From bb319a8a598cdaa3fdf431988f28cafbdd9b2a11 Mon Sep 17 00:00:00 2001 From: JYChen Date: Fri, 29 Apr 2022 14:51:30 +0800 Subject: [PATCH] add pdparams links (#5864) --- configs/keypoint/README.md | 12 ++++++++++-- configs/keypoint/README_en.md | 13 ++++++++++--- deploy/pphuman/README.md | 16 ++++++++-------- deploy/pphuman/README_en.md | 15 ++++++++------- deploy/pphuman/docs/action.md | 12 +++++++----- deploy/pphuman/docs/action_en.md | 12 +++++++----- deploy/pphuman/docs/mot.md | 2 ++ deploy/pphuman/docs/mot_en.md | 2 ++ deploy/pphuman/docs/mtmct.md | 2 ++ deploy/pphuman/docs/mtmct_en.md | 2 ++ 10 files changed, 58 insertions(+), 30 deletions(-) diff --git a/configs/keypoint/README.md b/configs/keypoint/README.md index 1dc5e9d02..b00d9dda2 100644 --- a/configs/keypoint/README.md +++ b/configs/keypoint/README.md @@ -66,7 +66,7 @@ PaddleDetection 关键点检测能力紧跟业内最新最优算法方案，包 ## 模型库 COCO数据集 -| 模型 | 方案 |输入尺寸 | AP(coco val) | 模型下载 | 配置文件 | +| 模型 | 方案 |输入尺寸 | AP(coco val) | 模型下载 | 配置文件 | | :---------------- | -------- | :----------: | :----------------------------------------------------------: | ----------------------------------------------------| ------- | | HigherHRNet-w32 |Bottom-Up| 512 | 67.1 | [higherhrnet_hrnet_w32_512.pdparams](https://paddledet.bj.bcebos.com/models/keypoint/higherhrnet_hrnet_w32_512.pdparams) | [config](./higherhrnet/higherhrnet_hrnet_w32_512.yml) | | HigherHRNet-w32 | Bottom-Up| 640 | 68.3 | [higherhrnet_hrnet_w32_640.pdparams](https://paddledet.bj.bcebos.com/models/keypoint/higherhrnet_hrnet_w32_640.pdparams) | [config](./higherhrnet/higherhrnet_hrnet_w32_640.yml) | @@ -106,8 +106,16 @@ MPII数据集 | :---- | ---|----- | :--------: | :------------: | :----------------------------------------------------------: | -------------------------------------------- | | HRNet-w32 | Top-Down|256x256 | 90.6 | 38.5 | [hrnet_w32_256x256_mpii.pdparams](https://paddledet.bj.bcebos.com/models/keypoint/hrnet_w32_256x256_mpii.pdparams) | [config](./hrnet/hrnet_w32_256x256_mpii.yml) | +场景模型 +| 模型 | 方案 | 输入尺寸 | 精度 | 预测速度 |模型权重 | 部署模型 | 说明| +| :---- | ---|----- | :--------: | :--------: | :------------: |:------------: |:-------------------: | +| HRNet-w32 + DarkPose | Top-Down|256x192 | AP: 87.1 (业务数据集)| 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) | 针对摔倒场景特别优化，该模型应用于[PP-Human](../../deploy/pphuman/README.md) | + + 我们同时推出了基于LiteHRNet（Top-Down）针对移动端设备优化的实时关键点检测模型[PP-TinyPose](./tiny_pose/README.md), 欢迎体验。 + + ## 快速开始 ### 1、环境安装 @@ -172,7 +180,7 @@ CUDA_VISIBLE_DEVICES=0 python3 tools/infer.py -c configs/keypoint/higherhrnet/hi ```shell #导出检测模型 -python tools/export_model.py -c configs/ppyolo/ppyolov2_r50vd_dcn_365e_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyolov2_r50vd_dcn_365e_coco.pdparams +python tools/export_model.py -c configs/ppyolo/ppyolov2_r50vd_dcn_365e_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyolov2_r50vd_dcn_365e_coco.pdparams #导出关键点模型 python tools/export_model.py -c configs/keypoint/hrnet/hrnet_w32_256x192.yml -o weights=https://paddledet.bj.bcebos.com/models/keypoint/hrnet_w32_256x192.pdparams diff --git a/configs/keypoint/README_en.md b/configs/keypoint/README_en.md index 2c1ba042d..68b738bd1 100644 --- a/configs/keypoint/README_en.md +++ b/configs/keypoint/README_en.md @@ -27,9 +27,9 @@ ## Introduction -The keypoint detection part in PaddleDetection follows