Merge branch 'PaddlePaddle:develop' into develop

f67c9b2e · YixinKristy · GitHub · b9554990 · 2cd40bdd · f67c9b2e
23 changed file
--- a/configs/mot/README.md
+++ b/configs/mot/README.md
@@ -47,12 +47,11 @@ PP-Tracking 提供了简洁的GUI可视化界面，教程请参考[PP-Tracking
 ## 安装依赖
 一键安装MOT相关的依赖：
 ```
-pip install lap sklearn motmetrics openpyxl cython_bbox
+pip install lap sklearn motmetrics openpyxl
 或者
 pip install -r requirements.txt
 ```
 **注意：**
- `cython_bbox`在windows上安装：`pip install -e git+https://github.com/samson-wang/cython_bbox.git#egg=cython-bbox`。可参考这个[教程](https://stackoverflow.com/questions/60349980/is-there-a-way-to-install-cython-bbox-for-windows)。
 - 预测需确保已安装[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`。

--- a/configs/mot/README_en.md
+++ b/configs/mot/README_en.md
@@ -49,12 +49,11 @@ PP-Tracking supports GUI predict and deployment. Please refer to this [doc](http
 ## Installation
 Install all the related dependencies for MOT:
 ```
-pip install lap sklearn motmetrics openpyxl cython_bbox
+pip install lap sklearn motmetrics openpyxl
 or
 pip install -r requirements.txt
 ```
 **Notes:**
- Install `cython_bbox` for Windows: `pip install -e git+https://github.com/samson-wang/cython_bbox.git#egg=cython-bbox`. You can refer to this [tutorial](https://stackoverflow.com/questions/60349980/is-there-a-way-to-install-cython-bbox-for-windows).
 - 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`.

--- a/configs/mot/fairmot/README.md
+++ b/configs/mot/fairmot/README.md
@@ -86,7 +86,7 @@ PP-tracking provides an AI studio public project tutorial. Please refer to this
 ### Results on MOT-17 Half Set
 | backbone       | input shape | MOTA | IDF1 |  IDS  |    FP   |   FN   |    FPS    | download | config |
 | :--------------| :------- | :----: | :----: | :----: | :----: | :----: | :------: | :----: |:-----: |
-| DLA-34         | 1088x608 |  69.1  |  72.8  |  299  |  1957  | 14412 |    -     |[model](https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_1088x608_bytetracker.pdparams) | [config](./fairmot_dla34_30e_1088x608.yml) |
+| DLA-34         | 1088x608 |  69.1  |  72.8  |  299  |  1957  | 14412 |    -     |[model](https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_1088x608.pdparams) | [config](./fairmot_dla34_30e_1088x608.yml) |
 | DLA-34 + BYTETracker| 1088x608 |  70.3 |  73.2  |  234  |  2176  | 13598 |    -     |[model](https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_1088x608_bytetracker.pdparams) | [config](./fairmot_dla34_30e_1088x608_bytetracker.yml) |
 **Notes:**

--- a/configs/mot/fairmot/README_cn.md
+++ b/configs/mot/fairmot/README_cn.md
@@ -82,7 +82,7 @@ PP-Tracking 提供了AI Studio公开项目案例，教程请参考[PP-Tracking
 ### 在MOT-17 Half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         | 1088x608 |  69.1  |  72.8  |  299  |  1957  | 14412 |    -     |[下载链接](https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_1088x608_bytetracker.pdparams) | [配置文件](./fairmot_dla34_30e_1088x608.yml) |
+| DLA-34         | 1088x608 |  69.1  |  72.8  |  299  |  1957  | 14412 |    -     |[下载链接](https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_1088x608.pdparams) | [配置文件](./fairmot_dla34_30e_1088x608.yml) |
 | DLA-34 + BYTETracker| 1088x608 |  70.3 |  73.2  |  234  |  2176  | 13598 |    -     |[下载链接](https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_1088x608_bytetracker.pdparams) | [配置文件](./fairmot_dla34_30e_1088x608_bytetracker.yml) |

--- a/configs/mot/fairmot/fairmot_dla34_30e_1088x608_bytetracker.yml
+++ b/configs/mot/fairmot/fairmot_dla34_30e_1088x608_bytetracker.yml
@@ -14,8 +14,18 @@ TrainDataset:
    image_lists: ['mot17.half', 'caltech.all', 'cuhksysu.train', 'prw.train', 'citypersons.train', 'eth.train']
    data_fields: ['image', 'gt_bbox', 'gt_class', 'gt_ide']
+# for MOT evaluation
+# If you want to change the MOT evaluation dataset, please modify 'data_root'
+EvalMOTDataset:
+  !MOTImageFolder
+    dataset_dir: dataset/mot
+    data_root: MOT17/images/half
+    keep_ori_im: False # set True if save visualization images or video, or used in DeepSORT
 JDETracker:
  use_byte: True
  match_thres: 0.8
  conf_thres: 0.4
  low_conf_thres: 0.2
+  min_box_area: 200
+  vertical_ratio: 1.6 # for pedestrian
--- a/configs/mot/pedestrian/README_cn.md
+++ b/configs/mot/pedestrian/README_cn.md
@@ -18,7 +18,7 @@
 | :-------------| :-------- | :------- | :----: | :----: | :----: | :-----: |:------: |
 |  PathTrack    |   DLA-34  | 1088x608 |  44.9 |    59.3   |    -   |[下载链接](https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_1088x608_pathtrack.pdparams) | [配置文件](./fairmot_dla34_30e_1088x608_pathtrack.yml) |
 |  VisDrone     |   DLA-34  | 1088x608 |  49.2 |   63.1 |    -   | [下载链接](https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_1088x608_visdrone_pedestrian.pdparams) | [配置文件](./fairmot_dla34_30e_1088x608_visdrone_pedestrian.yml) |
-|  VisDrone     | HRNetv2-W18| 1088x608 |  40.5 |   54.7 |    -   | [下载链接](https://paddledet.bj.bcebos.com/models/mot/fairmot_hrnetv2_w18_dlafpn_30e_864x480_visdrone_pedestrian.pdparams) | [配置文件](./fairmot_hrnetv2_w18_dlafpn_30e_864x480_visdrone_pedestrian.yml) |
+|  VisDrone     | HRNetv2-W18| 1088x608 |  40.5 |   54.7 |    -   | [下载链接](https://paddledet.bj.bcebos.com/models/mot/fairmot_hrnetv2_w18_dlafpn_30e_1088x608_visdrone_pedestrian.pdparams) | [配置文件](./fairmot_hrnetv2_w18_dlafpn_30e_1088x608_visdrone_pedestrian.yml) |
 |  VisDrone     | HRNetv2-W18| 864x480 |  38.6 |   50.9 |    -   | [下载链接](https://paddledet.bj.bcebos.com/models/mot/fairmot_hrnetv2_w18_dlafpn_30e_864x480_visdrone_pedestrian.pdparams) | [配置文件](./fairmot_hrnetv2_w18_dlafpn_30e_864x480_visdrone_pedestrian.yml) |
 |  VisDrone     | HRNetv2-W18| 576x320 |  30.6 |   47.2 |    -   | [下载链接](https://paddledet.bj.bcebos.com/models/mot/fairmot_hrnetv2_w18_dlafpn_30e_576x320_visdrone_pedestrian.pdparams) | [配置文件](./fairmot_hrnetv2_w18_dlafpn_30e_576x320_visdrone_pedestrian.yml) |

