diff --git a/configs/mot/bytetrack/README_cn.md b/configs/mot/bytetrack/README_cn.md
index 56f72e0b168f64ffb6646c754de5272ab6a40c09..7620366da964987db90483cd920445c54c307068 100644
--- a/configs/mot/bytetrack/README_cn.md
+++ b/configs/mot/bytetrack/README_cn.md
@@ -17,13 +17,13 @@
 
 |  检测训练数据集      |  检测器     | 输入尺度  |  ReID  |  检测mAP  |  MOTA  |  IDF1  |  FPS | 配置文件 |
 | :--------         | :-----      | :----:  | :----:|:------:  | :----: |:-----: |:----:|:----:   |
-| MOT-17 half train | YOLOv3      | 608x608 | -     |  42.7    |  49.5  |  54.8  |   -    |[配置文件](./bytetrack_yolov3.yml) |
-| MOT-17 half train | PPYOLOe     | 640x640 | -     |  52.9    |  50.4  |  59.7  |   -    |[配置文件](./bytetrack_ppyoloe.yml) |
-| MOT-17 half train | PPYOLOe     | 640x640 |PPLCNet|  52.9    |  51.7  |  58.8  |   -    |[配置文件](./bytetrack_ppyoloe_pplcnet.yml) |
+| MOT-17 half train | YOLOv3      | 608x608 | -     |  42.7    |  49.3  |  55.5  |   -    |[配置文件](./bytetrack_yolov3.yml) |
+| MOT-17 half train | PPYOLOe     | 640x640 | -     |  52.7    |  50.4  |  59.7  |   -    |[配置文件](./bytetrack_ppyoloe.yml) |
+| MOT-17 half train | PPYOLOe     | 640x640 |PPLCNet|  52.7    |  51.7  |  58.8  |   -    |[配置文件](./bytetrack_ppyoloe_pplcnet.yml) |
 | mix_det           | YOLOX-x     | 800x1440|   -   |  61.9    |  77.3  |  71.6  |   -    |[配置文件](./bytetrack_yolox.yml) |
 
 **注意:**
-- 模型权重下载链接在配置文件中的```det_weights```和```reid_weights```，运行验证的命令即可自动下载。
+- 模型权重下载链接在配置文件中的```det_weights```和```reid_weights```，运行```tools/eval_mot.py```评估的命令即可自动下载。
 - **MOT17-half train**是MOT17的train序列(共7个)每个视频的前一半帧的图片和标注组成的数据集，而为了验证精度可以都用**MOT17-half val**数据集去评估，它是每个视频的后一半帧组成的，数据集可以从[此链接](https://dataset.bj.bcebos.com/mot/MOT17.zip)下载，并解压放在`dataset/mot/`文件夹下。
 - **mix_det**是MOT17、crowdhuman、Cityscapes、ETHZ组成的联合数据集，数据集整理的格式和目录可以参考[此链接](https://github.com/ifzhang/ByteTrack#data-preparation)，最终放置于`dataset/mot/`目录下。为了验证精度可以都用**MOT17-half val**数据集去评估。
 - ByteTrack的训练是单独的检测器训练MOT数据集，推理是组装跟踪器去评估MOT指标，单独的检测模型也可以评估检测指标。
@@ -35,13 +35,20 @@
 ### 1. 训练
 通过如下命令一键式启动训练和评估
 ```bash
-python -m paddle.distributed.launch --log_dir=ppyoloe --gpus 0,1,2,3,4,5,6,7 tools/train.py -c configs/mot/bytetrack/detector/ppyoloe_crn_l_36e_640x640_mot17half.yml --eval --amp --fleet
+python -m paddle.distributed.launch --log_dir=ppyoloe --gpus 0,1,2,3,4,5,6,7 tools/train.py -c configs/mot/bytetrack/detector/ppyoloe_crn_l_36e_640x640_mot17half.yml --eval --amp
+# 或者
+python -m paddle.distributed.launch --log_dir=ppyoloe --gpus 0,1,2,3,4,5,6,7 tools/train.py -c configs/mot/bytetrack/detector/yolox_x_24e_800x1440_mix_det.yml --eval --amp
 ```
 
+**注意:**
+  - ` --eval`是边训练边验证精度；`--amp`是混合精度训练避免溢出，推荐使用paddlepaddle2.2.2版本。
+
 ### 2. 评估
 #### 2.1 评估检测效果
 ```bash
-CUDA_VISIBLE_DEVICES=0 python tools/eval.py -c configs/mot/bytetrack/detector/ppyoloe_crn_l_36e_640x640_mot17half.yml
+CUDA_VISIBLE_DEVICES=0 python tools/eval.py -c configs/mot/bytetrack/detector/ppyoloe_crn_l_36e_640x640_mot17half.yml -o weights=https://bj.bcebos.com/v1/paddledet/models/mot/ppyoloe_crn_l_36e_640x640_mot17half.pdparams
+# 或者
+CUDA_VISIBLE_DEVICES=0 python tools/eval.py -c configs/mot/bytetrack/detector/yolox_x_24e_800x1440_mix_det.yml -o weights=https://bj.bcebos.com/v1/paddledet/models/mot/yolox_x_24e_800x1440_mix_det.pdparams
 ```
 
 **注意:**
@@ -54,30 +61,41 @@ CUDA_VISIBLE_DEVICES=0 python tools/eval_mot.py -c configs/mot/bytetrack/bytetra
 CUDA_VISIBLE_DEVICES=0 python tools/eval_mot.py -c configs/mot/bytetrack/bytetrack_ppyoloe.yml --scaled=True
 # 或者
 CUDA_VISIBLE_DEVICES=0 python tools/eval_mot.py -c configs/mot/bytetrack/bytetrack_ppyoloe_pplcnet.yml --scaled=True
+# 或者
+CUDA_VISIBLE_DEVICES=0 python tools/eval_mot.py -c configs/mot/bytetrack/bytetrack_yolox.yml --scaled=True
 ```
 **注意:**
  - `--scaled`表示在模型输出结果的坐标是否已经是缩放回原图的，如果使用的检测模型是JDE YOLOv3则为False，如果使用通用检测模型则为True, 默认值是False。
- - 跟踪结果会存于`{output_dir}/mot_results/`中，里面每个视频序列对应一个txt，每个txt文件每行信息是`frame,id,x1,y1,w,h,score,-1,-1,-1`, 此外`{output_dir}`可通过`--output_dir`设置。
+ - 跟踪结果会存于`{output_dir}/mot_results/`中，里面每个视频序列对应一个txt，每个txt文件每行信息是`frame,id,x1,y1,w,h,score,-1,-1,-1`, 此外`{output_dir}`可通过`--output_dir`设置，默认文件夹名为`output`。
 
 ### 3. 预测
 
 使用单个GPU通过如下命令预测一个视频，并保存为视频
 