the state-of-the-art algorithm closely, including Top-Down and Bottom-Up methods, which can satisfy the different needs of users. +The keypoint detection part in PaddleDetection follows the state-of-the-art algorithm closely, including Top-Down and Bottom-Up methods, which can satisfy the different needs of users. -Top-Down detects the object first and then detect the specific keypoint. The accuracy of Top-Down models will be higher, but the time required will increase by the number of objects. +Top-Down detects the object first and then detect the specific keypoint. The accuracy of Top-Down models will be higher, but the time required will increase by the number of objects. Differently, Bottom-Up detects the point first and then group or connect those points to form several instances of human pose. The speed of Bottom-Up is fixed and will not increase by the number of objects, but the accuracy will be lower. @@ -89,6 +89,13 @@ MPII Dataset | :---- | -------- | :--------: | :------------: | :----------------------------------------------------------: | -------------------------------------------- | | HRNet-w32 | 256x256 | 90.6 | 38.5 | [hrnet_w32_256x256_mpii.pdparams](https://paddledet.bj.bcebos.com/models/keypoint/hrnet_w32_256x256_mpii.pdparams) | [config](./hrnet/hrnet_w32_256x256_mpii.yml) | + +Model for Scenes +| Model | Strategy | Input Size | Precision | Inference Speed |Model Weights | Model Inference and Deployment | description| +| :---- | ---|----- | :--------: | :-------: |:------------: |:------------: |:-------------------: | +| HRNet-w32 + DarkPose | Top-Down|256x192 | AP: 87.1 (on internal dataset)| 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) | Especially optimized for fall scenarios, the model is applied to [PP-Human](../../deploy/pphuman/README_en.md) | + + We also release [PP-TinyPose](./tiny_pose/README_en.md), a real-time keypoint detection model optimized for mobile devices. Welcome to experience. ## Getting Start @@ -155,7 +162,7 @@ CUDA_VISIBLE_DEVICES=0 python3 tools/infer.py -c configs/keypoint/higherhrnet/hi ```shell #Export Detection Model -python tools/export_model.py -c configs/ppyolo/ppyolov2_r50vd_dcn_365e_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyolov2_r50vd_dcn_365e_coco.pdparams +python tools/export_model.py -c configs/ppyolo/ppyolov2_r50vd_dcn_365e_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyolov2_r50vd_dcn_365e_coco.pdparams #Export Keypoint Model diff --git a/deploy/pphuman/README.md b/deploy/pphuman/README.md index f5aa67b1b..0496f3f46 100644 --- a/deploy/pphuman/README.md +++ b/deploy/pphuman/README.md @@ -40,14 +40,14 @@ pip install -r requirements.txt PP-Human提供了目标检测、属性识别、行为识别、ReID预训练模型，以实现不同使用场景，用户可以直接下载使用 -| 任务 | 适用场景 | 精度 | 预测速度（ms） | 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.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.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.