From 5019c3bccf7734aef7b4c971288a89cdab73e900 Mon Sep 17 00:00:00 2001 From: Feng Ni Date: Tue, 28 Jun 2022 18:13:14 +0800 Subject: [PATCH] fix pphuman cfg doc (#6288) * fix pphuman cfg doc, test=document_fix * fix doc, test=document_fix * remove en readme doc, test=document_fix --- deploy/pphuman/README.md | 20 +- deploy/pphuman/README_en.md | 176 ------------------ .../pphuman/docs/tutorials/QUICK_STARTED.md | 33 ++-- deploy/pphuman/docs/tutorials/action.md | 10 +- deploy/pphuman/docs/tutorials/action_en.md | 10 +- deploy/pphuman/docs/tutorials/attribute.md | 13 +- deploy/pphuman/docs/tutorials/attribute_en.md | 13 +- deploy/pphuman/docs/tutorials/mot.md | 12 +- deploy/pphuman/docs/tutorials/mot_en.md | 12 +- deploy/pphuman/docs/tutorials/mtmct.md | 8 +- deploy/pphuman/docs/tutorials/mtmct_en.md | 8 +- deploy/pphuman/pipeline.py | 25 +-- 12 files changed, 83 insertions(+), 257 deletions(-) delete mode 100644 deploy/pphuman/README_en.md diff --git a/deploy/pphuman/README.md b/deploy/pphuman/README.md index 7c837f093..c2e7a9914 100644 --- a/deploy/pphuman/README.md +++ b/deploy/pphuman/README.md @@ -25,14 +25,18 @@ PP-Human支持图片/单镜头视频/多镜头视频多种输入方式，功能 ## 🗳 模型库 -| 任务 | 适用场景 | 精度 | 预测速度（ms） | 模型权重 | 预测部署模型 | -|:-----:|:------------:|:---------- |:--------:|:----------------------------------------------------------------------------------------------:|:--------------------------------------------------------------------------------------------:| -| 目标检测 | 图片输入 | mAP: 56.3 | 28.0ms | [下载链接](https://bj.bcebos.com/v1/paddledet/models/pipeline/mot_ppyoloe_l_36e_pipeline.pdparams) | [下载链接](https://bj.bcebos.com/v1/paddledet/models/pipeline/mot_ppyoloe_l_36e_pipeline.zip) | -| 目标跟踪 | 视频输入 | MOTA: 72.0 | 33.1ms | [下载链接](https://bj.bcebos.com/v1/paddledet/models/pipeline/mot_ppyoloe_l_36e_pipeline.pdparams) | [下载链接](https://bj.bcebos.com/v1/paddledet/models/pipeline/mot_ppyoloe_l_36e_pipeline.zip) | -| 属性识别 | 图片/视频输入 属性识别 | mA: 94.86 | 单人2ms | - | [下载链接](https://bj.bcebos.com/v1/paddledet/models/pipeline/strongbaseline_r50_30e_pa100k.zip) | -| 关键点检测 | 视频输入 行为识别 | AP: 87.1 | 单人2.9ms | [下载链接](https://bj.bcebos.com/v1/paddledet/models/pipeline/dark_hrnet_w32_256x192.pdparams) | [下载链接](https://bj.bcebos.com/v1/paddledet/models/pipeline/dark_hrnet_w32_256x192.zip) | -| 行为识别 | 视频输入 行为识别 | 准确率: 96.43 | 单人2.7ms | - | [下载链接](https://bj.bcebos.com/v1/paddledet/models/pipeline/STGCN.zip) | -| ReID | 视频输入 跨镜跟踪 | mAP: 98.8 | 单人1.5ms | - | [下载链接](https://bj.bcebos.com/v1/paddledet/models/pipeline/reid_model.zip) | +| 任务 | 适用场景 | 精度 | 预测速度（ms） | 模型权重 | 预测部署模型 | +| :---------: |:---------: |:--------------- | :-------: | :------: | :------: | +| 目标检测(高精度) | 图片输入 | mAP: 56.6 | 28.0ms |[下载链接](https://bj.bcebos.com/v1/paddledet/models/pipeline/mot_ppyoloe_l_36e_pipeline.pdparams) |[下载链接](https://bj.bcebos.com/v1/paddledet/models/pipeline/mot_ppyoloe_l_36e_pipeline.zip) | +| 目标检测(轻量级) | 图片输入 | mAP: 53.2 | 22.1ms |[下载链接](https://bj.bcebos.com/v1/paddledet/models/pipeline/mot_ppyoloe_s_36e_pipeline.pdparams) |[下载链接](https://bj.bcebos.com/v1/paddledet/models/pipeline/mot_ppyoloe_s_36e_pipeline.zip) | +| 目标跟踪(高精度) | 视频输入 | MOTA: 79.5 | 33.1ms |[下载链接](https://bj.bcebos.com/v1/paddledet/models/pipeline/mot_ppyoloe_l_36e_pipeline.pdparams) |[下载链接](https://bj.bcebos.com/v1/paddledet/models/pipeline/mot_ppyoloe_l_36e_pipeline.zip) | +| 目标跟踪(轻量级) | 视频输入 | MOTA: 69.1 | 27.2ms |[下载链接](https://bj.bcebos.com/v1/paddledet/models/pipeline/mot_ppyoloe_s_36e_pipeline.pdparams) |[下载链接](https://bj.bcebos.com/v1/paddledet/models/pipeline/mot_ppyoloe_s_36e_pipeline.zip) | +| 属性识别 | 图片/视频输入 属性识别 | mA: 94.86 | 单人2ms | - |[下载链接](https://bj.bcebos.com/v1/paddledet/models/pipeline/strongbaseline_r50_30e_pa100k.zip) | +| 关键点检测 | 视频输入 行为识别 | AP: 87.1 | 单人2.9ms |[下载链接](https://bj.bcebos.com/v1/paddledet/models/pipeline/dark_hrnet_w32_256x192.pdparams) |[下载链接](https://bj.bcebos.com/v1/paddledet/models/pipeline/dark_hrnet_w32_256x192.zip) +| 行为识别 | 视频输入 行为识别 | 准确率: 96.43 | 单人2.7ms | - |[下载链接](https://bj.bcebos.com/v1/paddledet/models/pipeline/STGCN.zip) | +| ReID | 视频输入 跨镜跟踪 | mAP: 98.8 | 单人1.5ms | - |[下载链接](https://bj.bcebos.com/v1/paddledet/models/pipeline/reid_model.zip) | + +下载预测部署模型并解压存放至`./output_inference`新建目录中 ## 📚 文档教程 diff --git a/deploy/pphuman/README_en.md b/deploy/pphuman/README_en.md deleted file mode 100644 index 1138ae0f8..000000000 --- a/deploy/pphuman/README_en.md +++ /dev/null @@ -1,176 +0,0 @@ -English | [简体中文](README.md) - -# PP-Human— a