 ```bash
-CUDA_VISIBLE_DEVICES=0 python tools/infer_mot.py -c configs/mot/bytetrack/bytetrack_ppyoloe.yml --video_file={your video name}.mp4 --scaled=True --save_videos
+# 下载demo视频
+wget https://bj.bcebos.com/v1/paddledet/data/mot/demo/mot17_demo.mp4
+
+# 使用PPYOLOe行人检测模型
+CUDA_VISIBLE_DEVICES=0 python tools/infer_mot.py -c configs/mot/bytetrack/bytetrack_ppyoloe.yml --video_file=mot17_demo.mp4 --scaled=True --save_videos
+# 或者使用YOLOX行人检测模型
+CUDA_VISIBLE_DEVICES=0 python tools/infer_mot.py -c configs/mot/bytetrack/bytetrack_yolox.yml --video_file=mot17_demo.mp4 --scaled=True --save_videos
 ```
 
 **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`。
  - `--scaled`表示在模型输出结果的坐标是否已经是缩放回原图的，如果使用的检测模型是JDE的YOLOv3则为False，如果使用通用检测模型则为True。
+ - `--save_videos`表示保存可视化视频，同时会保存可视化的图片在`{output_dir}/mot_outputs/`中，`{output_dir}`可通过`--output_dir`设置，默认文件夹名为`output`。
 
 
 ### 4. 导出预测模型
 
 Step 1：导出检测模型
 ```bash
-# 导出PPYOLe行人检测模型
+# 导出PPYOLOe行人检测模型
 CUDA_VISIBLE_DEVICES=0 python tools/export_model.py -c configs/mot/bytetrack/detector/ppyoloe_crn_l_36e_640x640_mot17half.yml -o weights=https://paddledet.bj.bcebos.com/models/mot/ppyoloe_crn_l_36e_640x640_mot17half.pdparams
+# 或者导出YOLOX行人检测模型
+CUDA_VISIBLE_DEVICES=0 python tools/export_model.py -c configs/mot/bytetrack/detector/yolox_x_24e_800x1440_mix_det.yml -o weights=https://paddledet.bj.bcebos.com/models/mot/yolox_x_24e_800x1440_mix_det.pdparams
 ```
 
 Step 2：导出ReID模型(可选步骤，默认不需要)
@@ -89,12 +107,14 @@ CUDA_VISIBLE_DEVICES=0 python tools/export_model.py -c configs/mot/deepsort/reid
 ### 4. 用导出的模型基于Python去预测
 
 ```bash
-python deploy/pptracking/python/mot_sde_infer.py --model_dir=output_inference/ppyoloe_crn_l_36e_640x640_mot17half/ --tracker_config=deploy/pptracking/python/tracker_config.yml --video_file={your video name}.mp4 --device=GPU --scaled=True --save_mot_txts
+python deploy/pptracking/python/mot_sde_infer.py --model_dir=output_inference/ppyoloe_crn_l_36e_640x640_mot17half/ --tracker_config=deploy/pptracking/python/tracker_config.yml --video_file=mot17_demo.mp4 --device=GPU --save_mot_txts
+# 或者
+python deploy/pptracking/python/mot_sde_infer.py --model_dir=output_inference/yolox_x_24e_800x1440_mix_det/ --tracker_config=deploy/pptracking/python/tracker_config.yml --video_file=mot17_demo.mp4 --device=GPU --save_mot_txts
 ```
+
 **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_mot_txts`(对每个视频保存一个txt)或`--save_mot_txt_per_img`(对每张图片保存一个txt)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。
  - 跟踪结果txt文件每行信息是`frame,id,x1,y1,w,h,score,-1,-1,-1`。
- - `--scaled`表示在模型输出结果的坐标是否已经是缩放回原图的，如果使用的检测模型是JDE的YOLOv3则为False，如果使用通用检测模型则为True。
 
 
 ## 引用
diff --git a/configs/mot/bytetrack/_base_/mix_det.yml b/configs/mot/bytetrack/_base_/mix_det.yml
index 157866824d72596c96014df278f3044c8430f04e..fbe19bdaa29246919189d5d93a3ea01e3734b52c 100644
--- a/configs/mot/bytetrack/_base_/mix_det.yml
+++ b/configs/mot/bytetrack/_base_/mix_det.yml
@@ -11,7 +11,7 @@ TrainDataset:
 
 EvalDataset:
   !COCODataSet
-    image_dir: train
+    image_dir: images/train
     anno_path: annotations/val_half.json
     dataset_dir: dataset/mot/MOT17
 
diff --git a/configs/mot/bytetrack/detector/README_cn.md b/configs/mot/bytetrack/detector/README_cn.md
index 8b47596a716cd2b398c18171245d01e09e415bc1..dcf44ee3ad0429593225c70578872d89cfe7a46c 100644
--- a/configs/mot/bytetrack/detector/README_cn.md
+++ b/configs/mot/bytetrack/detector/README_cn.md
@@ -30,7 +30,7 @@ job_name=ppyoloe_crn_l_36e_640x640_mot17half
 config=configs/mot/bytetrack/detector/${job_name}.yml
 log_dir=log_dir/${job_name}
 # 1. training
-python -m paddle.distributed.launch --log_dir=${log_dir} --gpus 0,1,2,3,4,5,6,7 tools/train.py -c ${config} --eval --amp --fleet
+python -m paddle.distributed.launch --log_dir=${log_dir} --gpus 0,1,2,3,4,5,6,7 tools/train.py -c ${config} --eval --amp
 # 2. evaluation
 CUDA_VISIBLE_DEVICES=0 python tools/eval.py -c ${config} -o weights=https://paddledet.bj.bcebos.com/models/mot/${job_name}.pdparams
 ```
diff --git a/configs/mot/deepsort/README_cn.md b/configs/mot/deepsort/README_cn.md
index 8a957d7fad61624bd70f9670182f3d2ad15e5992..3cb88327980b5013bffb715855e3066fe332b42c 100644
--- a/configs/mot/deepsort/README_cn.md
+++ b/configs/mot/deepsort/README_cn.md
@@ -18,18 +18,18 @@
 
