From d214d9ece7a7d435df405febb8ad8fad7c4e9efa Mon Sep 17 00:00:00 2001
From: George Ni <nemonameless@qq.com>
Date: Sat, 19 Jun 2021 23:52:07 +0800
Subject: [PATCH] [MOT] add jde fairmot deploy doc  (#3421)

---
 configs/mot/README.md            | 15 +++++++++++++++
 configs/mot/README_cn.md         | 14 ++++++++++++++
 configs/mot/fairmot/README.md    | 15 +++++++++++++++
 configs/mot/fairmot/README_cn.md | 14 ++++++++++++++
 configs/mot/jde/README.md        | 15 +++++++++++++++
 configs/mot/jde/README_cn.md     | 14 ++++++++++++++
 6 files changed, 87 insertions(+)

diff --git a/configs/mot/README.md b/configs/mot/README.md
index 439d085e0..e3f6ff2f3 100644
--- a/configs/mot/README.md
+++ b/configs/mot/README.md
@@ -246,6 +246,21 @@ CUDA_VISIBLE_DEVICES=0 python tools/infer_mot.py -c configs/mot/fairmot/fairmot_
  Please make sure that [ffmpeg](https://ffmpeg.org/ffmpeg.html) is installed first, on Linux(Ubuntu) platform you can directly install it by the following command:`apt-get update && apt-get install -y ffmpeg`.
 
 
+### 4. Export model
+
+```bash
+CUDA_VISIBLE_DEVICES=0 python tools/export_model.py -c configs/mot/fairmot/fairmot_dla34_30e_1088x608.yml -o weights=https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_1088x608.pdparams
+```
+
+### 5. Using exported model for python inference
+
+```bash
+python deploy/python/mot_infer.py --model_dir=output_inference/fairmot_dla34_30e_1088x608 --video_file={your video name}.mp4 --device=GPU --use_gpu=True --save_results
+```
+**Notes:** 
+The tracking model is used to predict the video, and does not support the prediction of a single image. The visualization video of the tracking results is saved by default. You can add `--save_results` to save the txt result file, or `--save_images` to save the visualization images.
+
+
 ## Citations
 ```
 @inproceedings{Wojke2017simple,
diff --git a/configs/mot/README_cn.md b/configs/mot/README_cn.md
index 3bc8ea799..1fe4e4d87 100644
--- a/configs/mot/README_cn.md
+++ b/configs/mot/README_cn.md
@@ -244,6 +244,20 @@ CUDA_VISIBLE_DEVICES=0 python tools/infer_mot.py -c configs/mot/fairmot/fairmot_
 **注意:**
  请先确保已经安装了[ffmpeg](https://ffmpeg.org/ffmpeg.html), Linux(Ubuntu)平台可以直接用以下命令安装：`apt-get update && apt-get install -y ffmpeg`。
 
+### 4. 导出预测模型
+
+```bash
+CUDA_VISIBLE_DEVICES=0 python tools/export_model.py -c configs/mot/fairmot/fairmot_dla34_30e_1088x608.yml -o weights=https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_1088x608.pdparams
+```
+
+### 5. 用导出的模型基于Python去预测
+
+```bash
+python deploy/python/mot_infer.py --model_dir=output_inference/fairmot_dla34_30e_1088x608 --video_file={your video name}.mp4 --device=GPU --use_gpu=True --save_results
+```
+**注意:** 
+ 跟踪模型是对视频进行预测，不支持单张图的预测，默认保存跟踪结果可视化后的视频，可添加`--save_results`表示保存跟踪结果的txt文件，或`--save_images`表示保存跟踪结果可视化图片。
+
 ## 引用
 ```
 @inproceedings{Wojke2017simple,
diff --git a/configs/mot/fairmot/README.md b/configs/mot/fairmot/README.md
index 30d93584e..ac4e5dcde 100644
--- a/configs/mot/fairmot/README.md
+++ b/configs/mot/fairmot/README.md
@@ -77,6 +77,21 @@ CUDA_VISIBLE_DEVICES=0 python tools/infer_mot.py -c configs/mot/fairmot/fairmot_
  Please make sure that [ffmpeg](https://ffmpeg.org/ffmpeg.html) is installed first, on Linux(Ubuntu) platform you can directly install it by the following command:`apt-get update && apt-get install -y ffmpeg`.
 