Real-Time Pedestrian Analysis Tool - -PP-Human serves as the first open-source tool of real-time pedestrian anaylsis relying on the PaddlePaddle deep learning framework. Versatile and efficient in deployment, it has been used in various senarios. PP-Human -offers many input options, including image/single-camera video/multi-camera video, and covers multi-object tracking, attribute recognition, and action recognition. PP-Human can be applied to intelligent traffic, the intelligent community, industiral patrol, and so on. It supports server-side deployment and TensorRT acceleration，and achieves real-time analysis on the T4 server. - -Community intelligent management supportted by PP-Human, please refer to this [AI Studio project](https://aistudio.baidu.com/aistudio/projectdetail/3679564) for quick start tutorial. - -Full-process operation tutorial of PP-Human, covering training, deployment, action expansion, please refer to this [AI Studio project](https://aistudio.baidu.com/aistudio/projectdetail/3842982). - -## I. Environment Preparation - -Requirement: PaddleDetection version >= release/2.4 or develop - - -The installation of PaddlePaddle and PaddleDetection - -``` -# PaddlePaddle CUDA10.1 -python -m pip install paddlepaddle-gpu==2.2.2.post101 -f https://www.paddlepaddle.org.cn/whl/linux/mkl/avx/stable.html - -# PaddlePaddle CPU -python -m pip install paddlepaddle -i https://mirror.baidu.com/pypi/simple - -# Clone the PaddleDetection repository -cd -git clone https://github.com/PaddlePaddle/PaddleDetection.git - -# Install other dependencies -cd PaddleDetection -pip install -r requirements.txt -``` - -1. For details of the installation, please refer to this [document](../../docs/tutorials/INSTALL.md) -2. Please install `Paddle-TensorRT` if your want speedup inference by TensorRT. You can download the whl package from [Paddle-whl-list](https://paddleinference.paddlepaddle.org.cn/v2.2/user_guides/download_lib.html#python), or prepare the envs by yourself follows the [Install-Guide](https://www.paddlepaddle.org.cn/inference/master/optimize/paddle_trt.html). - -## II. Quick Start - -### 1. Model Download - -To make users have access to models of different scenarios, PP-Human provides pre-trained models of object detection, attribute recognition， behavior recognition, and ReID. - -| Task | Scenario | Precision | Inference Speed（FPS） | Model Weights |Model Inference and Deployment | -| :---------: |:---------: |:--------------- | :-------: | :------: | :------: | -| Object Detection(high-precision) | Image/Video Input | mAP: 56.6 | 28.0ms |[Link](https://bj.bcebos.com/v1/paddledet/models/pipeline/mot_ppyoloe_l_36e_pipeline.pdparams) |[Link](https://bj.bcebos.com/v1/paddledet/models/pipeline/mot_ppyoloe_l_36e_pipeline.zip) | -| Object Detection(light-weight) | Image/Video Input | mAP: 53.2 | 22.1ms |[Link](https://bj.bcebos.com/v1/paddledet/models/pipeline/mot_ppyoloe_s_36e_pipeline.pdparams) |[Link](https://bj.bcebos.com/v1/paddledet/models/pipeline/mot_ppyoloe_s_36e_pipeline.zip) | -| Object Tracking(high-precision) | Image/Video Input | MOTA: 79.5 | 33.1ms |[Link](https://bj.bcebos.com/v1/paddledet/models/pipeline/mot_ppyoloe_l_36e_pipeline.pdparams) |[Link](https://bj.bcebos.com/v1/paddledet/models/pipeline/mot_ppyoloe_l_36e_pipeline.zip) | -| Object Tracking(light-weight) | Image/Video Input | MOTA: 69.1 | 27.2ms |[Link](https://bj.bcebos.com/v1/paddledet/models/pipeline/mot_ppyoloe_s_36e_pipeline.pdparams) |[Link](https://bj.bcebos.com/v1/paddledet/models/pipeline/mot_ppyoloe_s_36e_pipeline.zip) | -| Attribute Recognition | Image/Video Input Attribute Recognition | mA: 94.86 | 2ms per person | - |[Link](https://bj.bcebos.com/v1/paddledet/models/pipeline/strongbaseline_r50_30e_pa100k.zip) | -| Keypoint Detection | Video Input Falling Recognition | AP: 87.1 | 2.9ms per person | [Link](https://bj.bcebos.com/v1/paddledet/models/pipeline/dark_hrnet_w32_256x192.pdparams) |[Link](https://bj.bcebos.com/v1/paddledet/models/pipeline/dark_hrnet_w32_256x192.zip) -| Falling Recognition | Video Input Falling Recognition | Precision 96.43 | 2.7ms per person | - |[Link](https://bj.bcebos.com/v1/paddledet/models/pipeline/STGCN.zip) | -| ReID | Multi-Target Multi-Camera Tracking | mAP: 98.8 | 1.5ms per person | - |[Link](https://bj.bcebos.com/v1/paddledet/models/pipeline/reid_model.zip) | - -Then, unzip the downloaded model to the folder `./output_inference`. - -**Note: ** - -- The model