 |  骨干网络  |  输入尺寸  |  MOTA  |  IDF1  |  IDS |   FP   |   FN  |  FPS | 检测结果或模型 | ReID模型 |配置文件 |
 | :---------| :------- | :----: | :----: | :--: | :----: | :---: | :---: | :-----:| :-----: | :-----: |
-| ResNet-101 | 1088x608 |  72.2  |  60.5  | 998  |  8054  | 21644 |  - | [检测结果](https://dataset.bj.bcebos.com/mot/det_results_dir.zip) |[ReID模型](https://paddledet.bj.bcebos.com/models/mot/deepsort/deepsort_pcb_pyramid_r101.pdparams)|[配置文件](./reid/deepsort_pcb_pyramid_r101.yml) |
+| ResNet-101 | 1088x608 |  72.2  |  60.5  | 998  |  8054  | 21644 |  - | [检测结果](https://bj.bcebos.com/v1/paddledet/data/mot/det_results_dir.zip) |[ReID模型](https://paddledet.bj.bcebos.com/models/mot/deepsort/deepsort_pcb_pyramid_r101.pdparams)|[配置文件](./reid/deepsort_pcb_pyramid_r101.yml) |
 | ResNet-101 | 1088x608 |  68.3  |  56.5  | 1722 |  17337 | 15890 |  - | [检测模型](https://paddledet.bj.bcebos.com/models/mot/deepsort/jde_yolov3_darknet53_30e_1088x608_mix.pdparams) |[ReID模型](https://paddledet.bj.bcebos.com/models/mot/deepsort/deepsort_pcb_pyramid_r101.pdparams)|[配置文件](./deepsort_jde_yolov3_pcb_pyramid.yml) |
-| PPLCNet    | 1088x608 |  72.2  |  59.5  | 1087  |  8034  | 21481 |  - | [检测结果](https://dataset.bj.bcebos.com/mot/det_results_dir.zip) |[ReID模型](https://paddledet.bj.bcebos.com/models/mot/deepsort/deepsort_pplcnet.pdparams)|[配置文件](./reid/deepsort_pplcnet.yml) |
+| PPLCNet    | 1088x608 |  72.2  |  59.5  | 1087  |  8034  | 21481 |  - | [检测结果](https://bj.bcebos.com/v1/paddledet/data/mot/det_results_dir.zip) |[ReID模型](https://paddledet.bj.bcebos.com/models/mot/deepsort/deepsort_pplcnet.pdparams)|[配置文件](./reid/deepsort_pplcnet.yml) |
 | PPLCNet    | 1088x608 |  68.1  |  53.6  | 1979 |  17446 | 15766 |  - | [检测模型](https://paddledet.bj.bcebos.com/models/mot/deepsort/jde_yolov3_darknet53_30e_1088x608_mix.pdparams) |[ReID模型](https://paddledet.bj.bcebos.com/models/mot/deepsort/deepsort_pplcnet.pdparams)|[配置文件](./deepsort_jde_yolov3_pplcnet.yml) |
 
 ### DeepSORT在MOT-16 Test Set上结果
 
 |  骨干网络  |  输入尺寸  |  MOTA  |  IDF1  |  IDS |   FP   |   FN  |  FPS | 检测结果或模型 | ReID模型 |配置文件 |
 | :---------| :------- | :----: | :----: | :--: | :----: | :---: | :---: | :-----: | :-----: |:-----: |
-| ResNet-101 | 1088x608 |  64.1  |  53.0  | 1024  |  12457  | 51919 |  - | [检测结果](https://dataset.bj.bcebos.com/mot/det_results_dir.zip) | [ReID模型](https://paddledet.bj.bcebos.com/models/mot/deepsort/deepsort_pcb_pyramid_r101.pdparams)|[配置文件](./reid/deepsort_pcb_pyramid_r101.yml) |
+| ResNet-101 | 1088x608 |  64.1  |  53.0  | 1024  |  12457  | 51919 |  - | [检测结果](https://bj.bcebos.com/v1/paddledet/data/mot/det_results_dir.zip) | [ReID模型](https://paddledet.bj.bcebos.com/models/mot/deepsort/deepsort_pcb_pyramid_r101.pdparams)|[配置文件](./reid/deepsort_pcb_pyramid_r101.yml) |
 | ResNet-101 | 1088x608 |  61.2  |  48.5  | 1799  |  25796  | 43232 |  - | [检测模型](https://paddledet.bj.bcebos.com/models/mot/deepsort/jde_yolov3_darknet53_30e_1088x608_mix.pdparams)  |[ReID模型](https://paddledet.bj.bcebos.com/models/mot/deepsort/deepsort_pcb_pyramid_r101.pdparams)|[配置文件](./deepsort_jde_yolov3_pcb_pyramid.yml) |
-| PPLCNet    | 1088x608 |  64.0  |  51.3  | 1208  |  12697  | 51784 |  - | [检测结果](https://dataset.bj.bcebos.com/mot/det_results_dir.zip) |[ReID模型](https://paddledet.bj.bcebos.com/models/mot/deepsort/deepsort_pplcnet.pdparams)|[配置文件](./reid/deepsort_pplcnet.yml) |
+| PPLCNet    | 1088x608 |  64.0  |  51.3  | 1208  |  12697  | 51784 |  - | [检测结果](https://bj.bcebos.com/v1/paddledet/data/mot/det_results_dir.zip) |[ReID模型](https://paddledet.bj.bcebos.com/models/mot/deepsort/deepsort_pplcnet.pdparams)|[配置文件](./reid/deepsort_pplcnet.yml) |
 | PPLCNet    | 1088x608 |  61.1  |  48.8  | 2010 |  25401 | 43432 |  - | [检测模型](https://paddledet.bj.bcebos.com/models/mot/deepsort/jde_yolov3_darknet53_30e_1088x608_mix.pdparams) |[ReID模型](https://paddledet.bj.bcebos.com/models/mot/deepsort/deepsort_pplcnet.pdparams)|[配置文件](./deepsort_jde_yolov3_pplcnet.yml) |
 
 
@@ -41,8 +41,8 @@
 | MIX               | JDE YOLOv3 | PPLCNet     |  -       |  66.3  |  62.1  |   -    |[配置文件](./deepsort_jde_yolov3_pplcnet.yml) |
 | MOT-17 half train | YOLOv3     | PPLCNet     |  42.7    |  50.2  |  52.4  |   -    |[配置文件](./deepsort_yolov3_pplcnet.yml) |
 | MOT-17 half train | PPYOLOv2   | PPLCNet     |  46.8    |  51.8  |  55.8  |   -    |[配置文件](./deepsort_ppyolov2_pplcnet.yml) |
-| MOT-17 half train | PPYOLOe    | PPLCNet     |  52.9    |  56.7  |  60.5  |   -    |[配置文件](./deepsort_ppyoloe_pplcnet.yml) |
-| MOT-17 half train | PPYOLOe    | ResNet-50   |  52.9    |  56.7  |  64.6  |   -    |[配置文件](./deepsort_ppyoloe_resnet.yml) |
+| MOT-17 half train | PPYOLOe    | PPLCNet     |  52.7    |  56.7  |  60.5  |   -    |[配置文件](./deepsort_ppyoloe_pplcnet.yml) |
+| MOT-17 half train | PPYOLOe    | ResNet-50   |  52.7    |  56.7  |  64.6  |   -    |[配置文件](./deepsort_ppyoloe_resnet.yml) |
 
 **注意:**
 模型权重下载链接在配置文件中的```det_weights```和```reid_weights```，运行验证的命令即可自动下载。
@@ -60,7 +60,7 @@ det_results_dir
 ```
 对于MOT16数据集，可以下载PaddleDetection提供的一个经过匹配之后的检测框结果det_results_dir.zip并解压：
 ```
-wget https://dataset.bj.bcebos.com/mot/det_results_dir.zip
+wget https://bj.bcebos.com/v1/paddledet/data/mot/det_results_dir.zip
 ```
 如果使用更强的检测模型，可以取得更好的结果。其中每个txt是每个视频中所有图片的检测结果，每行都描述一个边界框，格式如下：
 ```
@@ -72,7 +72,7 @@ wget https://dataset.bj.bcebos.com/mot/det_results_dir.zip
 - `score`是目标框的得分
 - `class_id`是目标框的类别，如果只有1类则是`0`
 