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 | 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) | 下载模型后，解压至`./output_inference`文件夹 diff --git a/deploy/pphuman/README_en.md b/deploy/pphuman/README_en.md index fc57e86c3..735f817d4 100644 --- a/deploy/pphuman/README_en.md +++ b/deploy/pphuman/README_en.md @@ -41,13 +41,14 @@ pip install -r requirements.txt 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 Inference and Deployment | -| :---------: |:---------: |:--------------- | :-------: | :------: | -| Object Detection | Image/Video Input | mAP: 56.3 | 28.0ms | [Link](https://bj.bcebos.com/v1/paddledet/models/pipeline/mot_ppyoloe_l_36e_pipeline.zip) | -| Attribute Recognition | Image/Video Input Attribute Recognition | MOTA: 72.0 | 33.1ms | [Link](https://bj.bcebos.com/v1/paddledet/models/pipeline/strongbaseline_r50_30e_pa100k.zip) | -| Keypoint Detection | Video Input Action Recognition | mA: 94.86 | 2ms per person | [Link](https://bj.bcebos.com/v1/paddledet/models/pipeline/dark_hrnet_w32_256x192.zip) -| Behavior Recognition | Video Input Bheavior 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) | +| Task | Scenario | Precision | Inference Speed（FPS） | Model Weights |Model Inference and Deployment | +| :---------: |:---------: |:--------------- | :-------: | :------: | :------: | +| Object Detection | Image/Video Input | mAP: 56.3 | 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 Tracking | Image/Video Input | MOTA: 72.0 | 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) | +| 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 Action 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) +| Action Recognition | Video Input Action 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`. diff --git a/deploy/pphuman/docs/action.md b/deploy/pphuman/docs/action.md index f23654299..96cb35e4f 100644 --- a/deploy/pphuman/docs/action.md +++ b/deploy/pphuman/docs/action.md @@ -1,3 +1,5 @@ +[English](action_en.md) | 简体中文 + # PP-Human行为识别模块 行为识别在智慧社区，安防监控等方向具有广泛应用，PP-Human中集成了基于骨骼点的行为识别模块。 @@ -10,11 +12,11 @@ ## 模型库 在这里，我们提供了检测/跟踪、关键点识别以及识别摔倒动作的预训练模型，用户可以直接下载使用。 -| 任务 | 算法 | 精度 | 预测速度(ms) | 下载链接 | -|:---------------------|:---------:|:------:|:------:| :---------------------------------------------------------------------------------: | -| 行人检测/跟踪 | PP-YOLOE | mAP: 56.3
MOTA: 72.0 | 检测: 28ms
跟踪：33.1ms | [下载链接](https://bj.bcebos.com/v1/paddledet/models/pipeline/mot_ppyoloe_l_36e_pipeline.zip) | -| 关键点识别 | HRNet | AP: 87.1 | 单人 2.9ms | [下载链接](https://bj.bcebos.com/v1/paddledet/models/pipeline/dark_hrnet_w32_256x192.zip)| -| 行为识别 | ST-GCN | 准确率: 96.43 | 单人 2.7ms | [下载链接](https://bj.bcebos.com/v1/paddledet/models/pipeline/STGCN.zip) | +| 任务 | 算法 | 精度 | 预测速度(ms) | 模型权重 | 预测部署模型 | +|:---------------------|:---------:|:------:|:------:| :------: |:---------------------------------------------------------------------------------: | +| 行人检测/跟踪 | PP-YOLOE | mAP: 56.3
MOTA: 72.0 | 检测: 28ms
跟踪：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) | +| 关键点识别 | HRNet | 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 | ST-GCN | 准确率: 96.43 | 单人 2.7ms | - |[下载链接](https://bj.bcebos.com/v1/paddledet/models/pipeline/STGCN.zip) | 注： diff --git a/deploy/pphuman/docs/action_en.md b/deploy/pphuman/docs/action_en.md index ba33efc4c..f2c8e8fc8 100644 --- a/deploy/pphuman/docs/action_en.md +++ b/deploy/pphuman/docs/action_en.md @@ -1,3 +1,5 @@ +English | [简体中文](action.md) + # Action Recognition Module of PP-Human Action Recognition is widely used in the intelligent community/smart city, and security monitoring. PP-Human provides the module of skeleton-based action recognition. @@ -12,11 +14,11 @@ used for academic research here. There are multiple available pretrained models including pedestrian detection/tracking, keypoint detection, and fall detection models. Users can download and use them directly. -| Task | Algorithm | Precision | Inference Speed(ms) | Download Link | -|:----------------------------- |:---------:|:-------------------------:|:-----------------------------------:|:-----------------------------------------------------------------------------------------:| -| Pedestrian Detection/Tracking | PP-YOLOE | mAP: 56.3
