {}
- NormalizeBox: {}
- NormalizeImage: {mean: [0, 0, 0], std: [1, 1, 1]}
- RGBReverse: {}
- Permute: {}
batch_transforms:
- Gt2FairMOTTarget: {}
batch_size: 6
shuffle: True
drop_last: True
use_shared_memory: True
EvalMOTReader:
sample_transforms:
- Decode: {}
- LetterBoxResize: {target_size: [480, 864]}
- NormalizeImage: {mean: [0, 0, 0], std: [1, 1, 1]}
- Permute: {}
batch_size: 1
TestMOTReader:
inputs_def:
image_shape: [3, 480, 864]
sample_transforms:
- Decode: {}
- LetterBoxResize: {target_size: [480, 864]}
- NormalizeImage: {mean: [0, 0, 0], std: [1, 1, 1]}
- Permute: {}
batch_size: 1
......@@ -6,5 +6,4 @@ _BASE_: [
'_base_/fairmot_reader_1088x608.yml',
]
metric: MOT
weights: output/fairmot_dla34_30e_1088x608/model_final
_BASE_: [
'../../datasets/mot.yml',
'../../runtime.yml',
'_base_/optimizer_30e.yml',
'_base_/fairmot_dla34.yml',
'_base_/fairmot_reader_576x320.yml',
]
weights: output/fairmot_dla34_30e_576x320/model_final
_BASE_: [
'../../datasets/mot.yml',
'../../runtime.yml',
'_base_/optimizer_30e.yml',
'_base_/fairmot_dla34.yml',
'_base_/fairmot_reader_864x480.yml',
]
weights: output/fairmot_dla34_30e_864x480/model_final
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