-- **方式2**：同时加载检测模型和ReID模型，此处选用JDE版本的YOLOv3，具体配置见`configs/mot/deepsort/deepsort_jde_yolov3_pcb_pyramid.yml`。加载其他通用检测模型可参照`configs/mot/deepsort/deepsort_ppyolov2_pplcnet.yml`进行修改。
+- **方式2**：同时加载检测模型和ReID模型，此处选用JDE版本的YOLOv3，具体配置见`configs/mot/deepsort/deepsort_jde_yolov3_pcb_pyramid.yml`。加载其他通用检测模型可参照`configs/mot/deepsort/deepsort_yoloe_pplcnet.yml`进行修改。
 
 ## 快速开始
 
@@ -80,7 +80,7 @@ wget https://dataset.bj.bcebos.com/mot/det_results_dir.zip
 
 #### 1.1 评估检测效果
 ```bash
-CUDA_VISIBLE_DEVICES=0 python tools/eval.py -c configs/mot/deepsort/detector/ppyoloe_crn_l_36e_640x640_mot17half.yml
+CUDA_VISIBLE_DEVICES=0 python tools/eval.py -c configs/mot/deepsort/detector/ppyoloe_crn_l_36e_640x640_mot17half.yml -o weights=https://bj.bcebos.com/v1/paddledet/models/mot/ppyoloe_crn_l_36e_640x640_mot17half.pdparams
 ```
 
 **注意:**
@@ -89,9 +89,12 @@ CUDA_VISIBLE_DEVICES=0 python tools/eval.py -c configs/mot/deepsort/detector/ppy
 #### 1.2 评估跟踪效果
 **方式1**：加载检测结果文件和ReID模型，得到跟踪结果
 ```bash
-CUDA_VISIBLE_DEVICES=0 python tools/eval_mot.py -c configs/mot/deepsort/reid/deepsort_pcb_pyramid_r101.yml --det_results_dir {your detection results}
+# 下载PaddleDetection提供的MOT16数据集检测结果文件并解压，如需自己使用其他检测器生成请参照这个文件里的格式
+wget https://bj.bcebos.com/v1/paddledet/data/mot/det_results_dir.zip
+
+CUDA_VISIBLE_DEVICES=0 python tools/eval_mot.py -c configs/mot/deepsort/reid/deepsort_pcb_pyramid_r101.yml --det_results_dir det_results_dir
 # 或者
-CUDA_VISIBLE_DEVICES=0 python tools/eval_mot.py -c configs/mot/deepsort/reid/deepsort_pplcnet.yml --det_results_dir {your detection results}
+CUDA_VISIBLE_DEVICES=0 python tools/eval_mot.py -c configs/mot/deepsort/reid/deepsort_pplcnet.yml --det_results_dir det_results_dir
 ```
 
 **方式2**：加载行人检测模型和ReID模型，得到跟踪结果
@@ -115,11 +118,14 @@ CUDA_VISIBLE_DEVICES=0 python tools/eval_mot.py -c configs/mot/deepsort/deepsort
 使用单个GPU通过如下命令预测一个视频，并保存为视频
 
 ```bash
+# 下载demo视频
+wget https://bj.bcebos.com/v1/paddledet/data/mot/demo/mot17_demo.mp4
+
 # 加载JDE YOLOv3行人检测模型和PCB Pyramid ReID模型，并保存为视频
-CUDA_VISIBLE_DEVICES=0 python tools/infer_mot.py -c configs/mot/deepsort/deepsort_jde_yolov3_pcb_pyramid.yml --video_file={your video name}.mp4  --save_videos
+CUDA_VISIBLE_DEVICES=0 python tools/infer_mot.py -c configs/mot/deepsort/deepsort_jde_yolov3_pcb_pyramid.yml --video_file=mot17_demo.mp4  --save_videos
 
-# 或者加载PPYOLOv2行人检测模型和PPLCNet ReID模型，并保存为视频
-CUDA_VISIBLE_DEVICES=0 python tools/infer_mot.py -c configs/mot/deepsort/deepsort_ppyolov2_pplcnet.yml --video_file={your video name}.mp4 --scaled=True --save_videos
+# 或者加载PPYOLOE行人检测模型和PPLCNet ReID模型，并保存为视频
+CUDA_VISIBLE_DEVICES=0 python tools/infer_mot.py -c configs/mot/deepsort/deepsort_ppyoloe_pplcnet.yml --video_file=mot17_demo.mp4 --scaled=True --save_videos
 ```
 
 **注意:**
@@ -132,33 +138,34 @@ CUDA_VISIBLE_DEVICES=0 python tools/infer_mot.py -c configs/mot/deepsort/deepsor
 Step 1：导出检测模型
 ```bash
 # 导出JDE YOLOv3行人检测模型
-CUDA_VISIBLE_DEVICES=0 python tools/export_model.py -c configs/mot/deepsort/detector/jde_yolov3_darknet53_30e_1088x608_mix.yml -o weights=https://paddledet.bj.bcebos.com/models/mot/deepsort/jde_yolov3_darknet53_30e_1088x608_mix.pdparams
+CUDA_VISIBLE_DEVICES=0 python3.7 tools/export_model.py -c configs/mot/deepsort/detector/jde_yolov3_darknet53_30e_1088x608_mix.yml -o weights=https://paddledet.bj.bcebos.com/models/mot/deepsort/jde_yolov3_darknet53_30e_1088x608_mix.pdparams
 
-# 或导出PPYOLOv2行人检测模型
-CUDA_VISIBLE_DEVICES=0 python tools/export_model.py -c configs/mot/deepsort/detector/ppyolov2_r50vd_dcn_365e_640x640_mot17half.yml -o weights=https://paddledet.bj.bcebos.com/models/mot/deepsort/ppyolov2_r50vd_dcn_365e_640x640_mot17half.pdparams
+# 或导出PPYOLOE行人检测模型
+CUDA_VISIBLE_DEVICES=0 python tools/export_model.py -c configs/mot/deepsort/detector/ppyoloe_crn_l_36e_640x640_mot17half.yml -o weights=https://paddledet.bj.bcebos.com/models/mot/deepsort/ppyoloe_crn_l_36e_640x640_mot17half.pdparams
 ```
 