--- a/configs/picodet/README.md
+++ b/configs/picodet/README.md
-English | [简体中文](README_cn.md)
+简体中文 | [English](README_en.md)
 # PP-PicoDet
 ![](../../docs/images/picedet_demo.jpeg)
-## News
+## 最新动态
- Released a new series of PP-PicoDet models: **(2022.03.20)**
+- 发布全新系列PP-PicoDet模型：**（2022.03.20）**
-  - (1) It was used TAL/Task-aligned-Head and optimized PAN, which greatly improved the accuracy;
+  - (1)引入TAL及Task-aligned Head，优化PAN等结构，精度大幅提升；
-  - (2) Moreover optimized CPU prediction speed, and the training speed is greatly improved;
+  - (2)优化CPU端预测速度，同时训练速度大幅提升；
-  - (3) The export model includes post-processing, and the prediction directly outputs the result, without secondary development, and the migration cost is lower.
+  - (3)导出模型将后处理包含在网络中，预测直接输出box结果，无需二次开发，迁移成本更低。
-### Legacy Model
+## 历史版本模型
- Please refer to: [PicoDet 2021.10版本](./legacy_model/)
+- 详情请参考：[PicoDet 2021.10版本](./legacy_model/)
-## Introduction
+## 简介
-We developed a series of lightweight models, named `PP-PicoDet`. Because of the excellent performance, our models are very suitable for deployment on mobile or CPU. For more details, please refer to our [report on arXiv](https://arxiv.org/abs/2111.00902).
+PaddleDetection中提出了全新的轻量级系列模型`PP-PicoDet`，在移动端具有卓越的性能，成为全新SOTA轻量级模型。详细的技术细节可以参考我们的[arXiv技术报告](https://arxiv.org/abs/2111.00902)。
- 🌟 Higher mAP: the **first** object detectors that surpass mAP(0.5:0.95) **30+** within 1M parameters when the input size is 416.
+PP-PicoDet模型有如下特点：
- 🚀 Faster latency: 150FPS on mobile ARM CPU.
- 😊 Deploy friendly: support PaddleLite/MNN/NCNN/OpenVINO and provide C++/Python/Android implementation.
+- 🌟 更高的mAP: 第一个在1M参数量之内`mAP(0.5:0.95)`超越**30+**(输入416像素时)。
- 😍 Advanced algorithm: use the most advanced algorithms and offer innovation, such as ESNet, CSP-PAN, SimOTA with VFL, etc.
+- 🚀 更快的预测速度: 网络预测在ARM CPU下可达150FPS。
+- 😊 部署友好: 支持PaddleLite/MNN/NCNN/OpenVINO等预测库，支持转出ONNX，提供了C++/Python/Android的demo。
+- 😍 先进的算法: 我们在现有SOTA算法中进行了创新, 包括：ESNet, CSP-PAN, SimOTA等等。
 <div align="center">
  <img src="../../docs/images/picodet_map.png" width='600'/>
 </div>
-## Benchmark
+## 基线
-| Model     | Input size | mAP<sup>val<br>0.5:0.95 | mAP<sup>val<br>0.5 | Params<br><sup>(M) | FLOPS<br><sup>(G) | Latency<sup><small>[CPU](#latency)</small><sup><br><sup>(ms) | Latency<sup><small>[Lite](#latency)</small><sup><br><sup>(ms) |  Download  | Config |
+| 模型     | 输入尺寸 | mAP<sup>val<br>0.5:0.95 | mAP<sup>val<br>0.5 | 参数量<br><sup>(M) | FLOPS<br><sup>(G) | 预测时延<sup><small>[NCNN](#latency)</small><sup><br><sup>(ms) | 预测时延<sup><small>[Lite](#latency)</small><sup><br><sup>(ms) |  下载  | 配置文件 |
 | :-------- | :--------: | :---------------------: | :----------------: | :----------------: | :---------------: | :-----------------------------: | :-----------------------------: | :----------------------------------------: | :--------------------------------------- |
 | PicoDet-XS |  320*320   |          23.5           |        36.1       |        0.70        |       0.67        |              10.9ms              |            7.81ms             | [model](https://paddledet.bj.bcebos.com/models/picodet_xs_320_coco_lcnet.pdparams) &#124; [log](https://paddledet.bj.bcebos.com/logs/train_picodet_xs_320_coco_lcnet.log) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/picodet/picodet_xs_320_coco_lcnet.yml) |
 | PicoDet-XS |  416*416   |          26.2           |        39.3        |        0.70        |       1.13        |              15.4ms             |            12.38ms             | [model](https://paddledet.bj.bcebos.com/models/picodet_xs_416_coco_lcnet.pdparams) &#124; [log](https://paddledet.bj.bcebos.com/logs/train_picodet_xs_416_coco_lcnet.log) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/picodet/picodet_xs_416_coco_lcnet.yml) |
 | PicoDet-S |  320*320   |          29.1           |        43.4        |        1.18       |       0.97       |             12.6ms              |            9.56ms             | [model](https://paddledet.bj.bcebos.com/models/picodet_s_320_coco_lcnet.pdparams) &#124; [log](https://paddledet.bj.bcebos.com/logs/train_picodet_s_320_coco_lcnet.log) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/picodet/picodet_s_320_coco_lcnet.yml) |
-| PicoDet-S |  416*416   |          32.5           |        47.6        |        1.18        |       1.65       |              17.2ms              |            15.20             | [model](https://paddledet.bj.bcebos.com/models/picodet_s_416_coco_lcnet.pdparams) &#124; [log](https://paddledet.bj.bcebos.com/logs/train_picodet_s_416_coco_lcnet.log) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/picodet/picodet_s_416_coco_lcnet.yml) |
+| PicoDet-S |  416*416   |          32.5           |        47.6        |        1.18        |       1.65       |              17.2ms              |            15.20ms             | [model](https://paddledet.bj.bcebos.com/models/picodet_s_416_coco_lcnet.pdparams) &#124; [log](https://paddledet.bj.bcebos.com/logs/train_picodet_s_416_coco_lcnet.log) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/picodet/picodet_s_416_coco_lcnet.yml) |
 | PicoDet-M |  320*320   |          34.4           |        50.0        |        3.46        |       2.57       |              14.5ms              |            17.68ms             | [model](https://paddledet.bj.bcebos.com/models/picodet_m_320_coco_lcnet.pdparams) &#124; [log](https://paddledet.bj.bcebos.com/logs/train_picodet_m_320_coco_lcnet.log) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/picodet/picodet_m_320_coco_lcnet.yml) |
 | PicoDet-M |  416*416   |          37.5           |        53.4       |        3.46        |       4.34        |              19.5ms              |            28.39ms            | [model](https://paddledet.bj.bcebos.com/models/picodet_m_416_coco_lcnet.pdparams) &#124; [log](https://paddledet.bj.bcebos.com/logs/train_picodet_m_416_coco_lcnet.log) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/picodet/picodet_m_416_coco_lcnet.yml) |
 | PicoDet-L |  320*320   |          36.1           |        52.0        |        5.80       |       4.20        |              18.3ms             |            25.21ms           | [model](https://paddledet.bj.bcebos.com/models/picodet_l_320_coco_lcnet.pdparams) &#124; [log](https://paddledet.bj.bcebos.com/logs/train_picodet_l_320_coco_lcnet.log) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/picodet/picodet_l_320_coco_lcnet.yml) |
 | PicoDet-L |  416*416   |          39.4           |        55.7        |        5.80        |       7.10       |              22.1ms              |            42.23ms            | [model](https://paddledet.bj.bcebos.com/models/picodet_l_416_coco_lcnet.pdparams) &#124; [log](https://paddledet.bj.bcebos.com/logs/train_picodet_l_416_coco_lcnet.log) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/picodet/picodet_l_416_coco_lcnet.yml) |
-| PicoDet-L |  640*640   |          42.3           |        59.2        |        5.80        |       16.81        |              43.1ms              |            108.1ms          | [model](https://paddledet.bj.bcebos.com/models/picodet_l_640_coco_lcnet.pdparams) &#124; [log](https://paddledet.bj.bcebos.com/logs/train_picodet_l_640_coco_lcnet.log) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/picodet/picodet_l_640_coco_lcnet.yml) |
+| PicoDet-L |  640*640   |          42.6           |        59.2        |        5.80        |       16.81        |              43.1ms              |            108.1ms          | [model](https://paddledet.bj.bcebos.com/models/picodet_l_640_coco_lcnet.pdparams) &#124; [log](https://paddledet.bj.bcebos.com/logs/train_picodet_l_640_coco_lcnet.log) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/picodet/picodet_l_640_coco_lcnet.yml) |
 <details open>
-<summary><b>Table Notes:</b></summary>
+<summary><b>注意事项:</b></summary>
- <a name="latency">Latency:</a> All our models test on `Intel-Xeon-Gold-6148` CPU with MKLDNN by 10 threads and `Qualcomm Snapdragon 865(4xA77+4xA55)` with 4 threads by arm8 and with FP16. In the above table, test CPU latency on Paddle-Inference and testing Mobile latency with `Lite`->[Paddle-Lite](https://github.com/PaddlePaddle/Paddle-Lite).
+- <a name="latency">时延测试：</a> 我们所有的模型都在英特尔至强6148的CPU（MKLDNN 10线程）和`骁龙865(4xA77+4xA55)`的ARM CPU上测试(4线程，FP16预测)。上面表格中标有`CPU`的是使用Paddle Inference库测试，标有`Lite`的是使用[Paddle Lite](https://github.com/PaddlePaddle/Paddle-Lite)进行测试。
- PicoDet is trained on COCO train2017 dataset and evaluated on COCO val2017. And PicoDet used 4 GPUs for training and all checkpoints are trained with default settings and hyperparameters.
+- PicoDet在COCO train2017上训练，并且在COCO val2017上进行验证。使用4卡GPU训练，并且上表所有的预训练模型都是通过发布的默认配置训练得到。
- Benchmark test: When testing the speed benchmark, the post-processing is not included in the exported model, you need to set `-o export.benchmark=True` or manually modify [runtime.yml](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/configs/runtime.yml#L12).
+- Benchmark测试：测试速度benchmark性能时，导出模型后处理不包含在网络中，需要设置`-o export.benchmark=True` 或手动修改[runtime.yml](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/configs/runtime.yml#L12)。
 </details>
-#### Benchmark of Other Models
+#### 其他模型的基线
-| Model     | Input size | mAP<sup>val<br>0.5:0.95 | mAP<sup>val<br>0.5 | Params<br><sup>(M) | FLOPS<br><sup>(G) | Latency<sup><small>[NCNN](#latency)</small><sup><br><sup>(ms) |
+| 模型     | 输入尺寸 | mAP<sup>val<br>0.5:0.95 | mAP<sup>val<br>0.5 | 参数量<br><sup>(M) | FLOPS<br><sup>(G) | 预测时延<sup><small>[NCNN](#latency)</small><sup><br><sup>(ms) |
 | :-------- | :--------: | :---------------------: | :----------------: | :----------------: | :---------------: | :-----------------------------: |
 | YOLOv3-Tiny |  416*416   |          16.6           |        33.1      |        8.86        |       5.62        |             25.42               |
 | YOLOv4-Tiny |  416*416   |          21.7           |        40.2        |        6.06           |       6.96           |             23.69               |
@@ -68,38 +71,39 @@ We developed a series of lightweight models, named `PP-PicoDet`. Because of the
 | YOLOv5n |  640*640       |          28.4             |    46.0            |    1.9                |    4.5              |    40.35                          |
 | YOLOv5s |  640*640       |          37.2             |    56.0            |    7.2                |    16.5             |    78.05                          |