precision is decided by the fusion of datasets which include open-source datasets and enterprise ones. -- The precision on ReID model is evaluated on Market1501. -- The inference speed is tested on T4, using TensorRT FP16. The pipeline of preprocess, prediction and postprocess is included. - -### 2. Preparation of Configuration Files - -Configuration files of PP-Human are stored in ```deploy/pphuman/config/infer_cfg.yml```. Different tasks are for different functions, so you need to set the task type beforhand. - -Their correspondence is as follows: - -| Input | Function | Task Type | Config | -|-------|-------|----------|-----| -| Image | Attribute Recognition | Object Detection Attribute Recognition | DET ATTR | -| Single-Camera Video | Attribute Recognition | Multi-Object Tracking Attribute Recognition | MOT ATTR | -| Single-Camera Video | Behavior Recognition | Multi-Object Tracking Keypoint Detection Falling Recognition | MOT KPT SKELETON_ACTION | - -For example, for the attribute recognition with the video input, its task types contain multi-object tracking and attribute recognition, and the config is: - -``` -crop_thresh: 0.5 -attr_thresh: 0.5 -visual: True - -MOT: - model_dir: output_inference/mot_ppyoloe_l_36e_pipeline/ - tracker_config: deploy/pphuman/config/tracker_config.yml - batch_size: 1 - -ATTR: - model_dir: output_inference/strongbaseline_r50_30e_pa100k/ - batch_size: 8 -``` - -**Note: ** - -- For different tasks, users should set the "enable" to "True" in coresponding configs in the infer_cfg.yml file. -- if only need to change the model path, users could add `--model_dir det=ppyoloe/` in command line and do not need to set config file. For details info please refer to doc below. - - -### 3. Inference and Deployment - -``` -# Pedestrian detection. Specify the config file path and test images -python deploy/pphuman/pipeline.py --config deploy/pphuman/config/infer_cfg.yml --image_file=test_image.jpg --device=gpu [--run_mode trt_fp16] - -# Pedestrian tracking. Specify the config file path and test videos -python deploy/pphuman/pipeline.py --config deploy/pphuman/config/infer_cfg.yml --video_file=test_video.mp4 --device=gpu [--run_mode trt_fp16] - -# Pedestrian tracking. Specify the config file path, the model path and test videos -# The model path specified on the command line prioritizes over the config file -python deploy/pphuman/pipeline.py --config deploy/pphuman/config/infer_cfg.yml --video_file=test_video.mp4 --device=gpu --model_dir det=ppyoloe/ [--run_mode trt_fp16] - -# Attribute recognition. Specify the config file path and test videos, and set the "enable" to "True" in ATTR of infer_cfg.yml -python deploy/pphuman/pipeline.py --config deploy/pphuman/config/infer_cfg.yml --video_file=test_video.mp4 --device=gpu [--run_mode trt_fp16] - -# Action Recognition. Specify the config file path and test videos, and set the "enable" to "True" in corresponding action configs of infer_cfg.yml -python deploy/pphuman/pipeline.py --config deploy/pphuman/config/infer_cfg.yml --video_file=test_video.mp4 --device=gpu [--run_mode trt_fp16] - -# Pedestrian Multi-Target Multi-Camera tracking. Specify the config file path and the directory of test videos, and set the "enable" to "True" in REID in infer_cfg.yml -python deploy/pphuman/pipeline.py --config deploy/pphuman/config/infer_cfg.yml --video_dir=mtmct_dir/ --device=gpu [--run_mode trt_fp16] - -``` - -Other usage please refer to [sub-task docs](./docs) - -### 3.1 Description of Parameters - -| Parameter | Optional or not| Meaning | -|-------|-------|----------| -| --config | Yes | Config file path | -| --model_dir | Option | the model paths of different tasks in PP-Human, with a priority higher than config files. For example, `--model_dir det=better_det/ attr=better_attr/` | -| --image_file | Option | Images to-be-predicted | -| --image_dir | Option | The path of folders of to-be-predicted images | -| --video_file | Option | Videos to-be-predicted | -| --camera_id | Option | ID of the inference camera is -1 by default (means inference without cameras，and it can be set to 0 - (number of cameras-1)), and during the inference, click `q` on the visual interface to exit and output the inference result to output/output.mp4| -| --device | Option | During the operation，available devices are `CPU/GPU/XPU`，and the default is `CPU`| -| --output_dir | Option| The default root directory which stores the visualization result is output/| -| --run_mode | Option | When using GPU，the default one is paddle, and all these are available（paddle/trt_fp32/trt_fp16/trt_int8）.| -| --enable_mkldnn | Option |Enable the MKLDNN acceleration or not in the CPU inference, and the default value is false | -| --cpu_threads | Option| The default CPU thread is 1 | -| --trt_calib_mode | Option| Enable calibration on TensorRT or not, and the default is False. When using the int8 of TensorRT，it should be set to True; When using the model quantized by PaddleSlim, it should be set to False. | - - -## III. Introduction to the Solution - -The overall solution of PP-Human is as follows: - -