 Step 2：导出ReID模型
 ```bash
 # 导出PCB Pyramid ReID模型
 CUDA_VISIBLE_DEVICES=0 python tools/export_model.py -c configs/mot/deepsort/reid/deepsort_pcb_pyramid_r101.yml -o reid_weights=https://paddledet.bj.bcebos.com/models/mot/deepsort/deepsort_pcb_pyramid_r101.pdparams
+
 # 或者导出PPLCNet ReID模型
 CUDA_VISIBLE_DEVICES=0 python tools/export_model.py -c configs/mot/deepsort/reid/deepsort_pplcnet.yml -o reid_weights=https://paddledet.bj.bcebos.com/models/mot/deepsort/deepsort_pplcnet.pdparams
+
+# 或者导出ResNet ReID模型
+CUDA_VISIBLE_DEVICES=0 python tools/export_model.py -c configs/mot/deepsort/reid/deepsort_resnet.yml -o reid_weights=https://paddledet.bj.bcebos.com/models/mot/deepsort/deepsort_resnet.pdparams
 ```
 
 ### 4. 用导出的模型基于Python去预测
 
 ```bash
-# 用导出JDE YOLOv3行人检测模型和PCB Pyramid ReID模型
-python deploy/pptracking/python/mot_sde_infer.py --model_dir=output_inference/jde_yolov3_darknet53_30e_1088x608_mix/ --reid_model_dir=output_inference/deepsort_pcb_pyramid_r101/ --video_file={your video name}.mp4 --device=GPU --save_mot_txts
-
-# 或用导出的PPYOLOv2行人检测模型和PPLCNet ReID模型
-python deploy/pptracking/python/mot_sde_infer.py --model_dir=output_inference/ppyolov2_r50vd_dcn_365e_640x640_mot17half/ --reid_model_dir=output_inference/deepsort_pplcnet/ --video_file={your video name}.mp4 --device=GPU --scaled=True --save_mot_txts
+# 用导出的PPYOLOE行人检测模型和PPLCNet ReID模型
+python3.7 deploy/pptracking/python/mot_sde_infer.py --model_dir=output_inference/ppyoloe_crn_l_36e_640x640_mot17half/ --reid_model_dir=output_inference/deepsort_pplcnet/ --tracker_config=deploy/pptracking/python/tracker_config.yml  --video_file=mot17_demo.mp4 --device=GPU --save_mot_txts --threshold=0.5
 ```
 **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_mot_txts`(对每个视频保存一个txt)或`--save_mot_txt_per_img`(对每张图片保存一个txt)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。
+ - 运行前需要先改动`deploy/pptracking/python/tracker_config.yml`里的tracker为`DeepSORTTracker`。
+ - 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_mot_txts`表示对每个视频保存一个txt，或`--save_images`表示保存跟踪结果可视化图片。
  - 跟踪结果txt文件每行信息是`frame,id,x1,y1,w,h,score,-1,-1,-1`。
- - `--scaled`表示在模型输出结果的坐标是否已经是缩放回原图的，如果使用的检测模型是JDE的YOLOv3则为False，如果使用通用检测模型则为True。
 