- Testing Mobile latency with code: [MobileDetBenchmark](https://github.com/JiweiMaster/MobileDetBenchmark).
+- ARM测试的benchmark脚本来自: [MobileDetBenchmark](https://github.com/JiweiMaster/MobileDetBenchmark)。
-## Quick Start
+## 快速开始
 <details open>
-<summary>Requirements:</summary>
+<summary>依赖包:</summary>
- PaddlePaddle >= 2.2.1
+- PaddlePaddle == 2.2.2
 </details>
 <details>
-<summary>Installation</summary>
+<summary>安装</summary>
- [Installation guide](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/docs/tutorials/INSTALL.md)
+- [安装指导文档](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/docs/tutorials/INSTALL.md)
- [Prepare dataset](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/docs/tutorials/PrepareDataSet_en.md)
+- [准备数据文档](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/docs/tutorials/PrepareDataSet_en.md)
 </details>
 <details>
-<summary>Training and Evaluation</summary>
+<summary>训练&评估</summary>
- Training model on single-GPU:
+- 单卡GPU上训练:
 ```shell
 # training on single-GPU
 export CUDA_VISIBLE_DEVICES=0
 python tools/train.py -c configs/picodet/picodet_s_320_coco_lcnet.yml --eval
 ```
-If the GPU is out of memory during training, reduce the batch_size in TrainReader, and reduce the base_lr in LearningRate proportionally.
- Training model on multi-GPU:
+**注意：**如果训练时显存out memory，将TrainReader中batch_size调小，同时LearningRate中base_lr等比例减小。同时我们发布的config均由4卡训练得到，如果改变GPU卡数为1，那么base_lr需要减小4倍。
+- 多卡GPU上训练:
 ```shell
@@ -108,31 +112,31 @@ export CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7
 python -m paddle.distributed.launch --gpus 0,1,2,3,4,5,6,7 tools/train.py -c configs/picodet/picodet_s_320_coco_lcnet.yml --eval
 ```
- Evaluation:
+- 评估:
 ```shell
 python tools/eval.py -c configs/picodet/picodet_s_320_coco_lcnet.yml \
              -o weights=https://paddledet.bj.bcebos.com/models/picodet_s_320_coco_lcnet.pdparams
 ```
- Infer:
+- 测试:
 ```shell
 python tools/infer.py -c configs/picodet/picodet_s_320_coco_lcnet.yml \
              -o weights=https://paddledet.bj.bcebos.com/models/picodet_s_320_coco_lcnet.pdparams
 ```
-Detail also can refer to [Quick start guide](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/docs/tutorials/GETTING_STARTED.md).
+详情请参考[快速开始文档](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/docs/tutorials/GETTING_STARTED.md).
 </details>
-## Deployment
+## 部署
-### Export and Convert Model
+### 导出及转换模型
 <details>
-<summary>1. Export model (click to expand)</summary>
+<summary>1. 导出模型 (点击展开)</summary>
 ```shell
 cd PaddleDetection
@@ -141,18 +145,21 @@ python tools/export_model.py -c configs/picodet/picodet_s_320_coco_lcnet.yml \
              --output_dir=inference_model
 ```
+- 如无需导出后处理，请指定：`-o export.benchmark=True`（如果-o已出现过，此处删掉-o）或者手动修改[runtime.yml](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/configs/runtime.yml) 中相应字段。
+- 如无需导出NMS，请指定：`-o export.nms=False`或者手动修改[runtime.yml](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/configs/runtime.yml) 中相应字段。
 </details>
 <details>
-<summary>2. Convert to PaddleLite (click to expand)</summary>
+<summary>2. 转换模型至Paddle Lite (点击展开)</summary>
- Install Paddlelite>=2.10:
+- 安装Paddlelite>=2.10:
 ```shell
 pip install paddlelite
 ```
- Convert model:
+- 转换模型至Paddle Lite格式：
 ```shell
 # FP32
@@ -164,16 +171,16 @@ paddle_lite_opt --model_dir=inference_model/picodet_s_320_coco_lcnet --valid_tar
 </details>
 <details>
-<summary>3. Convert to ONNX (click to expand)</summary>
+<summary>3. 转换模型至ONNX (点击展开)</summary>
- Install [Paddle2ONNX](https://github.com/PaddlePaddle/Paddle2ONNX) >= 0.7 and ONNX > 1.10.1, for details, please refer to [Tutorials of Export ONNX Model](../../deploy/EXPORT_ONNX_MODEL.md)
+- 安装[Paddle2ONNX](https://github.com/PaddlePaddle/Paddle2ONNX) >= 0.7 并且 ONNX > 1.10.1, 细节请参考[导出ONNX模型教程](../../deploy/EXPORT_ONNX_MODEL.md)
 ```shell
 pip install onnx
-pip install paddle2onnx
+pip install paddle2onnx==0.9.2
 ```
- Convert model:
+- 转换模型:
 ```shell
 paddle2onnx --model_dir output_inference/picodet_s_320_coco_lcnet/ \
@@ -183,22 +190,22 @@ paddle2onnx --model_dir output_inference/picodet_s_320_coco_lcnet/ \
            --save_file picodet_s_320_coco.onnx
 ```
- Simplify ONNX model: use onnx-simplifier to simplify onnx model.
+- 简化ONNX模型: 使用`onnx-simplifier`库来简化ONNX模型。
-  - Install onnx-simplifier >= 0.3.6:
+  - 安装 onnx-simplifier >= 0.3.6:
  ```shell
  pip install onnx-simplifier
  ```
-  - simplify onnx model:
+  - 简化ONNX模型:
  ```shell
  python -m onnxsim picodet_s_320_coco.onnx picodet_s_processed.onnx
  ```
 </details>
- Deploy models
+- 部署用的模型
-| Model     | Input size | ONNX  | Paddle Lite(fp32) | Paddle Lite(fp16) |
+| 模型     | 输入尺寸 | ONNX  | Paddle Lite(fp32) | Paddle Lite(fp16) |
 | :-------- | :--------: | :---------------------: | :----------------: | :----------------: |
 | PicoDet-S |  320*320   | [model](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_s_320_coco.onnx) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_s_320.tar) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_s_320_fp16.tar) |
 | PicoDet-S |  416*416   |  [model](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_s_416_coco.onnx) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_s_416.tar) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_s_416_fp16.tar) |
@@ -212,31 +219,28 @@ paddle2onnx --model_dir output_inference/picodet_s_320_coco_lcnet/ \
 | PicoDet-LCNet 1.5x           |  416*416   | [model](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_lcnet_1_5x_416_coco.onnx) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_lcnet_1_5x.tar) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_lcnet_1_5x_fp16.tar) |
-### Deploy
+### 部署
 - PaddleInference demo [Python](../../deploy/python) & [C++](../../deploy/cpp)
 - [PaddleLite C++ demo](../../deploy/lite)
- [NCNN C++/Python demo](../../deploy/third_engine/demo_ncnn)
- [MNN C++/Python demo](../../deploy/third_engine/demo_mnn)
- [OpenVINO C++ demo](../../deploy/third_engine/demo_openvino)
 - [Android demo(Paddle Lite)](https://github.com/PaddlePaddle/Paddle-Lite-Demo/tree/develop/object_detection/android/app/cxx/picodet_detection_demo)
-Android demo visualization:
+Android demo可视化：
 <div align="center">
  <img src="../../docs/images/picodet_android_demo1.jpg" height="500px" ><img src="../../docs/images/picodet_android_demo2.jpg" height="500px" ><img src="../../docs/images/picodet_android_demo3.jpg" height="500px" ><img src="../../docs/images/picodet_android_demo4.jpg" height="500px" >
 </div>
-## Quantization
+## 量化
 <details open>
-<summary>Requirements:</summary>
+<summary>依赖包:</summary>
 - PaddlePaddle >= 2.2.2
 - PaddleSlim >= 2.2.1
-**Install:**
+**安装:**
 ```shell
 pip install paddleslim==2.2.1
@@ -245,61 +249,61 @@ pip install paddleslim==2.2.1
 </details>
 <details>
-<summary>Quant aware (click to expand)</summary>
+<summary>量化训练 (点击展开)</summary>
-Configure the quant config and start training:
+开始量化训练:
 ```shell
 python tools/train.py -c configs/picodet/picodet_s_320_coco_lcnet.yml \
          --slim_config configs/slim/quant/picodet_s_quant.yml --eval
 ```
- More detail can refer to [slim document](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/slim)
+- 更多细节请参考[slim文档](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/slim)
 </details>
 <details>
-<summary>Post quant (click to expand)</summary>
+<summary>离线量化 (点击展开)</summary>
-Configure the post quant config and start calibrate model:
+校准及导出量化模型:
 ```shell
 python tools/post_quant.py -c configs/picodet/picodet_s_320_coco_lcnet.yml \
          --slim_config configs/slim/post_quant/picodet_s_ptq.yml
 ```
- Notes: Now the accuracy of post quant is abnormal and this problem is being solved.
+- 注意: 离线量化模型精度问题正在解决中.
 </details>
-## Unstructured Pruning
+## 非结构化剪枝
 <details open>
-<summary>Toturial:</summary>
+<summary>教程:</summary>
-Please refer this [documentation](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/picodet/pruner/README.md) for details such as requirements, training and deployment.
+训练及部署细节请参考[非结构化剪枝文档](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/picodet/pruner/README.md)。
 </details>
-## Application
+## 应用
- **Pedestrian detection:** model zoo of `PicoDet-S-Pedestrian` please refer to [PP-TinyPose](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/keypoint/tiny_pose#%E8%A1%8C%E4%BA%BA%E6%A3%80%E6%B5%8B%E6%A8%A1%E5%9E%8B)
+- **行人检测：** `PicoDet-S-Pedestrian`行人检测模型请参考[PP-TinyPose](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/keypoint/tiny_pose#%E8%A1%8C%E4%BA%BA%E6%A3%80%E6%B5%8B%E6%A8%A1%E5%9E%8B)
- **Mainbody detection:** model zoo of `PicoDet-L-Mainbody` please refer to [mainbody detection](./application/mainbody_detection/README.md)
+- **主体检测：** `PicoDet-L-Mainbody`主体检测模型请参考[主体检测文档](./application/mainbody_detection/README.md)
 ## FAQ
 <details>
-<summary>Out of memory error.</summary>
+<summary>显存爆炸(Out of memory error)</summary>
-Please reduce the `batch_size` of `TrainReader` in config.
+请减小配置文件中`TrainReader`的`batch_size`。
 </details>
 <details>
-<summary>How to transfer learning.</summary>
+<summary>如何迁移学习</summary>
-Please reset `pretrain_weights` in config, which trained on coco. Such as:
+请重新设置配置文件中的`pretrain_weights`字段，比如利用COCO上训好的模型在自己的数据上继续训练：
 ```yaml
 pretrain_weights: https://paddledet.bj.bcebos.com/models/picodet_l_640_coco_lcnet.pdparams
 ```
@@ -307,17 +311,17 @@ pretrain_weights: https://paddledet.bj.bcebos.com/models/picodet_l_640_coco_lcne
 </details>
 <details>
-<summary>The transpose operator is time-consuming on some hardware.</summary>
+<summary>`transpose`算子在某些硬件上耗时验证</summary>
-Please use `PicoDet-LCNet` model, which has fewer `transpose` operators.
+请使用`PicoDet-LCNet`模型，`transpose`较少。
 </details>
 <details>
-<summary>How to count model parameters.</summary>
+<summary>如何计算模型参数量。</summary>
-You can insert below code at [here](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/ppdet/engine/trainer.py#L141) to count learnable parameters.
+可以将以下代码插入：[trainer.py](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/ppdet/engine/trainer.py#L141) 来计算参数量。
 ```python
 params = sum([
@@ -329,8 +333,8 @@ print('params: ', params)
 </details>
-## Cite PP-PicoDet
+## 引用PP-PicoDet
-If you use PicoDet in your research, please cite our work by using the following BibTeX entry:
+如果需要在你的研究中使用PP-PicoDet，请通过一下方式引用我们的技术报告：
 ```
 @misc{yu2021pppicodet,
      title={PP-PicoDet: A Better Real-Time Object Detector on Mobile Devices},