- -
- - -### 1. Object Detection -- Use PP-YOLOE L as the model of object detection -- For details, please refer to [PP-YOLOE](../../configs/ppyoloe/) and [Detection and Tracking](docs/mot_en.md) - -### 2. Multi-Object Tracking -- Conduct multi-object tracking with the SDE solution -- Use PP-YOLOE L as the detection model -- Use the Bytetrack solution to track modules -- For details, refer to [Bytetrack](configs/mot/bytetrack) and [Detection and Tracking](docs/mot_en.md) - -### 3. Multi-Camera Tracking -- Use PP-YOLOE + Bytetrack to obtain the tracks of single-camera multi-object tracking -- Use ReID（centroid network）to extract features of the detection result of each frame -- Match the features of multi-camera tracks to get the cross-camera tracking result -- For details, please refer to [Multi-Camera Tracking](docs/mtmct_en.md) - -### 4. Attribute Recognition -- Use PP-YOLOE + Bytetrack to track humans -- Use StrongBaseline（a multi-class model）to conduct attribute recognition, and the main attributes include age, gender, hats, eyes, clothing, and backpacks. -- For details, please refer to [Attribute Recognition](docs/attribute_en.md) - -### 5. Falling Recognition -- Use PP-YOLOE + Bytetrack to track humans -- Use HRNet for keypoint detection and get the information of the 17 key points in the human body -- According to the changes of the key points of the same person within 50 frames, judge whether the action made by the person within 50 frames is a fall with the help of ST-GCN -- For details, please refer to [Falling Recognition](docs/action_en.md) diff --git a/deploy/pphuman/docs/tutorials/QUICK_STARTED.md b/deploy/pphuman/docs/tutorials/QUICK_STARTED.md index b6b5ff071..32818c3f2 100644 --- a/deploy/pphuman/docs/tutorials/QUICK_STARTED.md +++ b/deploy/pphuman/docs/tutorials/QUICK_STARTED.md @@ -31,8 +31,10 @@ PP-Human提供了目标检测、属性识别、行为识别、ReID预训练模 | 任务 | 适用场景 | 精度 | 预测速度（ms） | 模型权重 | 预测部署模型 | | :---------: |:---------: |:--------------- | :-------: | :------: | :------: | -| 目标检测 | 图片输入 | mAP: 56.3 | 28.0ms |[下载链接](https://bj.bcebos.com/v1/paddledet/models/pipeline/mot_ppyoloe_l_36e_pipeline.pdparams) |[下载链接](https://bj.bcebos.com/v1/paddledet/models/pipeline/mot_ppyoloe_l_36e_pipeline.zip) | -| 目标跟踪 | 视频输入 | MOTA: 72.0 | 33.1ms |[下载链接](https://bj.bcebos.com/v1/paddledet/models/pipeline/mot_ppyoloe_l_36e_pipeline.pdparams) |[下载链接](https://bj.bcebos.com/v1/paddledet/models/pipeline/mot_ppyoloe_l_36e_pipeline.zip) | +| 目标检测(高精度) | 图片输入 | mAP: 56.6 | 28.0ms |[下载链接](https://bj.bcebos.com/v1/paddledet/models/pipeline/mot_ppyoloe_l_36e_pipeline.pdparams) |[下载链接](https://bj.bcebos.com/v1/paddledet/models/pipeline/mot_ppyoloe_l_36e_pipeline.zip) | +| 目标检测(轻量级) | 图片输入 | mAP: 53.2 | 22.1ms |[下载链接](https://bj.bcebos.com/v1/paddledet/models/pipeline/mot_ppyoloe_s_36e_pipeline.pdparams) |[下载链接](https://bj.bcebos.com/v1/paddledet/models/pipeline/mot_ppyoloe_s_36e_pipeline.zip) | +| 目标跟踪(高精度) | 视频输入 | MOTA: 79.5 | 33.1ms |[下载链接](https://bj.bcebos.com/v1/paddledet/models/pipeline/mot_ppyoloe_l_36e_pipeline.pdparams) |[下载链接](https://bj.bcebos.com/v1/paddledet/models/pipeline/mot_ppyoloe_l_36e_pipeline.zip) | +| 目标跟踪(轻量级) | 视频输入 | MOTA: 69.1 | 27.2ms |[下载链接](https://bj.bcebos.com/v1/paddledet/models/pipeline/mot_ppyoloe_s_36e_pipeline.pdparams) |[下载链接](https://bj.bcebos.com/v1/paddledet/models/pipeline/mot_ppyoloe_s_36e_pipeline.zip) | | 属性识别 | 图片/视频输入 属性识别 | mA: 94.86 | 单人2ms | - |[下载链接](https://bj.bcebos.com/v1/paddledet/models/pipeline/strongbaseline_r50_30e_pa100k.zip) | | 关键点检测 | 视频输入 行为识别 | AP: 87.1 | 单人2.9ms |[下载链接](https://bj.bcebos.com/v1/paddledet/models/pipeline/dark_hrnet_w32_256x192.pdparams) |[下载链接](https://bj.bcebos.com/v1/paddledet/models/pipeline/dark_hrnet_w32_256x192.zip) | 行为识别 | 视频输入 行为识别 | 准确率: 96.43 | 单人2.7ms | - |[下载链接](https://bj.bcebos.com/v1/paddledet/models/pipeline/STGCN.zip) | @@ -48,7 +50,7 @@ PP-Human提供了目标检测、属性识别、行为识别、ReID预训练模 ## 三、配置文件说明 -PP-Human相关配置位于```deploy/pphuman/config/infer_cfg.yml```中，存放模型路径，完成不同功能需要设置不同的任务类型 +PP-Human相关配置位于```deploy/pphuman/config/infer_cfg_pphuman.yml```中，存放模型路径，完成不同功能需要设置不同的任务类型 功能及任务类型对应表单如下： @@ -70,6 +72,7 @@ MOT: tracker_config: deploy/pphuman/config/tracker_config.yml batch_size: 1 basemode: "idbased" + enable: False ATTR: model_dir: output_inference/strongbaseline_r50_30e_pa100k/ @@ -81,30 +84,30 @@ ATTR: **注意：** - 如果用户需要实现不同任务，可以在配置文件对应enable选项设置为True, 其basemode类型会在代码中开启依赖的基础能力模型，比如跟踪模型。 -- 如果用户仅需要修改模型文件路径，可以在命令行中加入 `--model_dir det=ppyoloe/` 即可，无需修改配置文件，详细说明参考下方参数说明文档 +- 如果用户仅需要修改模型文件路径，可以在命令行中加入 `--model_dir det=ppyoloe/` 即可，也可以手动修改配置文件中的相应模型路径，详细说明参考下方参数说明文档。 ### 四、预测部署 ``` # 行人检测，指定配置文件路径和测试图片 -python deploy/pphuman/pipeline.py --config deploy/pphuman/config/infer_cfg.yml --image_file=test_image.jpg --device=gpu [--run_mode trt_fp16] +python deploy/pphuman/pipeline.py --config deploy/pphuman/config/infer_cfg_pphuman.yml --image_file=test_image.jpg --device=gpu [--run_mode trt_fp16] -# 行人跟踪，指定配置文件路径和测试视频 -python deploy/pphuman/pipeline.py --config deploy/pphuman/config/infer_cfg.yml --video_file=test_video.mp4 --device=gpu [--run_mode trt_fp16] +# 行人跟踪，指定配置文件路径和测试视频，在配置文件中```deploy/pphuman/config/infer_cfg_pphuman.yml```中的MOT部分enable设置为```True``` +python deploy/pphuman/pipeline.py --config deploy/pphuman/config/infer_cfg_pphuman.yml --video_file=test_video.mp4 --device=gpu [--run_mode trt_fp16] -# 行人跟踪，指定配置文件路径，模型路径和测试视频 +# 行人跟踪，指定配置文件路径，模型路径和测试视频，在配置文件中```deploy/pphuman/config/infer_cfg_pphuman.yml```中的MOT部分enable设置为```True``` # 命令行中指定的模型路径优先级高于配置文件 -python deploy/pphuman/pipeline.py --config deploy/pphuman/config/infer_cfg.yml --video_file=test_video.mp4 --device=gpu --model_dir det=ppyoloe/ [--run_mode trt_fp16] +python deploy/pphuman/pipeline.py --config deploy/pphuman/config/infer_cfg_pphuman.yml --video_file=test_video.mp4 --device=gpu --model_dir det=ppyoloe/ [--run_mode trt_fp16] -# 行人属性识别，指定配置文件路径和测试视频，在配置文件中ATTR部分开启enable选项。 -python deploy/pphuman/pipeline.py --config deploy/pphuman/config/infer_cfg.yml --video_file=test_video.mp4 --device=gpu [--run_mode trt_fp16] +# 行人属性识别，指定配置文件路径和测试视频，在配置文件中```deploy/pphuman/config/infer_cfg_pphuman.yml```中的ATTR部分enable设置为```True``` +python deploy/pphuman/pipeline.py --config deploy/pphuman/config/infer_cfg_pphuman.yml --video_file=test_video.mp4 --device=gpu [--run_mode trt_fp16] -# 行为识别，指定配置文件路径和测试视频，在配置文件中对应行为识别功能开启enable选项。 -python deploy/pphuman/pipeline.py --config deploy/pphuman/config/infer_cfg.yml --video_file=test_video.mp4 --device=gpu [--run_mode trt_fp16] +# 行为识别，指定配置文件路径和测试视频，在配置文件中```deploy/pphuman/config/infer_cfg_pphuman.yml```中的SKELETON_ACTION部分enable设置为```True``` +python deploy/pphuman/pipeline.py --config deploy/pphuman/config/infer_cfg_pphuman.yml --video_file=test_video.mp4 --device=gpu [--run_mode trt_fp16] -# 行人跨境跟踪，指定配置文件路径和测试视频列表文件夹，在配置文件中REID部分开启enable选项。 -python deploy/pphuman/pipeline.py --config deploy/pphuman/config/infer_cfg.yml --video_dir=mtmct_dir/ --device=gpu [--run_mode trt_fp16] +# 行人跨境跟踪，指定配置文件路径和测试视频列表文件夹，在配置文件中```deploy/pphuman/config/infer_cfg_pphuman.yml```中的REID部分enable设置为```True``` +python deploy/pphuman/pipeline.py --config deploy/pphuman/config/infer_cfg_pphuman.yml --video_dir=mtmct_dir/ --device=gpu [--run_mode trt_fp16] ``` ### 4.1 参数说明 diff --git a/deploy/pphuman/docs/tutorials/action.md b/deploy/pphuman/docs/tutorials/action.md index 1144ae88c..adf1c95cb 100644 --- a/deploy/pphuman/docs/tutorials/action.md +++ b/deploy/pphuman/docs/tutorials/action.md @@ -26,7 +26,7 @@ 4. 预测速度为NVIDIA T4 机器上使用TensorRT FP16时的速度, 速度包含数据预处理、模型预测、后处理全流程。 ## 配置说明 -[配置文件](../config/infer_cfg.yml)中与行为识别相关的参数如下： +[配置文件](../config/infer_cfg_pphuman.yml)中与行为识别相关的参数如下： ``` SKELETON_ACTION: model_dir: output_inference/STGCN # 模型所在路径 @@ -40,18 +40,18 @@ SKELETON_ACTION: ## 使用方法 1. 从上表链接中下载模型并解压到```./output_inference```路径下。 -2. 目前行为识别模块仅支持视频输入，设置infer_cfg.yml中`SKELETON_ACTION`的enable: True, 然后启动命令如下： +2. 目前行为识别模块仅支持视频输入，设置infer_cfg_pphuman.yml中`SKELETON_ACTION`的enable: True, 然后启动命令如下： ```python -python deploy/pphuman/pipeline.py --config deploy/pphuman/config/infer_cfg.yml \ +python deploy/pphuman/pipeline.py --config deploy/pphuman/config/infer_cfg_pphuman.yml \ --video_file=test_video.mp4 \ --device=gpu \ ``` 3. 若修改模型路径，有以下两种方式： - - ```./deploy/pphuman/config/infer_cfg.yml```下可以配置不同模型路径，关键点模型和摔倒行为识别模型分别对应`KPT`和`SKELETON_ACTION`字段，修改对应字段下的路径为实际期望的路径即可。 + - ```./deploy/pphuman/config/infer_cfg_pphuman.yml```下可以配置不同模型路径，关键点模型和摔倒行为识别模型分别对应`KPT`和`SKELETON_ACTION`字段，修改对应字段下的路径为实际期望的路径即可。 - 命令行中增加`--model_dir`修改模型路径： ```python -python deploy/pphuman/pipeline.py --config deploy/pphuman/config/infer_cfg.yml \ +python deploy/pphuman/pipeline.py --config deploy/pphuman/config/infer_cfg_pphuman.yml \ --video_file=test_video.mp4 \ --device=gpu \ --model_dir kpt=./dark_hrnet_w32_256x192 action=./STGCN diff --git a/deploy/pphuman/docs/tutorials/action_en.md b/deploy/pphuman/docs/tutorials/action_en.md index ebabcac80..0d059a367 100644 --- a/deploy/pphuman/docs/tutorials/action_en.md +++ b/deploy/pphuman/docs/tutorials/action_en.md @@ -32,7 +32,7 @@ Note: ## Description of Configuration -Parameters related to action recognition in the [config file](../config/infer_cfg.yml) are as follow: +Parameters related to action recognition in the [config file](../config/infer_cfg_pphuman.yml) are as follow: ``` SKELETON_ACTION: @@ -52,22 +52,22 @@ SKELETON_ACTION: - Download models from the links of the above table and unzip them to ```./output_inference```. -- Now the only available input is the video input in the action recognition module. set the "enable: True" in SKELETON_ACTION of infer_cfg.yml. And then run the command: +- Now the only available input is the video input in the action recognition module. set the "enable: True" in SKELETON_ACTION of infer_cfg_pphuman.yml. And then run the command: ```python - python deploy/pphuman/pipeline.py --config deploy/pphuman/config/infer_cfg.yml \ + python deploy/pphuman/pipeline.py --config deploy/pphuman/config/infer_cfg_pphuman.yml \ --video_file=test_video.mp4 \ --device=gpu ``` - There are two ways to modify the model path: - - In ```./deploy/pphuman/config/infer_cfg.yml```, you can configurate different model paths，which is proper only if you match keypoint models and action recognition models with the fields of `KPT` and `SKELETON_ACTION` respectively, and modify the corresponding path of each field into the expected path. + - In ```./deploy/pphuman/config/infer_cfg_pphuman.yml```, you can configurate different model paths，which is proper only if you match keypoint models and action recognition models with the fields of `KPT` and `SKELETON_ACTION` respectively, and modify the corresponding path of each field into the expected path. - Add `--model_dir` in the command line to revise the model path： ```python - python deploy/pphuman/pipeline.py --config deploy/pphuman/config/infer_cfg.yml \ + python deploy/pphuman/pipeline.py --config deploy/pphuman/config/infer_cfg_pphuman.yml \ --video_file=test_video.mp4 \ --device=gpu \ --model_dir kpt=./dark_hrnet_w32_256x192 action=./STGCN diff --git a/deploy/pphuman/docs/tutorials/attribute.md b/deploy/pphuman/docs/tutorials/attribute.md index 53c41e285..1ca7a7f66 100644 --- a/deploy/pphuman/docs/tutorials/attribute.md +++ b/deploy/pphuman/docs/tutorials/attribute.md @@ -15,30 +15,27 @@ ## 使用方法 -1. 从上表链接中下载模型并解压到```./output_inference```路径下 +1. 从上表链接中下载模型并解压到```./output_inference```路径下，并且设置infer_cfg_pphuman.yml中`ATTR`的enable: True 2. 图片输入时，启动命令如下 ```python -python deploy/pphuman/pipeline.py --config deploy/pphuman/config/infer_cfg.yml \ +python deploy/pphuman/pipeline.py --config deploy/pphuman/config/infer_cfg_pphuman.yml \ --image_file=test_image.jpg \ --device=gpu \ - --enable_attr=True ``` 3. 视频输入时，启动命令如下 ```python -python deploy/pphuman/pipeline.py --config deploy/pphuman/config/infer_cfg.yml \ +python deploy/pphuman/pipeline.py --config deploy/pphuman/config/infer_cfg_pphuman.yml \ --video_file=test_video.mp4 \ --device=gpu \ - --enable_attr=True ``` 4. 若修改模型路径，有以下两种方式： - - ```./deploy/pphuman/config/infer_cfg.yml```下可以配置不同模型路径，属性识别模型修改ATTR字段下配置 + - ```./deploy/pphuman/config/infer_cfg_pphuman.yml```下可以配置不同模型路径，属性识别模型修改ATTR字段下配置 - **(推荐)**命令行中增加`--model_dir`修改模型路径： ```python -python deploy/pphuman/pipeline.py --config deploy/pphuman/config/infer_cfg.yml \ +python deploy/pphuman/pipeline.py --config deploy/pphuman/config/infer_cfg_pphuman.yml \ --video_file=test_video.mp4 \ --device=gpu \ - --enable_attr=True \ --model_dir det=ppyoloe/ ``` diff --git a/deploy/pphuman/docs/tutorials/attribute_en.md b/deploy/pphuman/docs/tutorials/attribute_en.md index 6078c6c0c..c31d8a9f8 100644 --- a/deploy/pphuman/docs/tutorials/attribute_en.md +++ b/deploy/pphuman/docs/tutorials/attribute_en.md @@ -15,30 +15,27 @@ Pedestrian attribute recognition has