MOTA: 72.0 | Detection: 28ms
Tracking：33.1ms | [Link](https://bj.bcebos.com/v1/paddledet/models/pipeline/mot_ppyoloe_l_36e_pipeline.zip) | -| Keypoint Detection | HRNet | AP: 87.1 | Single Person 2.9ms | [Link](https://bj.bcebos.com/v1/paddledet/models/pipeline/dark_hrnet_w32_256x192.zip) | -| Action Recognition | ST-GCN | Precision Rate: 96.43 | Single Person 2.7ms | [Link](https://bj.bcebos.com/v1/paddledet/models/pipeline/STGCN.zip) | +| Task | Algorithm | Precision | Inference Speed(ms) | Model Weights |Model Inference and Deployment | +|:----------------------------- |:---------:|:-------------------------:|:-----------------------------------:| :-----------------: |:-----------------------------------------------------------------------------------------:| +| Pedestrian Detection/Tracking | PP-YOLOE | mAP: 56.3
MOTA: 72.0 | Detection: 28ms
Tracking：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) | +| Keypoint Detection | HRNet | AP: 87.1 | Single Person 2.9ms |[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) | +| Action Recognition | ST-GCN | Precision Rate: 96.43 | Single Person 2.7ms | - |[Link](https://bj.bcebos.com/v1/paddledet/models/pipeline/STGCN.zip) | Note: diff --git a/deploy/pphuman/docs/mot.md b/deploy/pphuman/docs/mot.md index d9487a394..0552c4df2 100644 --- a/deploy/pphuman/docs/mot.md +++ b/deploy/pphuman/docs/mot.md @@ -1,3 +1,5 @@ +[English](mot_en.md) | 简体中文 + # PP-Human检测跟踪模块 行人检测与跟踪在智慧社区，工业巡检，交通监控等方向都具有广泛应用，PP-Human中集成了检测跟踪模块，是关键点检测、属性行为识别等任务的基础。我们提供了预训练模型，用户可以直接下载使用。 diff --git a/deploy/pphuman/docs/mot_en.md b/deploy/pphuman/docs/mot_en.md index 2c657e8ec..61a970898 100644 --- a/deploy/pphuman/docs/mot_en.md +++ b/deploy/pphuman/docs/mot_en.md @@ -1,3 +1,5 @@ +English | [简体中文](mot.md) + # Detection and Tracking Module of PP-Human Pedestrian detection and tracking is widely used in the intelligent community, industrial inspection, transportation monitoring and so on. PP-Human has the detection and tracking module, which is fundamental to keypoint detection, attribute action recognition, etc. Users enjoy easy access to pretrained models here. diff --git a/deploy/pphuman/docs/mtmct.md b/deploy/pphuman/docs/mtmct.md index 1896d1c1f..5e2eacef8 100644 --- a/deploy/pphuman/docs/mtmct.md +++ b/deploy/pphuman/docs/mtmct.md @@ -1,3 +1,5 @@ +[English](mtmct_en.md) | 简体中文 + # PP-Human跨镜头跟踪模块 跨镜头跟踪任务，是在单镜头跟踪的基础上，实现不同摄像头中人员的身份匹配关联。在安放、智慧零售等方向有较多的应用。 diff --git a/deploy/pphuman/docs/mtmct_en.md b/deploy/pphuman/docs/mtmct_en.md index 117e2d78e..935aa1442 100644 --- a/deploy/pphuman/docs/mtmct_en.md +++ b/deploy/pphuman/docs/mtmct_en.md @@ -1,3 +1,5 @@ +English | [简体中文](mtmct.md) + # Multi-Target Multi-Camera Tracking Module of PP-Human Multi-target multi-camera tracking, or MTMCT, matches the identity of a person in different cameras based on the single-camera tracking. MTMCT is usually applied to the security system and the smart retailing. -- GitLab