--- a/configs/picodet/README_cn.md
+++ b/configs/picodet/README_cn.md
-简体中文 | [English](README.md)
+English | [简体中文](README.md)
 # PP-PicoDet
 ![](../../docs/images/picedet_demo.jpeg)
-## 最新动态
+## News
- 发布全新系列PP-PicoDet模型：**（2022.03.20）**
+- Released a new series of PP-PicoDet models: **(2022.03.20)**
-  - (1)引入TAL及Task-aligned Head，优化PAN等结构，精度大幅提升；
+  - (1) It was used TAL/Task-aligned-Head and optimized PAN, which greatly improved the accuracy;
-  - (2)优化CPU端预测速度，同时训练速度大幅提升；
+  - (2) Moreover optimized CPU prediction speed, and the training speed is greatly improved;
-  - (3)导出模型将后处理包含在网络中，预测直接输出box结果，无需二次开发，迁移成本更低。
+  - (3) The export model includes post-processing, and the prediction directly outputs the result, without secondary development, and the migration cost is lower.
-## 历史版本模型
+### Legacy Model
- 详情请参考：[PicoDet 2021.10版本](./legacy_model/)
+- Please refer to: [PicoDet 2021.10](./legacy_model/)
-## 简介
+## Introduction
-PaddleDetection中提出了全新的轻量级系列模型`PP-PicoDet`，在移动端具有卓越的性能，成为全新SOTA轻量级模型。详细的技术细节可以参考我们的[arXiv技术报告](https://arxiv.org/abs/2111.00902)。
+We developed a series of lightweight models, named `PP-PicoDet`. Because of the excellent performance, our models are very suitable for deployment on mobile or CPU. For more details, please refer to our [report on arXiv](https://arxiv.org/abs/2111.00902).
-PP-PicoDet模型有如下特点：
+- 🌟 Higher mAP: the **first** object detectors that surpass mAP(0.5:0.95) **30+** within 1M parameters when the input size is 416.
+- 🚀 Faster latency: 150FPS on mobile ARM CPU.
- 🌟 更高的mAP: 第一个在1M参数量之内`mAP(0.5:0.95)`超越**30+**(输入416像素时)。
+- 😊 Deploy friendly: support PaddleLite/MNN/NCNN/OpenVINO and provide C++/Python/Android implementation.
- 🚀 更快的预测速度: 网络预测在ARM CPU下可达150FPS。
+- 😍 Advanced algorithm: use the most advanced algorithms and offer innovation, such as ESNet, CSP-PAN, SimOTA with VFL, etc.
- 😊 部署友好: 支持PaddleLite/MNN/NCNN/OpenVINO等预测库，支持转出ONNX，提供了C++/Python/Android的demo。
- 😍 先进的算法: 我们在现有SOTA算法中进行了创新, 包括：ESNet, CSP-PAN, SimOTA等等。
 <div align="center">
  <img src="../../docs/images/picodet_map.png" width='600'/>
 </div>
-## 基线
+## Benchmark
-| 模型     | 输入尺寸 | mAP<sup>val<br>0.5:0.95 | mAP<sup>val<br>0.5 | 参数量<br><sup>(M) | FLOPS<br><sup>(G) | 预测时延<sup><small>[NCNN](#latency)</small><sup><br><sup>(ms) | 预测时延<sup><small>[Lite](#latency)</small><sup><br><sup>(ms) |  下载  | 配置文件 |
+| Model     | Input size | mAP<sup>val<br>0.5:0.95 | mAP<sup>val<br>0.5 | Params<br><sup>(M) | FLOPS<br><sup>(G) | Latency<sup><small>[CPU](#latency)</small><sup><br><sup>(ms) | Latency<sup><small>[Lite](#latency)</small><sup><br><sup>(ms) |  Download  | Config |
 | :-------- | :--------: | :---------------------: | :----------------: | :----------------: | :---------------: | :-----------------------------: | :-----------------------------: | :----------------------------------------: | :--------------------------------------- |
 | PicoDet-XS |  320*320   |          23.5           |        36.1       |        0.70        |       0.67        |              10.9ms              |            7.81ms             | [model](https://paddledet.bj.bcebos.com/models/picodet_xs_320_coco_lcnet.pdparams) &#124; [log](https://paddledet.bj.bcebos.com/logs/train_picodet_xs_320_coco_lcnet.log) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/picodet/picodet_xs_320_coco_lcnet.yml) |
 | PicoDet-XS |  416*416   |          26.2           |        39.3        |        0.70        |       1.13        |              15.4ms             |            12.38ms             | [model](https://paddledet.bj.bcebos.com/models/picodet_xs_416_coco_lcnet.pdparams) &#124; [log](https://paddledet.bj.bcebos.com/logs/train_picodet_xs_416_coco_lcnet.log) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/picodet/picodet_xs_416_coco_lcnet.yml) |
 | PicoDet-S |  320*320   |          29.1           |        43.4        |        1.18       |       0.97       |             12.6ms              |            9.56ms             | [model](https://paddledet.bj.bcebos.com/models/picodet_s_320_coco_lcnet.pdparams) &#124; [log](https://paddledet.bj.bcebos.com/logs/train_picodet_s_320_coco_lcnet.log) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/picodet/picodet_s_320_coco_lcnet.yml) |
-| PicoDet-S |  416*416   |          32.5           |        47.6        |        1.18        |       1.65       |              17.2ms              |            15.20             | [model](https://paddledet.bj.bcebos.com/models/picodet_s_416_coco_lcnet.pdparams) &#124; [log](https://paddledet.bj.bcebos.com/logs/train_picodet_s_416_coco_lcnet.log) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/picodet/picodet_s_416_coco_lcnet.yml) |
+| PicoDet-S |  416*416   |          32.5           |        47.6        |        1.18        |       1.65       |              17.2ms              |            15.20ms             | [model](https://paddledet.bj.bcebos.com/models/picodet_s_416_coco_lcnet.pdparams) &#124; [log](https://paddledet.bj.bcebos.com/logs/train_picodet_s_416_coco_lcnet.log) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/picodet/picodet_s_416_coco_lcnet.yml) |
 | PicoDet-M |  320*320   |          34.4           |        50.0        |        3.46        |       2.57       |              14.5ms              |            17.68ms             | [model](https://paddledet.bj.bcebos.com/models/picodet_m_320_coco_lcnet.pdparams) &#124; [log](https://paddledet.bj.bcebos.com/logs/train_picodet_m_320_coco_lcnet.log) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/picodet/picodet_m_320_coco_lcnet.yml) |
 | PicoDet-M |  416*416   |          37.5           |        53.4       |        3.46        |       4.34        |              19.5ms              |            28.39ms            | [model](https://paddledet.bj.bcebos.com/models/picodet_m_416_coco_lcnet.pdparams) &#124; [log](https://paddledet.bj.bcebos.com/logs/train_picodet_m_416_coco_lcnet.log) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/picodet/picodet_m_416_coco_lcnet.yml) |
 | PicoDet-L |  320*320   |          36.1           |        52.0        |        5.80       |       4.20        |              18.3ms             |            25.21ms           | [model](https://paddledet.bj.bcebos.com/models/picodet_l_320_coco_lcnet.pdparams) &#124; [log](https://paddledet.bj.bcebos.com/logs/train_picodet_l_320_coco_lcnet.log) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/picodet/picodet_l_320_coco_lcnet.yml) |
 | PicoDet-L |  416*416   |          39.4           |        55.7        |        5.80        |       7.10       |              22.1ms              |            42.23ms            | [model](https://paddledet.bj.bcebos.com/models/picodet_l_416_coco_lcnet.pdparams) &#124; [log](https://paddledet.bj.bcebos.com/logs/train_picodet_l_416_coco_lcnet.log) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/picodet/picodet_l_416_coco_lcnet.yml) |
-| PicoDet-L |  640*640   |          42.3           |        59.2        |        5.80        |       16.81        |              43.1ms              |            108.1ms          | [model](https://paddledet.bj.bcebos.com/models/picodet_l_640_coco_lcnet.pdparams) &#124; [log](https://paddledet.bj.bcebos.com/logs/train_picodet_l_640_coco_lcnet.log) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/picodet/picodet_l_640_coco_lcnet.yml) |
+| PicoDet-L |  640*640   |          42.6           |        59.2        |        5.80        |       16.81        |              43.1ms              |            108.1ms          | [model](https://paddledet.bj.bcebos.com/models/picodet_l_640_coco_lcnet.pdparams) &#124; [log](https://paddledet.bj.bcebos.com/logs/train_picodet_l_640_coco_lcnet.log) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/picodet/picodet_l_640_coco_lcnet.yml) |
 <details open>
-<summary><b>注意事项:</b></summary>
+<summary><b>Table Notes:</b></summary>
- <a name="latency">时延测试：</a> 我们所有的模型都在英特尔至强6148的CPU（MKLDNN 10线程）和`骁龙865(4xA77+4xA55)`的ARM CPU上测试(4线程，FP16预测)。上面表格中标有`CPU`的是使用Paddle Inference库测试，标有`Lite`的是使用[Paddle Lite](https://github.com/PaddlePaddle/Paddle-Lite)进行测试。
+- <a name="latency">Latency:</a> All our models test on `Intel-Xeon-Gold-6148` CPU with MKLDNN by 10 threads and `Qualcomm Snapdragon 865(4xA77+4xA55)` with 4 threads by arm8 and with FP16. In the above table, test CPU latency on Paddle-Inference and testing Mobile latency with `Lite`->[Paddle-Lite](https://github.com/PaddlePaddle/Paddle-Lite).
- PicoDet在COCO train2017上训练，并且在COCO val2017上进行验证。使用4卡GPU训练，并且上表所有的预训练模型都是通过发布的默认配置训练得到。
+- PicoDet is trained on COCO train2017 dataset and evaluated on COCO val2017. And PicoDet used 4 GPUs for training and all checkpoints are trained with default settings and hyperparameters.
- Benchmark测试：测试速度benchmark性能时，导出模型后处理不包含在网络中，需要设置`-o export.benchmark=True` 或手动修改[runtime.yml](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/configs/runtime.yml#L12)。
+- Benchmark test: When testing the speed benchmark, the post-processing is not included in the exported model, you need to set `-o export.benchmark=True` or manually modify [runtime.yml](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/configs/runtime.yml#L12).
 </details>
-#### 其他模型的基线
+#### Benchmark of Other Models
-| 模型     | 输入尺寸 | mAP<sup>val<br>0.5:0.95 | mAP<sup>val<br>0.5 | 参数量<br><sup>(M) | FLOPS<br><sup>(G) | 预测时延<sup><small>[NCNN](#latency)</small><sup><br><sup>(ms) |
+| Model     | Input size | mAP<sup>val<br>0.5:0.95 | mAP<sup>val<br>0.5 | Params<br><sup>(M) | FLOPS<br><sup>(G) | Latency<sup><small>[NCNN](#latency)</small><sup><br><sup>(ms) |
 | :-------- | :--------: | :---------------------: | :----------------: | :----------------: | :---------------: | :-----------------------------: |
 | YOLOv3-Tiny |  416*416   |          16.6           |        33.1      |        8.86        |       5.62        |             25.42               |
 | YOLOv4-Tiny |  416*416   |          21.7           |        40.2        |        6.06           |       6.96           |             23.69               |
@@ -71,39 +68,38 @@ PP-PicoDet模型有如下特点：
 | YOLOv5n |  640*640       |          28.4             |    46.0            |    1.9                |    4.5              |    40.35                          |
 | YOLOv5s |  640*640       |          37.2             |    56.0            |    7.2                |    16.5             |    78.05                          |
- ARM测试的benchmark脚本来自: [MobileDetBenchmark](https://github.com/JiweiMaster/MobileDetBenchmark)。
+- Testing Mobile latency with code: [MobileDetBenchmark](https://github.com/JiweiMaster/MobileDetBenchmark).