been widely used in the intelligent communi ## Instruction -1. Download the model from the link in the above table, and unzip it to```./output_inference```. +1. Download the model from the link in the above table, and unzip it to```./output_inference```, and set the "enable: True" in ATTR of infer_cfg_pphuman.yml 2. When inputting the image, run the command as follows: ```python -python deploy/pphuman/pipeline.py --config deploy/pphuman/config/infer_cfg.yml \ +python deploy/pphuman/pipeline.py --config deploy/pphuman/config/infer_cfg_pphuman.yml \ --image_file=test_image.jpg \ --device=gpu \ - --enable_attr=True ``` 3. When inputting the video, run the command as follows: ```python -python deploy/pphuman/pipeline.py --config deploy/pphuman/config/infer_cfg.yml \ +python deploy/pphuman/pipeline.py --config deploy/pphuman/config/infer_cfg_pphuman.yml \ --video_file=test_video.mp4 \ --device=gpu \ - --enable_attr=True ``` 4. If you want to change the model path, there are two methods： - - In ```./deploy/pphuman/config/infer_cfg.yml``` you can configurate different model paths. In attribute recognition models, you can modify the configuration in the field of ATTR. + - In ```./deploy/pphuman/config/infer_cfg_pphuman.yml``` you can configurate different model paths. In attribute recognition models, you can modify the configuration in the field of ATTR. - Add `--model_dir` in the command line to change the model path： ```python -python deploy/pphuman/pipeline.py --config deploy/pphuman/config/infer_cfg.yml \ +python deploy/pphuman/pipeline.py --config deploy/pphuman/config/infer_cfg_pphuman.yml \ --video_file=test_video.mp4 \ --device=gpu \ - --enable_attr=True \ --model_dir det=ppyoloe/ ``` diff --git a/deploy/pphuman/docs/tutorials/mot.md b/deploy/pphuman/docs/tutorials/mot.md index 33aa72cc7..04d05616e 100644 --- a/deploy/pphuman/docs/tutorials/mot.md +++ b/deploy/pphuman/docs/tutorials/mot.md @@ -15,24 +15,24 @@ ## 使用方法 1. 从上表链接中下载模型并解压到```./output_inference```路径下 -2. 图片输入时，启动命令如下 +2. 图片输入时，是纯检测任务，启动命令如下 ```python -python deploy/pphuman/pipeline.py --config deploy/pphuman/config/infer_cfg.yml \ +python deploy/pphuman/pipeline.py --config deploy/pphuman/config/infer_cfg_pphuman.yml \ --image_file=test_image.jpg \ --device=gpu ``` -3. 视频输入时，启动命令如下 +3. 视频输入时，是跟踪任务，注意首先设置infer_cfg_pphuman.yml中的MOT配置的enable=True，然后启动命令如下 ```python -python deploy/pphuman/pipeline.py --config deploy/pphuman/config/infer_cfg.yml \ +python deploy/pphuman/pipeline.py --config deploy/pphuman/config/infer_cfg_pphuman.yml \ --video_file=test_video.mp4 \ --device=gpu ``` 4. 若修改模型路径，有以下两种方式： - - ```./deploy/pphuman/config/infer_cfg.yml```下可以配置不同模型路径，检测和跟踪模型分别对应`DET`和`MOT`字段，修改对应字段下的路径为实际期望的路径即可。 + - ```./deploy/pphuman/config/infer_cfg_pphuman.yml```下可以配置不同模型路径，检测和跟踪模型分别对应`DET`和`MOT`字段，修改对应字段下的路径为实际期望的路径即可。 - 命令行中增加`--model_dir`修改模型路径： ```python -python deploy/pphuman/pipeline.py --config deploy/pphuman/config/infer_cfg.yml \ +python deploy/pphuman/pipeline.py --config deploy/pphuman/config/infer_cfg_pphuman.yml \ --video_file=test_video.mp4 \ --device=gpu \ --do_entrance_counting \ diff --git a/deploy/pphuman/docs/tutorials/mot_en.md b/deploy/pphuman/docs/tutorials/mot_en.md index 8fd66d2f1..86a64991e 100644 --- a/deploy/pphuman/docs/tutorials/mot_en.md +++ b/deploy/pphuman/docs/tutorials/mot_en.md @@ -15,25 +15,25 @@ Pedestrian detection and tracking is widely used in the intelligent community, i ## How to Use 1. Download models from the links of the above table and unizp them to ```./output_inference```. -2. During the image input, the start command is as follows: +2. When use the image as input, it's a detection task, the start command is as follows: ```python -python deploy/pphuman/pipeline.py --config deploy/pphuman/config/infer_cfg.yml \ +python deploy/pphuman/pipeline.py --config deploy/pphuman/config/infer_cfg_pphuman.yml \ --image_file=test_image.jpg \ --device=gpu ``` -3. In the video input, the start command is as follows: +3. When use the video as input, it's a tracking task, first you should set the "enable: True" in MOT of infer_cfg_pphuman.yml, and then the start command is as follows: ```python -python deploy/pphuman/pipeline.py --config deploy/pphuman/config/infer_cfg.yml \ +python deploy/pphuman/pipeline.py --config deploy/pphuman/config/infer_cfg_pphuman.yml \ --video_file=test_video.mp4 \ --device=gpu ``` 4. There are two ways to modify the model path: - - In `./deploy/pphuman/config/infer_cfg.yml`, you