 
 ## 适配其他检测器
@@ -184,7 +191,7 @@ CUDA_VISIBLE_DEVICES=0 python tools/eval_mot.py -c configs/mot/deepsort/deepsort
 ```
 #### 2.加载检测模型和ReID模型去推理:
 ```
-CUDA_VISIBLE_DEVICES=0 python tools/infer_mot.py -c configs/mot/deepsort/deepsort_xxx_yyy.yml --video_file={your video name}.mp4 --scaled=True --save_videos
+CUDA_VISIBLE_DEVICES=0 python tools/infer_mot.py -c configs/mot/deepsort/deepsort_xxx_yyy.yml --video_file=mot17_demo.mp4 --scaled=True --save_videos
 ```
 #### 3.导出检测模型和ReID模型:
 ```bash
@@ -195,7 +202,7 @@ CUDA_VISIBLE_DEVICES=0 python tools/export_model.py -c configs/mot/deepsort/reid
 ```
 #### 4.使用导出的检测模型和ReID模型去部署:
 ```
-python deploy/pptracking/python/mot_sde_infer.py --model_dir=output_inference/xxx./ --reid_model_dir=output_inference/deepsort_yyy/ --video_file={your video name}.mp4 --device=GPU --scaled=True --save_mot_txts
+python deploy/pptracking/python/mot_sde_infer.py --model_dir=output_inference/xxx./ --reid_model_dir=output_inference/deepsort_yyy/ --video_file=mot17_demo.mp4 --device=GPU --scaled=True --save_mot_txts
 ```
 **注意:**
  - `--scaled`表示在模型输出结果的坐标是否已经是缩放回原图的，如果使用的检测模型是JDE的YOLOv3则为False，如果使用通用检测模型则为True。
diff --git a/configs/mot/deepsort/deepsort_ppyoloe_pplcnet.yml b/configs/mot/deepsort/deepsort_ppyoloe_pplcnet.yml
index 972a1d16975a587a162ad5354b784dffdd473e60..0af80a7d899f02ac4b66c5191b2616ed1db1aa8e 100644
--- a/configs/mot/deepsort/deepsort_ppyoloe_pplcnet.yml
+++ b/configs/mot/deepsort/deepsort_ppyoloe_pplcnet.yml
@@ -92,7 +92,6 @@ PPYOLOEHead:
   grid_cell_offset: 0.5
   static_assigner_epoch: -1 # 100
   use_varifocal_loss: True
-  eval_input_size: [640, 640]
   loss_weight: {class: 1.0, iou: 2.5, dfl: 0.5}
   static_assigner:
     name: ATSSAssigner
diff --git a/configs/mot/deepsort/deepsort_ppyoloe_resnet.yml b/configs/mot/deepsort/deepsort_ppyoloe_resnet.yml
index cde2cf23cf4ea81ce67f7dbd08b4fe1fc4b77e15..d9692304b055040bb22c49a2f90e05e4e7ba53eb 100644
--- a/configs/mot/deepsort/deepsort_ppyoloe_resnet.yml
+++ b/configs/mot/deepsort/deepsort_ppyoloe_resnet.yml
@@ -91,7 +91,6 @@ PPYOLOEHead:
   grid_cell_offset: 0.5
   static_assigner_epoch: -1 # 100
   use_varifocal_loss: True
-  eval_input_size: [640, 640]
   loss_weight: {class: 1.0, iou: 2.5, dfl: 0.5}
   static_assigner:
     name: ATSSAssigner
diff --git a/configs/mot/deepsort/detector/README_cn.md b/configs/mot/deepsort/detector/README_cn.md
index 1a984b5c358f2c12e77e3d12396bba22bb46793c..6ebe7de7949d1db3d4c4f72db5ad8147f12e1f3d 100644
--- a/configs/mot/deepsort/detector/README_cn.md
+++ b/configs/mot/deepsort/detector/README_cn.md
@@ -26,11 +26,11 @@
 
 通过如下命令一键式启动训练和评估
 ```bash
-job_name=ppyolov2_r50vd_dcn_365e_640x640_mot17half
+job_name=ppyoloe_crn_l_36e_640x640_mot17half
 config=configs/mot/deepsort/detector/${job_name}.yml
 log_dir=log_dir/${job_name}
 # 1. training
-python -m paddle.distributed.launch --log_dir=${log_dir} --gpus 0,1,2,3,4,5,6,7 tools/train.py -c ${config} --eval --amp --fleet
+python -m paddle.distributed.launch --log_dir=${log_dir} --gpus 0,1,2,3,4,5,6,7 tools/train.py -c ${config} --eval --amp
 # 2. evaluation
-CUDA_VISIBLE_DEVICES=0 python tools/eval.py -c ${config} -o weights=https://paddledet.bj.bcebos.com/models/mot/deepsort/${job_name}.pdparams
+CUDA_VISIBLE_DEVICES=0 python tools/eval.py -c ${config} -o weights=https://paddledet.bj.bcebos.com/models/mot/${job_name}.pdparams
 ```
diff --git a/configs/mot/deepsort/detector/ppyoloe_crn_l_36e_640x640_mot17half.yml b/configs/mot/deepsort/detector/ppyoloe_crn_l_36e_640x640_mot17half.yml
index 4852d6b7e21924156826575dcc10a00cfecb5f80..a0501222c9f35d657826fb525e54bd7f4f663ae4 100644
--- a/configs/mot/deepsort/detector/ppyoloe_crn_l_36e_640x640_mot17half.yml
+++ b/configs/mot/deepsort/detector/ppyoloe_crn_l_36e_640x640_mot17half.yml
@@ -6,6 +6,7 @@ weights: output/ppyoloe_crn_l_36e_640x640_mot17half/model_final
 log_iter: 20
 snapshot_epoch: 2
 
+
 # schedule configuration for fine-tuning
 epoch: 36
 LearningRate:
@@ -15,7 +16,7 @@ LearningRate:
       max_epochs: 43
     - !LinearWarmup
       start_factor: 0.001
-      steps: 100
+      epochs: 1
 
 OptimizerBuilder:
   optimizer:
@@ -25,9 +26,11 @@ OptimizerBuilder:
     factor: 0.0005
     type: L2
 
+
 TrainReader:
   batch_size: 8
 
+
 # detector configuration
 architecture: YOLOv3
 norm_type: sync_bn
@@ -62,7 +65,6 @@ PPYOLOEHead:
   grid_cell_offset: 0.5
   static_assigner_epoch: -1 # 100
   use_varifocal_loss: True
-  eval_input_size: [640, 640]
   loss_weight: {class: 1.0, iou: 2.5, dfl: 0.5}
   static_assigner:
     name: ATSSAssigner
diff --git a/deploy/pptracking/python/README.md b/deploy/pptracking/python/README.md
index 46ff59a317ca08b2ef34197f5502f858189a8080..dc70b767bfa8f78c1caa94e4e67cbb9c75afb826 100644
--- a/deploy/pptracking/python/README.md
+++ b/deploy/pptracking/python/README.md
@@ -65,13 +65,12 @@ python deploy/pptracking/python/mot_jde_infer.py --model_dir=output_inference/fa
  - bdd100k车辆跟踪和多类别demo视频可从此链接下载：`wget https://bj.bcebos.com/v1/paddledet/data/mot/demo/bdd100k_demo.mp4`
 
 
+
 ## 2. 对DeepSORT模型的导出和预测
 ### 2.1 导出预测模型
 Step 1：导出检测模型
 ```bash
-# 导出PPYOLOv2行人检测模型
-CUDA_VISIBLE_DEVICES=0 python tools/export_model.py -c configs/mot/deepsort/detector/ppyolov2_r50vd_dcn_365e_640x640_mot17half.yml -o weights=https://paddledet.bj.bcebos.com/models/mot/deepsort/ppyolov2_r50vd_dcn_365e_640x640_mot17half.pdparams
-# 或导出PPYOLOe行人检测模型
+# 导出PPYOLOe行人检测模型
 CUDA_VISIBLE_DEVICES=0 python tools/export_model.py -c configs/mot/deepsort/detector/ppyoloe_crn_l_36e_640x640_mot17half.yml -o weights=https://paddledet.bj.bcebos.com/models/mot/deepsort/ppyoloe_crn_l_36e_640x640_mot17half.pdparams
 ```
 
@@ -88,45 +87,41 @@ CUDA_VISIBLE_DEVICES=0 python tools/export_model.py -c configs/mot/deepsort/reid
 # 下载行人跟踪demo视频：
 wget https://bj.bcebos.com/v1/paddledet/data/mot/demo/mot17_demo.mp4
 
-# 用导出的PPYOLOv2行人检测模型和PPLCNet ReID模型
-python deploy/pptracking/python/mot_sde_infer.py --model_dir=output_inference/ppyolov2_r50vd_dcn_365e_640x640_mot17half/ --reid_model_dir=output_inference/deepsort_pplcnet/ --tracker_config=deploy/pptracking/python/tracker_config.yml --video_file=mot17_demo.mp4 --device=GPU --threshold=0.5 --save_mot_txts --save_images
-# 或用导出的PPYOLOe行人检测模型和PPLCNet ReID模型
-python deploy/pptracking/python/mot_sde_infer.py --model_dir=output_inference/ppyoloe_crn_l_36e_640x640_mot17half/ --reid_model_dir=output_inference/deepsort_pplcnet/ --tracker_config=deploy/pptracking/python/tracker_config.yml --video_file=mot17_demo.mp4 --device=GPU --threshold=0.5 --save_mot_txts --save_images
+# 用导出的PPYOLOE行人检测模型和PPLCNet ReID模型
+python3.7 deploy/pptracking/python/mot_sde_infer.py --model_dir=output_inference/ppyoloe_crn_l_36e_640x640_mot17half/ --reid_model_dir=output_inference/deepsort_pplcnet/ --tracker_config=deploy/pptracking/python/tracker_config.yml  --video_file=mot17_demo.mp4 --device=GPU --save_mot_txts --threshold=0.5
 ```
 