-## 快速开始
+## Quick Start
 <details open>
-<summary>依赖包:</summary>
+<summary>Requirements:</summary>
- PaddlePaddle == 2.2.2
+- PaddlePaddle >= 2.2.2
 </details>
 <details>
-<summary>安装</summary>
+<summary>Installation</summary>
- [安装指导文档](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/docs/tutorials/INSTALL.md)
+- [Installation guide](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/docs/tutorials/INSTALL.md)
- [准备数据文档](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/docs/tutorials/PrepareDataSet_en.md)
+- [Prepare dataset](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/docs/tutorials/PrepareDataSet_en.md)
 </details>
 <details>
-<summary>训练&评估</summary>
+<summary>Training and Evaluation</summary>
- 单卡GPU上训练:
+- Training model on single-GPU:
 ```shell
 # training on single-GPU
 export CUDA_VISIBLE_DEVICES=0
 python tools/train.py -c configs/picodet/picodet_s_320_coco_lcnet.yml --eval
 ```
+If the GPU is out of memory during training, reduce the batch_size in TrainReader, and reduce the base_lr in LearningRate proportionally. At the same time, the configs we published are all trained with 4 GPUs. If the number of GPUs is changed to 1, the base_lr needs to be reduced by a factor of 4.
-如果训练时显存out memory，将TrainReader中batch_size调小，同时LearningRate中base_lr等比例减小。
+- Training model on multi-GPU:
- 多卡GPU上训练:
 ```shell
@@ -112,31 +108,31 @@ export CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7
 python -m paddle.distributed.launch --gpus 0,1,2,3,4,5,6,7 tools/train.py -c configs/picodet/picodet_s_320_coco_lcnet.yml --eval
 ```
- 评估:
+- Evaluation:
 ```shell
 python tools/eval.py -c configs/picodet/picodet_s_320_coco_lcnet.yml \
              -o weights=https://paddledet.bj.bcebos.com/models/picodet_s_320_coco_lcnet.pdparams
 ```
- 测试:
+- Infer:
 ```shell
 python tools/infer.py -c configs/picodet/picodet_s_320_coco_lcnet.yml \
              -o weights=https://paddledet.bj.bcebos.com/models/picodet_s_320_coco_lcnet.pdparams
 ```
-详情请参考[快速开始文档](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/docs/tutorials/GETTING_STARTED.md).
+Detail also can refer to [Quick start guide](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/docs/tutorials/GETTING_STARTED.md).
 </details>
-## 部署
+## Deployment
-### 导出及转换模型
+### Export and Convert Model
 <details>
-<summary>1. 导出模型 (点击展开)</summary>
+<summary>1. Export model (click to expand)</summary>
 ```shell
 cd PaddleDetection
@@ -145,18 +141,22 @@ python tools/export_model.py -c configs/picodet/picodet_s_320_coco_lcnet.yml \
              --output_dir=inference_model
 ```
+- If no post processing is required, please specify: `-o export.benchmark=True` (if -o has already appeared, delete -o here) or manually modify corresponding fields in [runtime.yml](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/configs/runtime.yml).
+- If no NMS is required, please specify: `-o export.nms=True` or manually modify corresponding fields in [runtime.yml](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/configs/runtime.yml).
 </details>
 <details>
-<summary>2. 转换模型至Paddle Lite (点击展开)</summary>
+<summary>2. Convert to PaddleLite (click to expand)</summary>
- 安装Paddlelite>=2.10:
+- Install Paddlelite>=2.10:
 ```shell
 pip install paddlelite
 ```
- 转换模型至Paddle Lite格式：
+- Convert model:
 ```shell
 # FP32
@@ -168,16 +168,16 @@ paddle_lite_opt --model_dir=inference_model/picodet_s_320_coco_lcnet --valid_tar
 </details>
 <details>
-<summary>3. 转换模型至ONNX (点击展开)</summary>
+<summary>3. Convert to ONNX (click to expand)</summary>
- 安装[Paddle2ONNX](https://github.com/PaddlePaddle/Paddle2ONNX) >= 0.7 并且 ONNX > 1.10.1, 细节请参考[导出ONNX模型教程](../../deploy/EXPORT_ONNX_MODEL.md)
+- Install [Paddle2ONNX](https://github.com/PaddlePaddle/Paddle2ONNX) >= 0.7 and ONNX > 1.10.1, for details, please refer to [Tutorials of Export ONNX Model](../../deploy/EXPORT_ONNX_MODEL.md)
 ```shell
 pip install onnx
-pip install paddle2onnx
+pip install paddle2onnx==0.9.2
 ```
- 转换模型:
+- Convert model:
 ```shell
 paddle2onnx --model_dir output_inference/picodet_s_320_coco_lcnet/ \
@@ -187,22 +187,22 @@ paddle2onnx --model_dir output_inference/picodet_s_320_coco_lcnet/ \
            --save_file picodet_s_320_coco.onnx
 ```
- 简化ONNX模型: 使用`onnx-simplifier`库来简化ONNX模型。
+- Simplify ONNX model: use onnx-simplifier to simplify onnx model.
-  - 安装 onnx-simplifier >= 0.3.6:
+  - Install onnx-simplifier >= 0.3.6:
  ```shell
  pip install onnx-simplifier
  ```
-  - 简化ONNX模型:
+  - simplify onnx model:
  ```shell
  python -m onnxsim picodet_s_320_coco.onnx picodet_s_processed.onnx
  ```
 </details>
- 部署用的模型
+- Deploy models
-| 模型     | 输入尺寸 | ONNX  | Paddle Lite(fp32) | Paddle Lite(fp16) |
+| Model     | Input size | ONNX  | Paddle Lite(fp32) | Paddle Lite(fp16) |
 | :-------- | :--------: | :---------------------: | :----------------: | :----------------: |
 | PicoDet-S |  320*320   | [model](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_s_320_coco.onnx) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_s_320.tar) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_s_320_fp16.tar) |
 | PicoDet-S |  416*416   |  [model](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_s_416_coco.onnx) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_s_416.tar) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_s_416_fp16.tar) |
@@ -216,31 +216,28 @@ paddle2onnx --model_dir output_inference/picodet_s_320_coco_lcnet/ \
 | PicoDet-LCNet 1.5x           |  416*416   | [model](https://paddledet.bj.bcebos.com/deploy/third_engine/picodet_lcnet_1_5x_416_coco.onnx) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_lcnet_1_5x.tar) | [model](https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_lcnet_1_5x_fp16.tar) |
-### 部署
+### Deploy
 - PaddleInference demo [Python](../../deploy/python) & [C++](../../deploy/cpp)
 - [PaddleLite C++ demo](../../deploy/lite)
- [NCNN C++/Python demo](../../deploy/third_engine/demo_ncnn)
- [MNN C++/Python demo](../../deploy/third_engine/demo_mnn)
- [OpenVINO C++ demo](../../deploy/third_engine/demo_openvino)
 - [Android demo(Paddle Lite)](https://github.com/PaddlePaddle/Paddle-Lite-Demo/tree/develop/object_detection/android/app/cxx/picodet_detection_demo)
-Android demo可视化：
+Android demo visualization:
 <div align="center">
  <img src="../../docs/images/picodet_android_demo1.jpg" height="500px" ><img src="../../docs/images/picodet_android_demo2.jpg" height="500px" ><img src="../../docs/images/picodet_android_demo3.jpg" height="500px" ><img src="../../docs/images/picodet_android_demo4.jpg" height="500px" >
 </div>
-## 量化
+## Quantization
 <details open>
-<summary>依赖包:</summary>
+<summary>Requirements:</summary>
 - PaddlePaddle >= 2.2.2
 - PaddleSlim >= 2.2.1
-**安装:**
+**Install:**
 ```shell
 pip install paddleslim==2.2.1
@@ -249,61 +246,61 @@ pip install paddleslim==2.2.1
 </details>
 <details>
-<summary>量化训练 (点击展开)</summary>
+<summary>Quant aware (click to expand)</summary>
-开始量化训练:
+Configure the quant config and start training:
 ```shell
 python tools/train.py -c configs/picodet/picodet_s_320_coco_lcnet.yml \
          --slim_config configs/slim/quant/picodet_s_quant.yml --eval
 ```
- 更多细节请参考[slim文档](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/slim)
+- More detail can refer to [slim document](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/slim)
 </details>
 <details>
-<summary>离线量化 (点击展开)</summary>
+<summary>Post quant (click to expand)</summary>
-校准及导出量化模型:
+Configure the post quant config and start calibrate model:
 ```shell
 python tools/post_quant.py -c configs/picodet/picodet_s_320_coco_lcnet.yml \
          --slim_config configs/slim/post_quant/picodet_s_ptq.yml
 ```
- 注意: 离线量化模型精度问题正在解决中.
+- Notes: Now the accuracy of post quant is abnormal and this problem is being solved.
 </details>
-## 非结构化剪枝
+## Unstructured Pruning
 <details open>
-<summary>教程:</summary>
+<summary>Toturial:</summary>
-训练及部署细节请参考[非结构化剪枝文档](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/picodet/pruner/README.md)。
+Please refer this [documentation](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/picodet/pruner/README.md) for details such as requirements, training and deployment.
 </details>
-## 应用
+## Application
- **行人检测：** `PicoDet-S-Pedestrian`行人检测模型请参考[PP-TinyPose](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/keypoint/tiny_pose#%E8%A1%8C%E4%BA%BA%E6%A3%80%E6%B5%8B%E6%A8%A1%E5%9E%8B)
+- **Pedestrian detection:** model zoo of `PicoDet-S-Pedestrian` please refer to [PP-TinyPose](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/keypoint/tiny_pose#%E8%A1%8C%E4%BA%BA%E6%A3%80%E6%B5%8B%E6%A8%A1%E5%9E%8B)
- **主体检测：** `PicoDet-L-Mainbody`主体检测模型请参考[主体检测文档](./application/mainbody_detection/README.md)
+- **Mainbody detection:** model zoo of `PicoDet-L-Mainbody` please refer to [mainbody detection](./application/mainbody_detection/README.md)
 ## FAQ
 <details>
-<summary>显存爆炸(Out of memory error)</summary>
+<summary>Out of memory error.</summary>
-请减小配置文件中`TrainReader`的`batch_size`。
+Please reduce the `batch_size` of `TrainReader` in config.
 </details>
 <details>
-<summary>如何迁移学习</summary>
+<summary>How to transfer learning.</summary>
-请重新设置配置文件中的`pretrain_weights`字段，比如利用COCO上训好的模型在自己的数据上继续训练：
+Please reset `pretrain_weights` in config, which trained on coco. Such as:
 ```yaml
 pretrain_weights: https://paddledet.bj.bcebos.com/models/picodet_l_640_coco_lcnet.pdparams
 ```
@@ -311,17 +308,17 @@ pretrain_weights: https://paddledet.bj.bcebos.com/models/picodet_l_640_coco_lcne
 </details>
 <details>
-<summary>`transpose`算子在某些硬件上耗时验证</summary>
+<summary>The transpose operator is time-consuming on some hardware.</summary>
-请使用`PicoDet-LCNet`模型，`transpose`较少。
+Please use `PicoDet-LCNet` model, which has fewer `transpose` operators.
 </details>
 <details>
-<summary>如何计算模型参数量。</summary>
+<summary>How to count model parameters.</summary>
-可以将以下代码插入：[trainer.py](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/ppdet/engine/trainer.py#L141) 来计算参数量。
+You can insert below code at [here](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/ppdet/engine/trainer.py#L141) to count learnable parameters.
 ```python
 params = sum([
@@ -333,8 +330,8 @@ print('params: ', params)
 </details>
-## 引用PP-PicoDet
+## Cite PP-PicoDet
-如果需要在你的研究中使用PP-PicoDet，请通过一下方式引用我们的技术报告：
+If you use PicoDet in your research, please cite our work by using the following BibTeX entry:
 ```
 @misc{yu2021pppicodet,
      title={PP-PicoDet: A Better Real-Time Object Detector on Mobile Devices},