 
+### 4. Export model
+
+```bash
+CUDA_VISIBLE_DEVICES=0 python tools/export_model.py -c configs/mot/fairmot/fairmot_dla34_30e_1088x608.yml -o weights=https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_1088x608.pdparams
+```
+
+### 5. Using exported model for python inference
+
+```bash
+python deploy/python/mot_infer.py --model_dir=output_inference/fairmot_dla34_30e_1088x608 --video_file={your video name}.mp4 --device=GPU --use_gpu=True --save_results
+```
+**Notes:** 
+The tracking model is used to predict the video, and does not support the prediction of a single image. The visualization video of the tracking results is saved by default. You can add `--save_results` to save the txt result file, or `--save_images` to save the visualization images.
+
+
 ## Citations
 ```
 @article{zhang2020fair,
diff --git a/configs/mot/fairmot/README_cn.md b/configs/mot/fairmot/README_cn.md
index bb2e92bfe..95035c702 100644
--- a/configs/mot/fairmot/README_cn.md
+++ b/configs/mot/fairmot/README_cn.md
@@ -75,6 +75,20 @@ CUDA_VISIBLE_DEVICES=0 python tools/infer_mot.py -c configs/mot/fairmot/fairmot_
 **注意:**
  请先确保已经安装了[ffmpeg](https://ffmpeg.org/ffmpeg.html), Linux(Ubuntu)平台可以直接用以下命令安装：`apt-get update && apt-get install -y ffmpeg`。
 
+### 4. 导出预测模型
+
+```bash
+CUDA_VISIBLE_DEVICES=0 python tools/export_model.py -c configs/mot/fairmot/fairmot_dla34_30e_1088x608.yml -o weights=https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_1088x608.pdparams
+```
+
+### 5. 用导出的模型基于Python去预测
+
+```bash
+python deploy/python/mot_infer.py --model_dir=output_inference/fairmot_dla34_30e_1088x608 --video_file={your video name}.mp4 --device=GPU --use_gpu=True --save_results
+```
+**注意:** 
+ 跟踪模型是对视频进行预测，不支持单张图的预测，默认保存跟踪结果可视化后的视频，可添加`--save_results`表示保存跟踪结果的txt文件，或`--save_images`表示保存跟踪结果可视化图片。
+
 ## 引用
 ```
 @article{zhang2020fair,
diff --git a/configs/mot/jde/README.md b/configs/mot/jde/README.md
index 0992c65c7..a4b1a8be5 100644
--- a/configs/mot/jde/README.md
+++ b/configs/mot/jde/README.md
@@ -83,6 +83,21 @@ CUDA_VISIBLE_DEVICES=0 python tools/infer_mot.py -c configs/mot/jde/jde_darknet5
  Please make sure that [ffmpeg](https://ffmpeg.org/ffmpeg.html) is installed first, on Linux(Ubuntu) platform you can directly install it by the following command:`apt-get update && apt-get install -y ffmpeg`.
 
 
+### 4. Export model
+
+```bash
+CUDA_VISIBLE_DEVICES=0 python tools/export_model.py -c configs/mot/jde/jde_darknet53_30e_1088x608.yml -o weights=https://paddledet.bj.bcebos.com/models/mot/jde_darknet53_30e_1088x608.pdparams
+```
+
+### 5. Using exported model for python inference
+
+```bash
+python deploy/python/mot_infer.py --model_dir=output_inference/jde_darknet53_30e_1088x608 --video_file={your video name}.mp4 --device=GPU --use_gpu=True --save_results
+```
+**Notes:** 
+The tracking model is used to predict the video, and does not support the prediction of a single image. The visualization video of the tracking results is saved by default. You can add `--save_results` to save the txt result file, or `--save_images` to save the visualization images.
+
+
 ## Citations
 ```
 @article{wang2019towards,
diff --git a/configs/mot/jde/README_cn.md b/configs/mot/jde/README_cn.md
index bbf11580c..ff5cc1b8c 100644
--- a/configs/mot/jde/README_cn.md
+++ b/configs/mot/jde/README_cn.md
@@ -84,6 +84,20 @@ CUDA_VISIBLE_DEVICES=0 python tools/infer_mot.py -c configs/mot/jde/jde_darknet5
 **注意:**
  请先确保已经安装了[ffmpeg](https://ffmpeg.org/ffmpeg.html), Linux(Ubuntu)平台可以直接用以下命令安装：`apt-get update && apt-get install -y ffmpeg`。
 
+### 4. 导出预测模型
+
+```bash
+CUDA_VISIBLE_DEVICES=0 python tools/export_model.py -c configs/mot/jde/jde_darknet53_30e_1088x608.yml -o weights=https://paddledet.bj.bcebos.com/models/mot/jde_darknet53_30e_1088x608.pdparams
+```
+
+### 5. 用导出的模型基于Python去预测
+
+```bash
+python deploy/python/mot_infer.py --model_dir=output_inference/jde_darknet53_30e_1088x608 --video_file={your video name}.mp4 --device=GPU --use_gpu=True --save_results
+```
+**注意:** 
+ 跟踪模型是对视频进行预测，不支持单张图的预测，默认保存跟踪结果可视化后的视频，可添加`--save_results`表示保存跟踪结果的txt文件，或`--save_images`表示保存跟踪结果可视化图片。。
+
 ## 引用
 ```
 @article{wang2019towards,
-- 
GitLab