diff --git a/README_cn.md b/README_cn.md index bfb8a575ba66d4ff39b29d69a41b7b3f9edc7ea1..3a45d59bf117acf50f6b93def810ea02ac488407 100644 --- a/README_cn.md +++ b/README_cn.md @@ -22,7 +22,6 @@ - ## 🚀 热门活动 - 🎊 **【AI快车道两日课】手把手教你将PP-YOLOE+用于旋转框、小目标检测，达成SOTA性能** - ⏰ **时间：11月16-17日 晚上8:15** @@ -65,7 +64,7 @@ PaddleDetection非常欢迎你加入到飞桨社区的开源建设中，参与 - 发布行人分析工具[PP-Human v2](./deploy/pipeline)，新增打架、打电话、抽烟、闯入四大行为识别，底层算法性能升级，覆盖行人检测、跟踪、属性三类核心算法能力，提供保姆级全流程开发及模型优化策略，支持在线视频流输入 - 首次发布[PP-Vehicle](./deploy/pipeline)，提供车牌识别、车辆属性分析（颜色、车型）、车流量统计以及违章检测四大功能，兼容图片、在线视频流、视频输入，提供完善的二次开发文档教程 - 💡 前沿算法： - - 全面覆盖的[YOLO家族](docs/feature_models/YOLOSERIES_MODEL.md)经典与最新模型代码库[PaddleYOLO](https://github.com/PaddlePaddle/PaddleYOLO): 包括YOLOv3，百度飞桨自研的实时高精度目标检测模型PP-YOLOE，以及前沿检测算法YOLOv4、YOLOv5、YOLOX，YOLOv6及YOLOv7 + - 全面覆盖的[YOLO家族](https://github.com/PaddlePaddle/PaddleYOLO/tree/develop/docs/MODEL_ZOO_cn.md)经典与最新算法模型的代码库[PaddleYOLO](https://github.com/PaddlePaddle/PaddleYOLO): 包括YOLOv3，百度飞桨自研的实时高精度目标检测模型PP-YOLOE，以及前沿检测算法YOLOv4、YOLOv5、YOLOX，YOLOv6及YOLOv7 - 新增基于[ViT](configs/vitdet)骨干网络高精度检测模型，COCO数据集精度达到55.7% mAP；新增[OC-SORT](configs/mot/ocsort)多目标跟踪模型；新增[ConvNeXt](configs/convnext)骨干网络 - 📋 产业范例：新增[智能健身](https://aistudio.baidu.com/aistudio/projectdetail/4385813)、[打架识别](https://aistudio.baidu.com/aistudio/projectdetail/4086987?channelType=0&channel=0)、[来客分析](https://aistudio.baidu.com/aistudio/projectdetail/4230123?channelType=0&channel=0)、车辆结构化范例 @@ -298,7 +297,7 @@ PaddleDetection非常欢迎你加入到飞桨社区的开源建设中，参与 - `Cascade-Faster-RCNN`为`Cascade-Faster-RCNN-ResNet50vd-DCN`，PaddleDetection将其优化到COCO数据mAP为47.8%时推理速度为20FPS - `PP-YOLOE`是对`PP-YOLO v2`模型的进一步优化，L版本在COCO数据集mAP为51.6%，Tesla V100预测速度78.1FPS - `PP-YOLOE+`是对`PPOLOE`模型的进一步优化，L版本在COCO数据集mAP为53.3%，Tesla V100预测速度78.1FPS -- [`YOLOX`](configs/yolox)和[`YOLOv5`](https://github.com/PaddlePaddle/PaddleYOLO/tree/develop/configs/yolov5)均为基于PaddleDetection复现算法，`YOLOv5`代码在[`PaddleYOLO`](https://github.com/PaddlePaddle/PaddleYOLO)中，参照[YOLOSERIES_MODEL](docs/feature_models/YOLOSERIES_MODEL.md) +- [`YOLOX`](configs/yolox)和[`YOLOv5`](https://github.com/PaddlePaddle/PaddleYOLO/tree/develop/configs/yolov5)均为基于PaddleDetection复现算法，`YOLOv5`代码在[`PaddleYOLO`](https://github.com/PaddlePaddle/PaddleYOLO)中，参照[PaddleYOLO_MODEL](docs/feature_models/PaddleYOLO_MODEL.md) - 图中模型均可在[模型库](#模型库)中获取 @@ -347,11 +346,11 @@ PaddleDetection非常欢迎你加入到飞桨社区的开源建设中，参与 | 模型名称 | COCO精度（mAP） | V100 TensorRT FP16速度(FPS) | 配置文件 | 模型下载 | |:------------------------------------------------------------------ |:-----------:|:-------------------------:|:------------------------------------------------------------------------------------------------------------:|:--------------------------------------------------------------------------:| | [YOLOX-l](configs/yolox) | 50.1 | 107.5 | [链接](configs/yolox/yolox_l_300e_coco.yml) | [下载地址](https://paddledet.bj.bcebos.com/models/yolox_l_300e_coco.pdparams) | -| [YOLOv5-l](https://github.com/PaddlePaddle/PaddleYOLO/tree/develop/configs/yolov5) | 48.6 | 136.0 | [链接](https://github.com/nemonameless/PaddlePaddle/PaddleYOLO/blob/develop/configs/yolov5/yolov5_l_300e_coco.yml) | [下载地址](https://paddledet.bj.bcebos.com/models/yolov5_l_300e_coco.pdparams) | -| [YOLOv7-l](https://github.com/nemonameless/PaddlePaddle/PaddleYOLO/tree/develop/configs/yolov7) | 51.0 | 135.0 | [链接](https://github.com/nemonameless/PaddlePaddle/PaddleYOLO/blob/develop/configs/yolov7/yolov7_l_300e_coco.yml) | [下载地址](https://paddledet.bj.bcebos.com/models/yolov7_l_300e_coco.pdparams) | +| [YOLOv5-l](https://github.com/PaddlePaddle/PaddleYOLO/tree/develop/configs/yolov5) | 