--- a/deploy/cpp/src/object_detector.cc
+++ b/deploy/cpp/src/object_detector.cc
@@ -15,16 +15,15 @@
 // for setprecision
 #include <chrono>
 #include <iomanip>
-#include "include/object_detector.h"
-using namespace paddle_infer;
+#include "include/object_detector.h"
 namespace PaddleDetection {
 // Load Model and create model predictor
-void ObjectDetector::LoadModel(const std::string& model_dir,
+void ObjectDetector::LoadModel(const std::string &model_dir,
                               const int batch_size,
-                               const std::string& run_mode) {
+                               const std::string &run_mode) {
  paddle_infer::Config config;
  std::string prog_file = model_dir + OS_PATH_SEP + "model.pdmodel";
  std::string params_file = model_dir + OS_PATH_SEP + "model.pdiparams";
@@ -42,27 +41,22 @@ void ObjectDetector::LoadModel(const std::string& model_dir,
      } else if (run_mode == "trt_int8") {
        precision = paddle_infer::Config::Precision::kInt8;
      } else {
-        printf(
+        printf("run_mode should be 'paddle', 'trt_fp32', 'trt_fp16' or "
-            "run_mode should be 'paddle', 'trt_fp32', 'trt_fp16' or "
               "'trt_int8'");
      }
      // set tensorrt
-      config.EnableTensorRtEngine(1 << 30,
+      config.EnableTensorRtEngine(1 << 30, batch_size, this->min_subgraph_size_,
-                                  batch_size,
+                                  precision, false, this->trt_calib_mode_);
-                                  this->min_subgraph_size_,
-                                  precision,
-                                  false,
-                                  this->trt_calib_mode_);
      // set use dynamic shape
      if (this->use_dynamic_shape_) {
-        // set DynamicShsape for image tensor
+        // set DynamicShape for image tensor
        const std::vector<int> min_input_shape = {
-            1, 3, this->trt_min_shape_, this->trt_min_shape_};
+            batch_size, 3, this->trt_min_shape_, this->trt_min_shape_};
        const std::vector<int> max_input_shape = {
-            1, 3, this->trt_max_shape_, this->trt_max_shape_};
+            batch_size, 3, this->trt_max_shape_, this->trt_max_shape_};
        const std::vector<int> opt_input_shape = {
-            1, 3, this->trt_opt_shape_, this->trt_opt_shape_};
+            batch_size, 3, this->trt_opt_shape_, this->trt_opt_shape_};
        const std::map<std::string, std::vector<int>> map_min_input_shape = {
            {"image", min_input_shape}};
        const std::map<std::string, std::vector<int>> map_max_input_shape = {
@@ -70,8 +64,8 @@ void ObjectDetector::LoadModel(const std::string& model_dir,
        const std::map<std::string, std::vector<int>> map_opt_input_shape = {
            {"image", opt_input_shape}};
-        config.SetTRTDynamicShapeInfo(
+        config.SetTRTDynamicShapeInfo(map_min_input_shape, map_max_input_shape,
-            map_min_input_shape, map_max_input_shape, map_opt_input_shape);
+                                      map_opt_input_shape);
        std::cout << "TensorRT dynamic shape enabled" << std::endl;
      }
    }
@@ -96,12 +90,11 @@ void ObjectDetector::LoadModel(const std::string& model_dir,
 }
 // Visualiztion MaskDetector results
-cv::Mat VisualizeResult(
+cv::Mat
-    const cv::Mat& img,
+VisualizeResult(const cv::Mat &img,
-    const std::vector<PaddleDetection::ObjectResult>& results,
+                const std::vector<PaddleDetection::ObjectResult> &results,
-    const std::vector<std::string>& lables,
+                const std::vector<std::string> &lables,
-    const std::vector<int>& colormap,
+                const std::vector<int> &colormap, const bool is_rbox = false) {
-    const bool is_rbox = false) {
  cv::Mat vis_img = img.clone();
  for (int i = 0; i < results.size(); ++i) {
    // Configure color and text size
@@ -142,24 +135,18 @@ cv::Mat VisualizeResult(
    origin.y = results[i].rect[1];
    // Configure text background
-    cv::Rect text_back = cv::Rect(results[i].rect[0],
+    cv::Rect text_back =
-                                  results[i].rect[1] - text_size.height,
+        cv::Rect(results[i].rect[0], results[i].rect[1] - text_size.height,
-                                  text_size.width,
+                 text_size.width, text_size.height);
-                                  text_size.height);
    // Draw text, and background
    cv::rectangle(vis_img, text_back, roi_color, -1);
-    cv::putText(vis_img,
+    cv::putText(vis_img, text, origin, font_face, font_scale,
-                text,
+                cv::Scalar(255, 255, 255), thickness);
-                origin,
-                font_face,
-                font_scale,
-                cv::Scalar(255, 255, 255),
-                thickness);
  }
  return vis_img;
 }
-void ObjectDetector::Preprocess(const cv::Mat& ori_im) {
+void ObjectDetector::Preprocess(const cv::Mat &ori_im) {
  // Clone the image : keep the original mat for postprocess
  cv::Mat im = ori_im.clone();
  cv::cvtColor(im, im, cv::COLOR_BGR2RGB);
@@ -168,9 +155,8 @@ void ObjectDetector::Preprocess(const cv::Mat& ori_im) {
 void ObjectDetector::Postprocess(
    const std::vector<cv::Mat> mats,
-    std::vector<PaddleDetection::ObjectResult>* result,
+    std::vector<PaddleDetection::ObjectResult> *result,
-    std::vector<int> bbox_num,
+    std::vector<int> bbox_num, std::vector<float> output_data_,
-    std::vector<float> output_data_,
    bool is_rbox = false) {
  result->clear();
  int start_idx = 0;
@@ -226,12 +212,11 @@ void ObjectDetector::Postprocess(
 }
 void ObjectDetector::Predict(const std::vector<cv::Mat> imgs,
-                             const double threshold,
+                             const double threshold, const int warmup,
-                             const int warmup,
                             const int repeats,
-                             std::vector<PaddleDetection::ObjectResult>* result,
+                             std::vector<PaddleDetection::ObjectResult> *result,
-                             std::vector<int>* bbox_num,
+                             std::vector<int> *bbox_num,
-                             std::vector<double>* times) {
+                             std::vector<double> *times) {
  auto preprocess_start = std::chrono::steady_clock::now();
  int batch_size = imgs.size();
@@ -239,7 +224,7 @@ void ObjectDetector::Predict(const std::vector<cv::Mat> imgs,
  std::vector<float> in_data_all;
  std::vector<float> im_shape_all(batch_size * 2);
  std::vector<float> scale_factor_all(batch_size * 2);
-  std::vector<const float*> output_data_list_;
+  std::vector<const float *> output_data_list_;
  std::vector<int> out_bbox_num_data_;
  // in_net img for each batch
@@ -255,9 +240,8 @@ void ObjectDetector::Predict(const std::vector<cv::Mat> imgs,
    scale_factor_all[bs_idx * 2] = inputs_.scale_factor_[0];
    scale_factor_all[bs_idx * 2 + 1] = inputs_.scale_factor_[1];
-    // TODO: reduce cost time
+    in_data_all.insert(in_data_all.end(), inputs_.im_data_.begin(),
-    in_data_all.insert(
+                       inputs_.im_data_.end());
-        in_data_all.end(), inputs_.im_data_.begin(), inputs_.im_data_.end());
    // collect in_net img
    in_net_img_all[bs_idx] = inputs_.in_net_im_;
@@ -276,10 +260,10 @@ void ObjectDetector::Predict(const std::vector<cv::Mat> imgs,
      pad_img.convertTo(pad_img, CV_32FC3);
      std::vector<float> pad_data;
      pad_data.resize(rc * rh * rw);
-      float* base = pad_data.data();
+      float *base = pad_data.data();
      for (int i = 0; i < rc; ++i) {
-        cv::extractChannel(
+        cv::extractChannel(pad_img,
-            pad_img, cv::Mat(rh, rw, CV_32FC1, base + i * rh * rw), i);
+                           cv::Mat(rh, rw, CV_32FC1, base + i * rh * rw), i);
      }
      in_data_all.insert(in_data_all.end(), pad_data.begin(), pad_data.end());
    }
@@ -290,7 +274,7 @@ void ObjectDetector::Predict(const std::vector<cv::Mat> imgs,
  auto preprocess_end = std::chrono::steady_clock::now();
  // Prepare input tensor
  auto input_names = predictor_->GetInputNames();
-  for (const auto& tensor_name : input_names) {
+  for (const auto &tensor_name : input_names) {
    auto in_tensor = predictor_->GetInputHandle(tensor_name);
    if (tensor_name == "image") {
      int rh = inputs_.in_net_shape_[0];
@@ -320,8 +304,8 @@ void ObjectDetector::Predict(const std::vector<cv::Mat> imgs,
    for (int j = 0; j < output_names.size(); j++) {
      auto output_tensor = predictor_->GetOutputHandle(output_names[j]);
      std::vector<int> output_shape = output_tensor->shape();
-      int out_num = std::accumulate(
+      int out_num = std::accumulate(output_shape.begin(), output_shape.end(), 1,
-          output_shape.begin(), output_shape.end(), 1, std::multiplies<int>());
+                                    std::multiplies<int>());
      if (output_tensor->type() == paddle_infer::DataType::INT32) {
        out_bbox_num_data_.resize(out_num);
        output_tensor->CopyToCpu(out_bbox_num_data_.data());
@@ -344,8 +328,8 @@ void ObjectDetector::Predict(const std::vector<cv::Mat> imgs,
    for (int j = 0; j < output_names.size(); j++) {
      auto output_tensor = predictor_->GetOutputHandle(output_names[j]);
      std::vector<int> output_shape = output_tensor->shape();
-      int out_num = std::accumulate(
+      int out_num = std::accumulate(output_shape.begin(), output_shape.end(), 1,
-          output_shape.begin(), output_shape.end(), 1, std::multiplies<int>());
+                                    std::multiplies<int>());
      output_shape_list.push_back(output_shape);
      if (output_tensor->type() == paddle_infer::DataType::INT32) {
        out_bbox_num_data_.resize(out_num);
@@ -371,22 +355,15 @@ void ObjectDetector::Predict(const std::vector<cv::Mat> imgs,
      if (i == config_.fpn_stride_.size()) {
        reg_max = output_shape_list[i][2] / 4 - 1;
      }
-      float* buffer = new float[out_tensor_list[i].size()];
+      float *buffer = new float[out_tensor_list[i].size()];
-      memcpy(buffer,
+      memcpy(buffer, &out_tensor_list[i][0],
-             &out_tensor_list[i][0],
             out_tensor_list[i].size() * sizeof(float));
      output_data_list_.push_back(buffer);
    }
    PaddleDetection::PicoDetPostProcess(
-        result,
+        result, output_data_list_, config_.fpn_stride_, inputs_.im_shape_,
-        output_data_list_,
+        inputs_.scale_factor_, config_.nms_info_["score_threshold"].as<float>(),
-        config_.fpn_stride_,
+        config_.nms_info_["nms_threshold"].as<float>(), num_class, reg_max);
-        inputs_.im_shape_,
-        inputs_.scale_factor_,
-        config_.nms_info_["score_threshold"].as<float>(),
-        config_.nms_info_["nms_threshold"].as<float>(),
-        num_class,
-        reg_max);
    bbox_num->push_back(result->size());
  } else {
    is_rbox = output_shape_list[0][output_shape_list[0].size() - 1] % 10 == 0;