 ### 2.3 用导出的模型基于Python去预测车辆跟踪
 ```bash
-# 下载车辆检测PicoDet导出的模型：
-wget https://paddledet.bj.bcebos.com/models/mot/deepsort/picodet_l_640_aic21mtmct_vehicle.tar
-tar -xvf picodet_l_640_aic21mtmct_vehicle.tar
-# 或者车辆检测PP-YOLOv2导出的模型：
-wget https://paddledet.bj.bcebos.com/models/mot/deepsort/ppyolov2_r50vd_dcn_365e_aic21mtmct_vehicle.tar
-tar -xvf ppyolov2_r50vd_dcn_365e_aic21mtmct_vehicle.tar
+# 下载车辆demo视频
+wget https://bj.bcebos.com/v1/paddledet/data/mot/demo/bdd100k_demo.mp4
+
+# 下载车辆检测PPYOLOE导出的模型：
+wget https://bj.bcebos.com/v1/paddledet/models/pipeline/mot_ppyoloe_l_36e_ppvehicle.zip
+unzip mot_ppyoloe_l_36e_ppvehicle.zip
 
 # 下载车辆ReID导出的模型：
 wget https://paddledet.bj.bcebos.com/models/mot/deepsort/deepsort_pplcnet_vehicle.tar
 tar -xvf deepsort_pplcnet_vehicle.tar
 
-# 用导出的PicoDet车辆检测模型和PPLCNet车辆ReID模型
-python deploy/pptracking/python/mot_sde_infer.py --model_dir=picodet_l_640_aic21mtmct_vehicle/ --reid_model_dir=deepsort_pplcnet_vehicle/ --tracker_config=deploy/pptracking/python/tracker_config.yml --device=GPU --threshold=0.5 --video_file={your video}.mp4 --save_mot_txts --save_images
-
-# 用导出的PP-YOLOv2车辆检测模型和PPLCNet车辆ReID模型
-python deploy/pptracking/python/mot_sde_infer.py --model_dir=ppyolov2_r50vd_dcn_365e_aic21mtmct_vehicle/ --reid_model_dir=deepsort_pplcnet_vehicle/ --tracker_config=deploy/pptracking/python/tracker_config.yml --device=GPU --threshold=0.5 --video_file={your video}.mp4 --save_mot_txts --save_images
+# 用导出的PPYOLOE车辆检测模型和PPLCNet车辆ReID模型
+python deploy/pptracking/python/mot_sde_infer.py --model_dir=mot_ppyoloe_l_36e_ppvehicle/ --reid_model_dir=deepsort_pplcnet_vehicle/ --tracker_config=deploy/pptracking/python/tracker_config.yml --device=GPU --threshold=0.5 --video_file=bdd100k_demo.mp4 --save_mot_txts --save_images
 ```
 
 **注意:**
+ - 运行前需要手动修改`tracker_config.yml`的跟踪器类型为`type: DeepSORTTracker`。
  - 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_mot_txts`(对每个视频保存一个txt)或`--save_images`表示保存跟踪结果可视化图片。
  - 跟踪结果txt文件每行信息是`frame,id,x1,y1,w,h,score,-1,-1,-1`。
  - `--threshold`表示结果可视化的置信度阈值，默认为0.5，低于该阈值的结果会被过滤掉，为了可视化效果更佳，可根据实际情况自行修改。
  - DeepSORT算法不支持多类别跟踪，只支持单类别跟踪，且ReID模型最好是与检测模型同一类别的物体训练过的，比如行人跟踪最好使用行人ReID模型，车辆跟踪最好使用车辆ReID模型。
- - 需要手动修改`tracker_config.yml`的跟踪器类型为`type: DeepSORTTracker`。
+
 
 
 ## 3. 对ByteTrack模型的导出和预测
 ### 3.1 导出预测模型
 ```bash
 # 导出PPYOLOe行人检测模型
-CUDA_VISIBLE_DEVICES=0 python tools/export_model.py -c configs/mot/deepsort/detector/ppyoloe_crn_l_36e_640x640_mot17half.yml -o weights=https://paddledet.bj.bcebos.com/models/mot/deepsort/ppyoloe_crn_l_36e_640x640_mot17half.pdparams
+CUDA_VISIBLE_DEVICES=0 python tools/export_model.py -c configs/mot/bytetrack/detector/ppyoloe_crn_l_36e_640x640_mot17half.yml -o weights=https://paddledet.bj.bcebos.com/models/mot/ppyoloe_crn_l_36e_640x640_mot17half.pdparams
 ```
 
 ### 3.2 用导出的模型基于Python去预测行人跟踪
@@ -135,27 +130,27 @@ CUDA_VISIBLE_DEVICES=0 python tools/export_model.py -c configs/mot/deepsort/dete
 wget https://bj.bcebos.com/v1/paddledet/data/mot/demo/mot17_demo.mp4
 
 # 用导出的PPYOLOe行人检测模型
-python deploy/pptracking/python/mot_sde_infer.py --model_dir=output_inference/ppyoloe_crn_l_36e_640x640_mot17half/ --tracker_config=deploy/pptracking/python/tracker_config.yml --video_file=mot17_demo.mp4 --device=GPU --threshold=0.5 --save_mot_txts --save_images
+python deploy/pptracking/python/mot_sde_infer.py --model_dir=output_inference/ppyoloe_crn_l_36e_640x640_mot17half/ --tracker_config=deploy/pptracking/python/tracker_config.yml --video_file=mot17_demo.mp4 --device=GPU --save_mot_txts
 
 # 用导出的PPYOLOe行人检测模型和PPLCNet ReID模型
 python deploy/pptracking/python/mot_sde_infer.py --model_dir=output_inference/ppyoloe_crn_l_36e_640x640_mot17half/ --reid_model_dir=output_inference/deepsort_pplcnet/ --tracker_config=deploy/pptracking/python/tracker_config.yml --video_file=mot17_demo.mp4 --device=GPU --threshold=0.5 --save_mot_txts --save_images
 ```
 **注意:**
+ - 运行前需要确认`tracker_config.yml`的跟踪器类型为`type: JDETracker`。
  - ByteTrack模型是加载导出的检测器和单独配置的`--tracker_config`文件运行的，为了实时跟踪所以不需要reid模型，`--reid_model_dir`表示reid导出模型的路径，默认为空，加不加具体视效果而定；
  - 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_mot_txts`(对每个视频保存一个txt)或`--save_images`表示保存跟踪结果可视化图片。
  - 跟踪结果txt文件每行信息是`frame,id,x1,y1,w,h,score,-1,-1,-1`。
  - `--threshold`表示结果可视化的置信度阈值，默认为0.5，低于该阈值的结果会被过滤掉，为了可视化效果更佳，可根据实际情况自行修改。
 
 
+
 ## 4. 跨境跟踪模型的导出和预测
 ### 4.1 导出预测模型
 Step 1：下载导出的检测模型
 ```bash
-wget https://paddledet.bj.bcebos.com/models/mot/deepsort/picodet_l_640_aic21mtmct_vehicle.tar
-tar -xvf picodet_l_640_aic21mtmct_vehicle.tar
-# 或者
-wget https://paddledet.bj.bcebos.com/models/mot/deepsort/ppyolov2_r50vd_dcn_365e_aic21mtmct_vehicle.tar
-tar -xvf ppyolov2_r50vd_dcn_365e_aic21mtmct_vehicle.tar
+# 下载车辆检测PPYOLOE导出的模型：
+wget https://bj.bcebos.com/v1/paddledet/models/pipeline/mot_ppyoloe_l_36e_ppvehicle.zip
+unzip mot_ppyoloe_l_36e_ppvehicle.zip
 ```
 Step 2：下载导出的ReID模型
 ```bash
@@ -169,13 +164,10 @@ tar -xvf deepsort_pplcnet_vehicle.tar
 wget https://paddledet.bj.bcebos.com/data/mot/demo/mtmct-demo.tar
 tar -xvf mtmct-demo.tar
 