48.6 | 136.0 | [链接](https://github.com/PaddlePaddle/PaddleYOLO/tree/develop/configs/yolov5/yolov5_l_300e_coco.yml) | [下载地址](https://paddledet.bj.bcebos.com/models/yolov5_l_300e_coco.pdparams) | +| [YOLOv7-l](https://github.com/PaddlePaddle/PaddleYOLO/tree/develop/configs/yolov7) | 51.0 | 135.0 | [链接](https://github.com/PaddlePaddle/PaddleYOLO/tree/develop/configs/yolov7/yolov7_l_300e_coco.yml) | [下载地址](https://paddledet.bj.bcebos.com/models/yolov7_l_300e_coco.pdparams) | **注意:** -- `YOLOv5`和`YOLOv7`代码在[`PaddleYOLO`](https://github.com/PaddlePaddle/PaddleYOLO)中，为基于`PaddleDetection`复现的算法，可参照[YOLOSERIES_MODEL](docs/feature_models/YOLOSERIES_MODEL.md)。 +- `YOLOv5`和`YOLOv7`代码在[`PaddleYOLO`](https://github.com/PaddlePaddle/PaddleYOLO)中，为基于`PaddleDetection`复现的算法，可参照[PaddleYOLO_MODEL](docs/feature_models/PaddleYOLO_MODEL.md)。 #### 其他通用检测模型 [文档链接](docs/MODEL_ZOO_cn.md) diff --git a/README_en.md b/README_en.md index 30ba328a768e0aed5a6658f9457362974d8c5a65..0811e4fb0c7e1f9e8be90730ad1a58ea5000a6ba 100644 --- a/README_en.md +++ b/README_en.md @@ -21,7 +21,6 @@ - ## Product Update - 🔥 **2022.11.15：SOTA rotated object detector and small object detector based on PP-YOLOE** @@ -48,7 +47,7 @@ - 💡 Cutting-edge algorithms： - - Covers [YOLO family](https://github.com/PaddlePaddle/PaddleYOLO) classic and latest models: YOLOv3, PP-YOLOE (a real-time high-precision object detection model developed by Baidu PaddlePaddle), and cutting-edge detection algorithms such as YOLOv4, YOLOv5, YOLOX, YOLOv6, and YOLOv7 + - Release [PaddleYOLO](https://github.com/PaddlePaddle/PaddleYOLO) which overs classic and latest models of [YOLO family](https://github.com/PaddlePaddle/PaddleYOLO/tree/develop/docs/MODEL_ZOO_en.md): YOLOv3, PP-YOLOE (a real-time high-precision object detection model developed by Baidu PaddlePaddle), and cutting-edge detection algorithms such as YOLOv4, YOLOv5, YOLOX, YOLOv6, and YOLOv7 - Newly add high precision detection model based on [ViT](configs/vitdet) backbone network, with a 55.7% mAP accuracy on COCO dataset; newly add multi-object tracking model [OC-SORT](configs/mot/ocsort); newly add [ConvNeXt](configs/convnext) backbone network. - 📋 Industrial applications: Newly add [Smart Fitness](https://aistudio.baidu.com/aistudio/projectdetail/4385813), [Fighting recognition](https://aistudio.baidu.com/aistudio/projectdetail/4086987?channelType=0&channel=0),[ and Visitor Analysis](https://aistudio.baidu.com/aistudio/projectdetail/4230123?channelType=0&channel=0). @@ -323,12 +322,13 @@ The comparison between COCO mAP and FPS on Qualcomm Snapdragon 865 processor of | PicoDet-M | 34.4 | 17.68 | [Link](configs/picodet/picodet_m_320_coco_lcnet.yml) | [Download](https://paddledet.bj.bcebos.com/models/picodet_m_320_coco_lcnet.pdparams) | | PicoDet-L | 36.1 | 25.21 | [Link](configs/picodet/picodet_l_320_coco_lcnet.yml) | [Download](https://paddledet.bj.bcebos.com/models/picodet_l_320_coco_lcnet.pdparams) | -#### [Frontier detection algorithm](docs/feature_models/YOLOSERIES_MODEL.md) +#### [Frontier detection algorithm](docs/feature_models/PaddleYOLO_MODEL.md) | Model | COCO Accuracy（mAP） | V100 TensorRT FP16 speed(FPS) | Configuration | Download | |:-------- |:------------------:|:-----------------------------:|:--------------------------------------------------------------------------------------------------------------:|:------------------------------------------------------------------------------:| -| YOLOX-l | 50.1 | 107.5 | [Link](configs/yolox/yolox_l_300e_coco.yml) | [Download](https://paddledet.bj.bcebos.com/models/yolox_l_300e_coco.pdparams) | -| YOLOv5-l | 48.6 | 136.0 | [Link](https://github.com/nemonameless/PaddleDetection_YOLOv5/blob/main/configs/yolov5/yolov5_l_300e_coco.yml) | [Download](https://paddledet.bj.bcebos.com/models/yolov5_l_300e_coco.pdparams) | +| [YOLOX-l](configs/yolox) | 50.1 | 107.5 | [Link](configs/yolox/yolox_l_300e_coco.yml) | [Download](https://paddledet.bj.bcebos.com/models/yolox_l_300e_coco.pdparams) | +| [YOLOv5-l](https://github.com/PaddlePaddle/PaddleYOLO/tree/develop/configs/yolov5) | 48.6 | 136.0 | [Link](https://github.com/PaddlePaddle/PaddleYOLO/tree/develop/configs/yolov5/yolov5_l_300e_coco.yml) | [Download](https://paddledet.bj.bcebos.com/models/yolov5_l_300e_coco.pdparams) | +| [YOLOv7-l](https://github.com/PaddlePaddle/PaddleYOLO/tree/develop/configs/yolov7) | 51.0 | 135.0 | [链接](https://github.com/PaddlePaddle/PaddleYOLO/tree/develop/configs/yolov7/yolov7_l_300e_coco.yml) | [下载地址](https://paddledet.bj.bcebos.com/models/yolov7_l_300e_coco.pdparams) | #### Other general purpose models [doc](docs/MODEL_ZOO_en.md) diff --git a/docs/MODEL_ZOO_cn.md b/docs/MODEL_ZOO_cn.md index 1306700d10adc1b62f091b42dcbb4cafbe9e0c2e..8ff9507ef6e245197ca5c983a2df00a813a3df47 100644 --- a/docs/MODEL_ZOO_cn.md +++ b/docs/MODEL_ZOO_cn.md @@ -1,5 +1,22 @@ # 模型库和基线 +# 内容 +- [基础设置](#基础设置) + - [测试环境](#测试环境) + - [通用设置](#通用设置) + - [训练策略](#训练策略) + - [ImageNet预训练模型](#ImageNet预训练模型) +- [基线](#基线) + - [目标检测](#目标检测) + - [实例分割](#实例分割) + - [PaddleYOLO](#PaddleYOLO) + - [人脸检测](#人脸检测) + - [旋转框检测](#旋转框检测) + - [关键点检测](#关键点检测) + - [多目标跟踪](#多目标跟踪) + +# 基础设置 + ## 测试环境 - Python 3.7 @@ -11,6 +28,7 @@ ## 通用设置 - 所有模型均在COCO17数据集中训练和测试。 +- [YOLOv5](https://github.com/PaddlePaddle/PaddleYOLO/tree/develop/configs/yolov5)、[YOLOv6](https://github.com/PaddlePaddle/PaddleYOLO/tree/develop/configs/yolov6)和[YOLOv7](https://github.com/PaddlePaddle/PaddleYOLO/tree/develop/configs/yolov7)这3类模型的代码在[PaddleYOLO](https://github.com/PaddlePaddle/PaddleYOLO)中，**PaddleYOLO库开源协议为GPL 3.0**。 - 除非特殊说明，所有ResNet骨干网络采用[ResNet-B](https://arxiv.org/pdf/1812.01187)结构。 - **推理时间(fps)**: 推理时间是在一张Tesla V100的GPU上通过'tools/eval.py'测试所有验证集得到，单位是fps(图片数/秒), cuDNN版本是7.5，包括数据加载、网络前向执行和后处理, batch size是1。 @@ -18,83 +36,133 @@ - 我们采用和[Detectron](https://github.com/facebookresearch/Detectron/blob/master/MODEL_ZOO.md#training-schedules)相同的训练策略。 - 1x 策略表示：在总batch size为8时，初始学习率为0.01，在8 epoch和11 epoch后学习率分别下降10倍，最终训练12 epoch。 -- 2x 策略为1x策略的两倍，同时学习率调整位置也为1x的两倍。 +- 2x 策略为1x策略的两倍，同时学习率调整的epoch数位置也为1x的两倍。 ## ImageNet预训练模型 Paddle提供基于ImageNet的骨架网络预训练模型。所有预训练模型均通过标准的Imagenet-1k数据集训练得到，ResNet和MobileNet等是采用余弦学习率调整策略或SSLD知识蒸馏训练得到的高精度预训练模型，可在[PaddleClas](https://github.com/PaddlePaddle/PaddleClas)查看模型细节。 -## 基线 +# 基线 + +## 目标检测 ### Faster R-CNN -请参考[Faster R-CNN](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/faster_rcnn/) +请参考[Faster R-CNN](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/faster_rcnn/) -### Mask R-CNN +### YOLOv3 -请参考[Mask R-CNN](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/mask_rcnn/) +请参考[YOLOv3](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/yolov3/) -### Cascade R-CNN +### PP-YOLOE/PP-YOLOE+ -请参考[Cascade R-CNN](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/cascade_rcnn) +请参考[PP-YOLOE](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppyoloe/) -### YOLOv3 +### PP-YOLO/PP-YOLOv2 -请参考[YOLOv3](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/yolov3/) +请参考[PP-YOLO](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppyolo/) -### SSD +### PicoDet -请参考[SSD](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/ssd/) +请参考[PicoDet](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/picodet) -### FCOS +### RetinaNet -请参考[FCOS](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/fcos/) +请参考[RetinaNet](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/retinanet/) -### SOLOv2 +### Cascade R-CNN + +请参考[Cascade R-CNN](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/cascade_rcnn) + +### SSD/SSDLite -请参考[SOLOv2](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/solov2/) +请参考[SSD](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ssd/) -### PP-YOLO +### FCOS + +请参考[FCOS](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/fcos/) -请参考[PP-YOLO](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/ppyolo/) +### CenterNet -### TTFNet +请参考[CenterNet](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/centernet/) -请参考[TTFNet](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/ttfnet/) +### TTFNet/PAFNet + +请参考[TTFNet](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ttfnet/) ### Group Normalization -请参考[Group Normalization](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/gn/) +请参考[Group Normalization](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/gn/) ### Deformable ConvNets v2 -请参考[Deformable ConvNets v2](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/dcn/) +请参考[Deformable ConvNets v2](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/dcn/) ### HRNets -请参考[HRNets](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/hrnet/) +请参考[HRNets](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/hrnet/) ### Res2Net -请参考[Res2Net](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/res2net/) +请参考[Res2Net](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/res2net/) + +### ConvNeXt + +请参考[ConvNeXt](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/convnext/) ### GFL -请参考[GFL](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/gfl) +请参考[GFL](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/gfl) -### PicoDet +### TOOD + +请参考[TOOD](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/tood) + +### PSS-DET(RCNN-Enhance) + +请参考[PSS-DET](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/rcnn_enhance) + +### DETR + +请参考[DETR](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/detr) + +### Deformable DETR -请参考[PicoDet](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/picodet) +请参考[Deformable DETR](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/deformable_detr) -### PP-YOLOE +### Sparse R-CNN -请参考[PP-YOLOE](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/ppyoloe) +请参考[Sparse R-CNN](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/sparse_rcnn) + +### Vision Transformer + +请参考[Vision Transformer](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/vitdet) ### YOLOX 请参考[YOLOX](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/yolox) + +## 实例分割 + +### Mask R-CNN + +请参考[Mask R-CNN](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/mask_rcnn/) + +### Cascade R-CNN + +请参考[Cascade R-CNN](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/cascade_rcnn) + +### SOLOv2 + +请参考[SOLOv2](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/solov2/) + + +## [PaddleYOLO](https://github.com/PaddlePaddle/PaddleYOLO) + +请参考[PaddleYOLO模型库](https://github.com/PaddlePaddle/PaddleYOLO/tree/develop/docs/MODEL_ZOO_cn.md) + ### YOLOv5 请参考[YOLOv5](https://github.com/PaddlePaddle/PaddleYOLO/tree/develop/configs/yolov5) @@ -107,41 +175,78 @@ Paddle提供基于ImageNet的骨架网络预训练模型。