--- a/deploy/pphuman/datacollector.py
+++ b/deploy/pphuman/datacollector.py
@@ -35,6 +35,9 @@ class Result(object):
            return self.res_dict[name]
        return None
+    def clear(self, name):
+        self.res_dict[name].clear()
 class DataCollector(object):
    """
@@ -80,7 +83,6 @@ class DataCollector(object):
            ids = int(mot_item[0])
            if ids not in self.collector:
                self.collector[ids] = copy.deepcopy(self.mots)
            self.collector[ids]["frames"].append(frameid)
            self.collector[ids]["rects"].append([mot_item[2:]])
            if attr_res:

--- a/deploy/pphuman/mtmct.py
+++ b/deploy/pphuman/mtmct.py
@@ -297,10 +297,9 @@ def distill_idfeat(mot_res):
        feature_new = feature_list
    #if available frames number is more than 200, take one frame data per 20 frames
-    if len(qualities_new) > 200:
+    skipf = 1
-        skipf = 20
+    if len(qualities_new) > 20:
-    else:
+        skipf = 2
-        skipf = max(10, len(qualities_new) // 10)
    quality_skip = np.array(qualities_new[::skipf])
    feature_skip = np.array(feature_new[::skipf])

--- a/deploy/pphuman/pipeline.py
+++ b/deploy/pphuman/pipeline.py
@@ -587,7 +587,7 @@ class PipePredictor(object):
                if self.cfg['visual']:
                    self.action_visual_helper.update(action_res)
-            if self.with_mtmct:
+            if self.with_mtmct and frame_id % 10 == 0:
                crop_input, img_qualities, rects = self.reid_predictor.crop_image_with_mot(
                    frame, mot_res)
                if frame_id > self.warmup_frame:
@@ -603,6 +603,8 @@ class PipePredictor(object):
                    "rects": rects
                }
                self.pipeline_res.update(reid_res_dict, 'reid')
+            else:
+                self.pipeline_res.clear('reid')
            self.collector.append(frame_id, self.pipeline_res)

--- a/deploy/pptracking/python/mot/matching/jde_matching.py
+++ b/deploy/pptracking/python/mot/matching/jde_matching.py
@@ -26,7 +26,7 @@ warnings.filterwarnings("ignore")
 __all__ = [
    'merge_matches',
    'linear_assignment',
-    'cython_bbox_ious',
+    'bbox_ious',
    'iou_distance',
    'embedding_distance',
    'fuse_motion',
@@ -68,22 +68,28 @@ def linear_assignment(cost_matrix, thresh):
    return matches, unmatched_a, unmatched_b
-def cython_bbox_ious(atlbrs, btlbrs):
+def bbox_ious(atlbrs, btlbrs):
-    ious = np.zeros((len(atlbrs), len(btlbrs)), dtype=np.float)
+    boxes = np.ascontiguousarray(atlbrs, dtype=np.float)
-    if ious.size == 0:
+    query_boxes = np.ascontiguousarray(btlbrs, dtype=np.float)
+    N = boxes.shape[0]
+    K = query_boxes.shape[0]
+    ious = np.zeros((N, K), dtype=boxes.dtype)
+    if N * K == 0:
        return ious
-    try:
-        import cython_bbox
+    for k in range(K):
-    except Exception as e:
+        box_area = ((query_boxes[k, 2] - query_boxes[k, 0] + 1) *
-        print('cython_bbox not found, please install cython_bbox.'
+                    (query_boxes[k, 3] - query_boxes[k, 1] + 1))
-              'for example: `pip install cython_bbox`.')
+        for n in range(N):
-        exit()
+            iw = (min(boxes[n, 2], query_boxes[k, 2]) - max(
+                boxes[n, 0], query_boxes[k, 0]) + 1)
-    ious = cython_bbox.bbox_overlaps(
+            if iw > 0:
-        np.ascontiguousarray(
+                ih = (min(boxes[n, 3], query_boxes[k, 3]) - max(
-            atlbrs, dtype=np.float),
+                    boxes[n, 1], query_boxes[k, 1]) + 1)
-        np.ascontiguousarray(
+                if ih > 0:
-            btlbrs, dtype=np.float))
+                    ua = float((boxes[n, 2] - boxes[n, 0] + 1) * (boxes[
+                        n, 3] - boxes[n, 1] + 1) + box_area - iw * ih)
+                    ious[n, k] = iw * ih / ua
    return ious
@@ -98,7 +104,7 @@ def iou_distance(atracks, btracks):
    else:
        atlbrs = [track.tlbr for track in atracks]
        btlbrs = [track.tlbr for track in btracks]
-    _ious = cython_bbox_ious(atlbrs, btlbrs)
+    _ious = bbox_ious(atlbrs, btlbrs)
    cost_matrix = 1 - _ious
    return cost_matrix

--- a/deploy/python/infer.py
+++ b/deploy/python/infer.py
@@ -231,7 +231,7 @@ class Detector(object):
                self.det_times.preprocess_time_s.end()
                # model prediction
-                result = self.predict(repeats=repeats)  # warmup
+                result = self.predict(repeats=50)  # warmup
                self.det_times.inference_time_s.start()
                result = self.predict(repeats=repeats)
                self.det_times.inference_time_s.end(repeats=repeats)
@@ -296,7 +296,7 @@ class Detector(object):
        if not os.path.exists(self.output_dir):
            os.makedirs(self.output_dir)
        out_path = os.path.join(self.output_dir, video_out_name)
-        fourcc = cv2.VideoWriter_fourcc(* 'mp4v')
+        fourcc = cv2.VideoWriter_fourcc(*'mp4v')
        writer = cv2.VideoWriter(out_path, fourcc, fps, (width, height))
        index = 1
        while (1):
@@ -790,7 +790,7 @@ def main():
        if FLAGS.image_dir is None and FLAGS.image_file is not None:
            assert FLAGS.batch_size == 1, "batch_size should be 1, when image_file is not None"
        img_list = get_test_images(FLAGS.image_dir, FLAGS.image_file)
-        detector.predict_image(img_list, FLAGS.run_benchmark, repeats=10)
+        detector.predict_image(img_list, FLAGS.run_benchmark, repeats=100)
        if not FLAGS.run_benchmark:
            detector.det_times.info(average=True)
        else:

--- a/ppdet/metrics/mcmot_metrics.py
+++ b/ppdet/metrics/mcmot_metrics.py
@@ -306,11 +306,12 @@ class MCMOTEvaluator(object):
    def load_annotations(self):
        assert self.data_type == 'mcmot'
-        self.gt_filename = os.path.join(self.data_root, '../',
+        self.gt_filename = os.path.join(self.data_root, '../', 'sequences',
-                                        'sequences',
                                        '{}.txt'.format(self.seq_name))
        if not os.path.exists(self.gt_filename):
-            logger.warning("gt_filename '{}' of MCMOTEvaluator is not exist, so the MOTA will be -inf.")
+            logger.warning(
+                "gt_filename '{}' of MCMOTEvaluator is not exist, so the MOTA will be -INF."
+            )
    def reset_accumulator(self):
        import motmetrics as mm

--- a/ppdet/metrics/mot_metrics.py
+++ b/ppdet/metrics/mot_metrics.py
@@ -37,8 +37,11 @@ __all__ = ['MOTEvaluator', 'MOTMetric', 'JDEDetMetric', 'KITTIMOTMetric']
 def read_mot_results(filename, is_gt=False, is_ignore=False):
    valid_label = [1]
    ignore_labels = [2, 7, 8, 12]  # only in motchallenge datasets like 'MOT16'
-    logger.info("In MOT16/17 dataset the valid_label of ground truth is '{}', "
+    if is_gt:
-        "in other dataset it should be '0' for single classs MOT.".format(valid_label[0]))
+        logger.info(
+            "In MOT16/17 dataset the valid_label of ground truth is '{}', "
+            "in other dataset it should be '0' for single classs MOT.".format(
+                valid_label[0]))
    results_dict = dict()
    if os.path.isfile(filename):
        with open(filename, 'r') as f:
@@ -118,7 +121,9 @@ class MOTEvaluator(object):
        gt_filename = os.path.join(self.data_root, self.seq_name, 'gt',
                                   'gt.txt')
        if not os.path.exists(gt_filename):
-            logger.warning("gt_filename '{}' of MOTEvaluator is not exist, so the MOTA will be -inf.")
+            logger.warning(
+                "gt_filename '{}' of MOTEvaluator is not exist, so the MOTA will be -INF."
+            )
        self.gt_frame_dict = read_mot_results(gt_filename, is_gt=True)
        self.gt_ignore_frame_dict = read_mot_results(
            gt_filename, is_ignore=True)