can configurate different model paths，which is proper only if you match keypoint models and action recognition models with the fields of `DET` and `MOT` respectively, and modify the corresponding path of each field into the expected path. + - In `./deploy/pphuman/config/infer_cfg_pphuman.yml`, you can configurate different model paths，which is proper only if you match keypoint models and action recognition models with the fields of `DET` and `MOT` respectively, and modify the corresponding path of each field into the expected path. - Add `--model_dir` in the command line to revise the model path: ```python -python deploy/pphuman/pipeline.py --config deploy/pphuman/config/infer_cfg.yml \ +python deploy/pphuman/pipeline.py --config deploy/pphuman/config/infer_cfg_pphuman.yml \ --video_file=test_video.mp4 \ --device=gpu \ --model_dir det=ppyoloe/ diff --git a/deploy/pphuman/docs/tutorials/mtmct.md b/deploy/pphuman/docs/tutorials/mtmct.md index b0f45fc13..73aed307d 100644 --- a/deploy/pphuman/docs/tutorials/mtmct.md +++ b/deploy/pphuman/docs/tutorials/mtmct.md @@ -9,16 +9,16 @@ PP-Human跨镜头跟踪模块主要目的在于提供一套简洁、高效的跨 1. 下载模型 [REID模型](https://bj.bcebos.com/v1/paddledet/models/pipeline/reid_model.zip) 并解压到```./output_inference```路径下, MOT模型请参考[mot说明](./mot.md)文件下载。 -2. 跨镜头跟踪模式下，要求输入的多个视频放在同一目录下，同时开启infer_cfg.yml 中的REID选择中的enable=True, 命令如下： +2. 跨镜头跟踪模式下，要求输入的多个视频放在同一目录下，同时开启infer_cfg_pphuman.yml 中的REID选择中的enable=True, 命令如下： ```python -python3 deploy/pphuman/pipeline.py --config deploy/pphuman/config/infer_cfg.yml --video_dir=[your_video_file_directory] --device=gpu +python3 deploy/pphuman/pipeline.py --config deploy/pphuman/config/infer_cfg_pphuman.yml --video_dir=[your_video_file_directory] --device=gpu ``` -3. 相关配置在`./deploy/pphuman/config/infer_cfg.yml`文件中修改： +3. 相关配置在`./deploy/pphuman/config/infer_cfg_pphuman.yml`文件中修改： ```python python3 deploy/pphuman/pipeline.py - --config deploy/pphuman/config/infer_cfg.yml + --config deploy/pphuman/config/infer_cfg_pphuman.yml --video_dir=[your_video_file_directory] --device=gpu --model_dir reid=reid_best/ diff --git a/deploy/pphuman/docs/tutorials/mtmct_en.md b/deploy/pphuman/docs/tutorials/mtmct_en.md index dd4716bc9..609861396 100644 --- a/deploy/pphuman/docs/tutorials/mtmct_en.md +++ b/deploy/pphuman/docs/tutorials/mtmct_en.md @@ -9,16 +9,16 @@ The MTMCT module of PP-Human aims to provide a multi-target multi-camera pipleli 1. Download [REID model](https://bj.bcebos.com/v1/paddledet/models/pipeline/reid_model.zip) and unzip it to ```./output_inference```. For the MOT model, please refer to [mot description](./mot.md). -2. In the MTMCT mode, input videos are required to be put in the same directory. set the REID "enable: True" in the infer_cfg.yml. The command line is: +2. In the MTMCT mode, input videos are required to be put in the same directory. set the REID "enable: True" in the infer_cfg_pphuman.yml. The command line is: ```python -python3 deploy/pphuman/pipeline.py --config deploy/pphuman/config/infer_cfg.yml --video_dir=[your_video_file_directory] --device=gpu +python3 deploy/pphuman/pipeline.py --config deploy/pphuman/config/infer_cfg_pphuman.yml --video_dir=[your_video_file_directory] --device=gpu ``` -3. Configuration can be modified in `./deploy/pphuman/config/infer_cfg.yml`. +3. Configuration can be modified in `./deploy/pphuman/config/infer_cfg_pphuman.yml`. ```python python3 deploy/pphuman/pipeline.py - --config deploy/pphuman/config/infer_cfg.yml + --config deploy/pphuman/config/infer_cfg_pphuman.yml --video_dir=[your_video_file_directory] --device=gpu --model_dir reid=reid_best/ diff --git a/deploy/pphuman/pipeline.py b/deploy/pphuman/pipeline.py index 2d1f85790..347f07714 100644 --- a/deploy/pphuman/pipeline.py +++ b/deploy/pphuman/pipeline.py @@ -869,18 +869,19 @@ class PipePredictor(object): online_scores[0] = scores online_ids[0] = ids - image = plot_tracking_dict( - image, - num_classes, - online_tlwhs, - online_ids, - online_scores, - frame_id=frame_id, - fps=fps, - do_entrance_counting=self.do_entrance_counting, - entrance=entrance, - records=records, - center_traj=center_traj) + if mot_res is not None: + image = plot_tracking_dict( + image, + num_classes, + online_tlwhs, + online_ids, + online_scores, + frame_id=frame_id, + fps=fps, + do_entrance_counting=self.do_entrance_counting, + entrance=entrance, + records=records, + center_traj=center_traj) human_attr_res = result.get('attr') if human_attr_res is not None: -- GitLab