-# 用导出的PicoDet车辆检测模型和PPLCNet车辆ReID模型
-python deploy/pptracking/python/mot_sde_infer.py --model_dir=picodet_l_640_aic21mtmct_vehicle/ --reid_model_dir=deepsort_pplcnet_vehicle/ --mtmct_dir=mtmct-demo --mtmct_cfg=mtmct_cfg.yml --device=GPU --threshold=0.5 --save_mot_txts --save_images
-
-# 用导出的PP-YOLOv2车辆检测模型和PPLCNet车辆ReID模型
-python deploy/pptracking/python/mot_sde_infer.py --model_dir=ppyolov2_r50vd_dcn_365e_aic21mtmct_vehicle/ --reid_model_dir=deepsort_pplcnet_vehicle/ --mtmct_dir=mtmct-demo --mtmct_cfg=mtmct_cfg.yml --device=GPU --threshold=0.5 --save_mot_txts --save_images
-
+# 用导出的PPYOLOE车辆检测模型和PPLCNet车辆ReID模型
+python deploy/pptracking/python/mot_sde_infer.py --model_dir=mot_ppyoloe_l_36e_ppvehicle/ --reid_model_dir=deepsort_pplcnet_vehicle/ --mtmct_dir=mtmct-demo --mtmct_cfg=mtmct_cfg.yml --device=GPU --threshold=0.5 --save_mot_txts --save_images
 ```
+
 **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_mot_txts`(对每个视频保存一个txt)，或`--save_images`表示保存跟踪结果可视化图片。
  - 跨镜头跟踪结果txt文件每行信息是`camera_id,frame,id,x1,y1,w,h,-1,-1`。
@@ -190,6 +182,7 @@ python deploy/pptracking/python/mot_sde_infer.py --model_dir=ppyolov2_r50vd_dcn_
 | 参数 | 是否必须|含义 |
 |-------|-------|----------|
 | --model_dir | Yes| 上述导出的模型路径 |
+| --reid_model_dir | Option| ReID导出的模型路径 |
 | --image_file | Option | 需要预测的图片 |
 | --image_dir  | Option |  要预测的图片文件夹路径   |
 | --video_file | Option | 需要预测的视频 |
@@ -203,8 +196,10 @@ python deploy/pptracking/python/mot_sde_infer.py --model_dir=ppyolov2_r50vd_dcn_
 | --enable_mkldnn | Option | CPU预测中是否开启MKLDNN加速，默认为False |
 | --cpu_threads | Option| 设置cpu线程数，默认为1 |
 | --trt_calib_mode | Option| TensorRT是否使用校准功能，默认为False。使用TensorRT的int8功能时，需设置为True，使用PaddleSlim量化后的模型时需要设置为False |
-| --do_entrance_counting | Option | 是否统计出入口流量，默认为False |
-| --draw_center_traj | Option | 是否绘制跟踪轨迹，默认为False |
+| --save_mot_txts | Option | 跟踪任务是否保存txt结果文件，默认为False |
+| --save_images | Option | 跟踪任务是否保存视频的可视化图片，默认为False |
+| --do_entrance_counting | Option | 跟踪任务是否统计出入口流量，默认为False |
+| --draw_center_traj | Option | 跟踪任务是否绘制跟踪轨迹，默认为False |
 | --mtmct_dir | Option | 需要进行MTMCT跨境头跟踪预测的图片文件夹路径，默认为None |
 | --mtmct_cfg | Option | 需要进行MTMCT跨境头跟踪预测的配置文件路径，默认为None |
 
diff --git a/deploy/pptracking/python/det_infer.py b/deploy/pptracking/python/det_infer.py
index 4a682093df16c913e443131bacba8e892f3e10c0..c52879453027e099d25cd0388083eb57d1f8aeea 100644
--- a/deploy/pptracking/python/det_infer.py
+++ b/deploy/pptracking/python/det_infer.py
@@ -32,7 +32,7 @@ sys.path.insert(0, parent_path)
 
 from benchmark_utils import PaddleInferBenchmark
 from picodet_postprocess import PicoDetPostProcess
-from preprocess import preprocess, Resize, NormalizeImage, Permute, PadStride, LetterBoxResize, decode_image
+from preprocess import preprocess, Resize, NormalizeImage, Permute, PadStride, LetterBoxResize, Pad, decode_image
 from mot.visualize import visualize_box_mask
 from mot_utils import argsparser, Timer, get_current_memory_mb
 
diff --git a/deploy/pptracking/python/mot_sde_infer.py b/deploy/pptracking/python/mot_sde_infer.py
index da1b3caed2e534d4e91dd9e18c032b30baa70d19..7b5c8852defeea0fc51bd6d45c25490a794011a2 100644
--- a/deploy/pptracking/python/mot_sde_infer.py
+++ b/deploy/pptracking/python/mot_sde_infer.py
@@ -186,7 +186,9 @@ class SDE_Detector(Detector):
 
     def postprocess(self, inputs, result):
         # postprocess output of predictor
-        np_boxes_num = result['boxes_num']
+        keep_idx = result['boxes'][:, 1] > self.threshold
+        result['boxes'] = result['boxes'][keep_idx]
+        np_boxes_num = [len(result['boxes'])]
         if np_boxes_num[0] <= 0:
             print('[WARNNING] No object detected.')
             result = {'boxes': np.zeros([0, 6]), 'boxes_num': [0]}
@@ -520,8 +522,8 @@ class SDE_Detector(Detector):
             # bs=1 in MOT model
             online_tlwhs, online_scores, online_ids = mot_results[0]
 
-            # NOTE: just implement flow statistic for one class
-            if num_classes == 1:
+            # flow statistic for one class, and only for bytetracker
+            if num_classes == 1 and not self.use_deepsort_tracker:
                 result = (frame_id + 1, online_tlwhs[0], online_scores[0],
                           online_ids[0])
                 statistic = flow_statistic(
diff --git a/deploy/pptracking/python/preprocess.py b/deploy/pptracking/python/preprocess.py
index 2df5df9c3c3dc0dcb90b0224bf0d8e022a47903e..427479c814d6b3250921ead6b7b2a07ea6352173 100644
--- a/deploy/pptracking/python/preprocess.py
+++ b/deploy/pptracking/python/preprocess.py
@@ -245,6 +245,34 @@ class LetterBoxResize(object):
         return im, im_info
 
 
+class Pad(object):
+    def __init__(self, size, fill_value=[114.0, 114.0, 114.0]):
+        """
+        Pad image to a specified size.
+        Args:
+            size (list[int]): image target size
+            fill_value (list[float]): rgb value of pad area, default (114.0, 114.0, 114.0)
+        """
+        super(Pad, self).__init__()
+        if isinstance(size, int):
+            size = [size, size]
+        self.size = size
+        self.fill_value = fill_value
+
+    def __call__(self, im, im_info):
+        im_h, im_w = im.shape[:2]
+        h, w = self.size
+        if h == im_h and w == im_w:
+            im = im.astype(np.float32)
+            return im, im_info
+
+        canvas = np.ones((h, w, 3), dtype=np.float32)
+        canvas *= np.array(self.fill_value, dtype=np.float32)
+        canvas[0:im_h, 0:im_w, :] = im.astype(np.float32)
+        im = canvas
+        return im, im_info
+
+
 def preprocess(im, preprocess_ops):
     # process image by preprocess_ops
     im_info = {