--- a/ppdet/modeling/architectures/meta_arch.py
+++ b/ppdet/modeling/architectures/meta_arch.py
@@ -22,22 +22,23 @@ class BaseArch(nn.Layer):
        self.fuse_norm = False
    def load_meanstd(self, cfg_transform):
-        self.scale = 1.
+        scale = 1.
-        self.mean = paddle.to_tensor([0.485, 0.456, 0.406]).reshape(
+        mean = np.array([0.485, 0.456, 0.406], dtype=np.float32)
-            (1, 3, 1, 1))
+        std = np.array([0.229, 0.224, 0.225], dtype=np.float32)
-        self.std = paddle.to_tensor([0.229, 0.224, 0.225]).reshape((1, 3, 1, 1))
        for item in cfg_transform:
            if 'NormalizeImage' in item:
-                self.mean = paddle.to_tensor(item['NormalizeImage'][
+                mean = np.array(
-                    'mean']).reshape((1, 3, 1, 1))
+                    item['NormalizeImage']['mean'], dtype=np.float32)
-                self.std = paddle.to_tensor(item['NormalizeImage'][
+                std = np.array(item['NormalizeImage']['std'], dtype=np.float32)
-                    'std']).reshape((1, 3, 1, 1))
                if item['NormalizeImage'].get('is_scale', True):
-                    self.scale = 1. / 255.
+                    scale = 1. / 255.
                break
        if self.data_format == 'NHWC':
-            self.mean = self.mean.reshape(1, 1, 1, 3)
+            self.scale = paddle.to_tensor(scale / std).reshape((1, 1, 1, 3))
-            self.std = self.std.reshape(1, 1, 1, 3)
+            self.bias = paddle.to_tensor(-mean / std).reshape((1, 1, 1, 3))
+        else:
+            self.scale = paddle.to_tensor(scale / std).reshape((1, 3, 1, 1))
+            self.bias = paddle.to_tensor(-mean / std).reshape((1, 3, 1, 1))
    def forward(self, inputs):
        if self.data_format == 'NHWC':
@@ -46,7 +47,7 @@ class BaseArch(nn.Layer):
        if self.fuse_norm:
            image = inputs['image']
-            self.inputs['image'] = (image * self.scale - self.mean) / self.std
+            self.inputs['image'] = image * self.scale + self.bias
            self.inputs['im_shape'] = inputs['im_shape']
            self.inputs['scale_factor'] = inputs['scale_factor']
        else:
@@ -66,8 +67,7 @@ class BaseArch(nn.Layer):
            outs = []
            for inp in inputs_list:
                if self.fuse_norm:
-                    self.inputs['image'] = (
+                    self.inputs['image'] = inp['image'] * self.scale + self.bias
-                        inp['image'] * self.scale - self.mean) / self.std
                    self.inputs['im_shape'] = inp['im_shape']
                    self.inputs['scale_factor'] = inp['scale_factor']
                else:
@@ -75,7 +75,7 @@ class BaseArch(nn.Layer):
                outs.append(self.get_pred())
            # multi-scale test
-            if len(outs)>1:
+            if len(outs) > 1:
                out = self.merge_multi_scale_predictions(outs)
            else:
                out = outs[0]
@@ -92,7 +92,9 @@ class BaseArch(nn.Layer):
            keep_top_k = self.bbox_post_process.nms.keep_top_k
            nms_threshold = self.bbox_post_process.nms.nms_threshold
        else:
-            raise Exception("Multi scale test only supports CascadeRCNN, FasterRCNN and MaskRCNN for now")
+            raise Exception(
+                "Multi scale test only supports CascadeRCNN, FasterRCNN and MaskRCNN for now"
+            )
        final_boxes = []
        all_scale_outs = paddle.concat([o['bbox'] for o in outs]).numpy()
@@ -101,9 +103,11 @@ class BaseArch(nn.Layer):
            if np.count_nonzero(idxs) == 0:
                continue
            r = nms(all_scale_outs[idxs, 1:], nms_threshold)
-            final_boxes.append(np.concatenate([np.full((r.shape[0], 1), c), r], 1))
+            final_boxes.append(
+                np.concatenate([np.full((r.shape[0], 1), c), r], 1))
        out = np.concatenate(final_boxes)
-        out = np.concatenate(sorted(out, key=lambda e: e[1])[-keep_top_k:]).reshape((-1, 6))
+        out = np.concatenate(sorted(
+            out, key=lambda e: e[1])[-keep_top_k:]).reshape((-1, 6))
        out = {
            'bbox': paddle.to_tensor(out),
            'bbox_num': paddle.to_tensor(np.array([out.shape[0], ]))

--- a/ppdet/modeling/assigners/atss_assigner.py
+++ b/ppdet/modeling/assigners/atss_assigner.py
@@ -199,7 +199,11 @@ class ATSSAssigner(nn.Layer):
            gt_bboxes.reshape([-1, 4]), assigned_gt_index.flatten(), axis=0)
        assigned_bboxes = assigned_bboxes.reshape([batch_size, num_anchors, 4])
-        assigned_scores = F.one_hot(assigned_labels, self.num_classes)
+        assigned_scores = F.one_hot(assigned_labels, self.num_classes + 1)
+        ind = list(range(self.num_classes + 1))
+        ind.remove(bg_index)
+        assigned_scores = paddle.index_select(
+            assigned_scores, paddle.to_tensor(ind), axis=-1)
        if pred_bboxes is not None:
            # assigned iou
            ious = batch_iou_similarity(gt_bboxes, pred_bboxes) * mask_positive

--- a/ppdet/modeling/assigners/task_aligned_assigner.py
+++ b/ppdet/modeling/assigners/task_aligned_assigner.py
@@ -143,7 +143,11 @@ class TaskAlignedAssigner(nn.Layer):
            gt_bboxes.reshape([-1, 4]), assigned_gt_index.flatten(), axis=0)
        assigned_bboxes = assigned_bboxes.reshape([batch_size, num_anchors, 4])
-        assigned_scores = F.one_hot(assigned_labels, num_classes)
+        assigned_scores = F.one_hot(assigned_labels, num_classes + 1)
+        ind = list(range(num_classes + 1))
+        ind.remove(bg_index)
+        assigned_scores = paddle.index_select(
+            assigned_scores, paddle.to_tensor(ind), axis=-1)
        # rescale alignment metrics
        alignment_metrics *= mask_positive
        max_metrics_per_instance = alignment_metrics.max(axis=-1, keepdim=True)

--- a/ppdet/modeling/heads/ppyoloe_head.py
+++ b/ppdet/modeling/heads/ppyoloe_head.py
@@ -331,7 +331,8 @@ class PPYOLOEHead(nn.Layer):
        assigned_bboxes /= stride_tensor
        # cls loss
        if self.use_varifocal_loss:
-            one_hot_label = F.one_hot(assigned_labels, self.num_classes)
+            one_hot_label = F.one_hot(assigned_labels,
+                                      self.num_classes + 1)[..., :-1]
            loss_cls = self._varifocal_loss(pred_scores, assigned_scores,
                                            one_hot_label)
        else:

--- a/ppdet/modeling/losses/detr_loss.py
+++ b/ppdet/modeling/losses/detr_loss.py
@@ -80,7 +80,7 @@ class DETRLoss(nn.Layer):
            target_label = target_label.reshape([bs, num_query_objects])
        if self.use_focal_loss:
            target_label = F.one_hot(target_label,
-                                     self.num_classes + 1)[:, :, :-1]
+                                     self.num_classes + 1)[..., :-1]
        return {
            'loss_class': self.loss_coeff['class'] * sigmoid_focal_loss(
                logits, target_label, num_gts / num_query_objects)

--- a/ppdet/modeling/mot/matching/jde_matching.py
+++ b/ppdet/modeling/mot/matching/jde_matching.py
@@ -26,7 +26,7 @@ warnings.filterwarnings("ignore")
 __all__ = [
    'merge_matches',
    'linear_assignment',
-    'cython_bbox_ious',
+    'bbox_ious',
    'iou_distance',
    'embedding_distance',
    'fuse_motion',
@@ -68,22 +68,28 @@ def linear_assignment(cost_matrix, thresh):
    return matches, unmatched_a, unmatched_b
-def cython_bbox_ious(atlbrs, btlbrs):
+def bbox_ious(atlbrs, btlbrs):
-    ious = np.zeros((len(atlbrs), len(btlbrs)), dtype=np.float)
+    boxes = np.ascontiguousarray(atlbrs, dtype=np.float)
-    if ious.size == 0:
+    query_boxes = np.ascontiguousarray(btlbrs, dtype=np.float)
+    N = boxes.shape[0]
+    K = query_boxes.shape[0]
+    ious = np.zeros((N, K), dtype=boxes.dtype)
+    if N * K == 0:
        return ious
-    try:
-        import cython_bbox
+    for k in range(K):
-    except Exception as e:
+        box_area = ((query_boxes[k, 2] - query_boxes[k, 0] + 1) *
-        print('cython_bbox not found, please install cython_bbox.'
+                    (query_boxes[k, 3] - query_boxes[k, 1] + 1))
-                     'for example: `pip install cython_bbox`.')
+        for n in range(N):
-        raise e
+            iw = (min(boxes[n, 2], query_boxes[k, 2]) - max(
+                boxes[n, 0], query_boxes[k, 0]) + 1)
-    ious = cython_bbox.bbox_overlaps(
+            if iw > 0:
-        np.ascontiguousarray(
+                ih = (min(boxes[n, 3], query_boxes[k, 3]) - max(
-            atlbrs, dtype=np.float),
+                    boxes[n, 1], query_boxes[k, 1]) + 1)
-        np.ascontiguousarray(
+                if ih > 0:
-            btlbrs, dtype=np.float))
+                    ua = float((boxes[n, 2] - boxes[n, 0] + 1) * (boxes[
+                        n, 3] - boxes[n, 1] + 1) + box_area - iw * ih)
+                    ious[n, k] = iw * ih / ua
    return ious
@@ -98,7 +104,7 @@ def iou_distance(atracks, btracks):
    else:
        atlbrs = [track.tlbr for track in atracks]
        btlbrs = [track.tlbr for track in btracks]
-    _ious = cython_bbox_ious(atlbrs, btlbrs)
+    _ious = bbox_ious(atlbrs, btlbrs)
    cost_matrix = 1 - _ious
    return cost_matrix

--- a/requirements.txt
+++ b/requirements.txt
@@ -14,4 +14,3 @@ lap
 sklearn
 motmetrics
 openpyxl
-cython_bbox