所有预训练模型 请参考[YOLOv7](https://github.com/PaddlePaddle/PaddleYOLO/tree/develop/configs/yolov7) +### RTMDet + +请参考[RTMDet](https://github.com/PaddlePaddle/PaddleYOLO/tree/develop/configs/rtmdet) + + +## 人脸检测 + +请参考[人脸检测模型库](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/face_detection) + +### BlazeFace + +请参考[BlazeFace](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/face_detection/) + ## 旋转框检测 -[旋转框检测模型库](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/rotate) +请参考[旋转框检测模型库](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/rotate) + +### PP-YOLOE-R + +请参考[PP-YOLOE-R](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/rotate/ppyoloe_r) + +### FCOSR + +请参考[FCOSR](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/rotate/fcosr) + +### S2ANet + +请参考[S2ANet](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/rotate/s2anet) ## 关键点检测 +请参考[关键点检测模型库](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/keypoint) + ### PP-TinyPose -请参考[PP-TinyPose](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/keypoint/tiny_pose) +请参考[PP-TinyPose](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/keypoint/tiny_pose) + +### HRNet + +请参考[HRNet](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/keypoint/hrnet) -## HRNet +### Lite-HRNet -请参考[HRNet](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/keypoint/hrnet) +请参考[Lite-HRNet](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/keypoint/lite_hrnet) -## HigherHRNet +### HigherHRNet -请参考[HigherHRNet](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/keypoint/higherhrnet) +请参考[HigherHRNet](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/keypoint/higherhrnet) ## 多目标跟踪 +请参考[多目标跟踪模型库](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/mot) + ### DeepSORT -请参考[DeepSORT](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/mot/deepsort) +请参考[DeepSORT](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/mot/deepsort) -### JDE +### ByteTrack -请参考[JDE](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/mot/jde) +请参考[ByteTrack](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/mot/bytetrack) -### FairMOT +### OC-SORT -请参考[FairMOT](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/mot/fairmot) +请参考[OC-SORT](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/mot/ocsort) -### ByteTrack +### FairMOT/MC-FairMOT + +请参考[FairMOT](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/mot/fairmot) + +### JDE -请参考[ByteTrack](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/mot/bytetrack) +请参考[JDE](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/mot/jde) diff --git a/docs/MODEL_ZOO_en.md b/docs/MODEL_ZOO_en.md index b9cc2f9deffaba96d2cac71b8bdd79bf317827d0..999144c2e42e416a8c7409e01893184249f20f8b 100644 --- a/docs/MODEL_ZOO_en.md +++ b/docs/MODEL_ZOO_en.md @@ -1,4 +1,21 @@ -# Model Libraries and Baselines +# Model Zoos and Baselines + +# Content +- [Basic Settings](#Basic-Settings) + - [Test Environment](#Test-Environment) + - [General Settings](#General-Settings) + - [Training strategy](#Training-strategy) + - [ImageNet pretraining model](#ImageNet-pretraining-model) +- [Baseline](#Baseline) + - [Object Detection](#Object-Detection) + - [Instance Segmentation](#Instance-Segmentation) + - [PaddleYOLO](#PaddleYOLO) + - [Face Detection](#Face-Detection) + - [Rotated Object detection](#Rotated-Object-detection) + - [KeyPoint Detection](#KeyPoint-Detection) + - [Multi Object Tracking](#Multi-Object-Tracking) + +# Basic Settings ## Test Environment @@ -11,6 +28,7 @@ ## General Settings - All models were trained and tested in the COCO17 dataset. +- The codes of [YOLOv5](https://github.com/PaddlePaddle/PaddleYOLO/tree/develop/configs/yolov5),[YOLOv6](https://github.com/PaddlePaddle/PaddleYOLO/tree/develop/configs/yolov6) and [YOLOv7](https://github.com/PaddlePaddle/PaddleYOLO/tree/develop/configs/yolov7) can be found in [PaddleYOLO](https://github.com/PaddlePaddle/PaddleYOLO). Note that **the LICENSE of PaddleYOLO is GPL 3.0**. - Unless special instructions, all the ResNet backbone network using [ResNet-B](https://arxiv.org/pdf/1812.01187) structure. - **Inference time (FPS)**: The reasoning time was calculated on a Tesla V100 GPU by `tools/eval.py` testing all validation sets in FPS (number of pictures/second). CuDNN version is 7.5, including data loading, network forward execution and post-processing, and Batch size is 1. @@ -18,129 +36,216 @@ - We adopt and [Detectron](https://github.com/facebookresearch/Detectron/blob/master/MODEL_ZOO.md#training-schedules) in the same training strategy. - 1x strategy indicates that when the total batch size is 8, the initial learning rate is 0.01, and the learning rate decreases by 10 times after 8 epoch and 11 epoch, respectively, and the final training is 12 epoch. -- 2X strategy is twice as much as strategy 1X, and the learning rate adjustment position is twice as much as strategy 1X. +- 2x strategy is twice as much as strategy 1x, and the learning rate adjustment position of epochs is twice as much as strategy 1x. ## ImageNet pretraining model -Paddle provides a skeleton network pretraining model based on ImageNet. All pre-training models were trained by standard Imagenet 1K dataset. Res Net and Mobile Net are high-precision pre-training models obtained by cosine learning rate adjustment strategy or SSLD knowledge distillation training. Model details are available at [PaddleClas](https://github.com/PaddlePaddle/PaddleClas). +Paddle provides a skeleton network pretraining model based on ImageNet. All pre-training models were trained by standard Imagenet 1K dataset. ResNet and MobileNet are high-precision pre-training models obtained by cosine learning rate adjustment strategy or SSLD knowledge distillation training. Model details are available at [PaddleClas](https://github.com/PaddlePaddle/PaddleClas). -## Baseline +# Baseline + +## Object Detection ### Faster R-CNN -Please refer to[Faster R-CNN](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/faster_rcnn/) +Please refer to [Faster R-CNN](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/faster_rcnn/) -### Mask R-CNN +### YOLOv3 -Please refer to[Mask R-CNN](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/mask_rcnn/) +Please refer to [YOLOv3](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/yolov3/) -### Cascade R-CNN +### PP-YOLOE/PP-YOLOE+ -Please refer to[Cascade R-CNN](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/cascade_rcnn) +Please refer to [PP-YOLOE](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppyoloe/) -### YOLOv3 +### PP-YOLO/PP-YOLOv2 -Please refer to[YOLOv3](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/yolov3/) +Please refer to [PP-YOLO](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppyolo/) -### SSD +### PicoDet -Please refer to[SSD](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/ssd/) +Please refer to [PicoDet](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/picodet) -### FCOS +### RetinaNet -Please refer to[FCOS](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/fcos/) +Please refer to [RetinaNet](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/retinanet/) -### SOLOv2 +### Cascade R-CNN + +Please refer to [Cascade R-CNN](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/cascade_rcnn) + +### SSD/SSDLite + +Please refer to [SSD](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ssd/) -Please refer to[SOLOv2](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/solov2/) +### FCOS + +Please refer to [FCOS](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/fcos/) -### PP-YOLO +### CenterNet -Please refer to[PP-YOLO](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/ppyolo/) +Please refer to [CenterNet](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/centernet/) -### TTFNet +### TTFNet/PAFNet -请参考[TTFNet](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/ttfnet/) +Please refer to [TTFNet](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ttfnet/) ### Group Normalization -Please refer to[Group Normalization](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/gn/) +Please refer to [Group Normalization](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/gn/) ### Deformable ConvNets v2 -Please refer to[Deformable ConvNets v2](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/dcn/) +Please refer to [Deformable ConvNets v2](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/dcn/) ### HRNets -Please refer to[HRNets](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/hrnet/) +Please refer to [HRNets](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/hrnet/) ### Res2Net -Please refer to[Res2Net](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/res2net/) +Please refer to [Res2Net](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/res2net/) + +### ConvNeXt + +Please refer to [ConvNeXt](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/convnext/) ### GFL -Please refer to[GFL](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/gfl) +Please refer to [GFL](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/gfl) -### PicoDet +### TOOD + +Please refer to [TOOD](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/tood) + +### PSS-DET(RCNN-Enhance) + +Please refer to [PSS-DET](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/rcnn_enhance) + +### DETR + +Please refer to [DETR](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/detr) + +### Deformable DETR + +Please refer to [Deformable DETR](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/deformable_detr) -Please refer to[PicoDet](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/picodet) +### Sparse R-CNN -### PP-YOLOE +Please refer to [Sparse R-CNN](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/sparse_rcnn) -Please refer to[PP-YOLOE](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/ppyoloe) +### Vision Transformer + +Please refer to [Vision Transformer](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/vitdet) ### YOLOX -Please refer to[YOLOX](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/yolox) +Please refer to [YOLOX](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/yolox) + + +## Instance-Segmentation + +### Mask R-CNN + +Please refer to [Mask R-CNN](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/mask_rcnn/) + +### Cascade R-CNN + +Please refer to [Cascade R-CNN](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/cascade_rcnn) + +### SOLOv2 + +Please refer to [SOLOv2](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/solov2/) + + +## [PaddleYOLO](https://github.com/PaddlePaddle/PaddleYOLO) + +Please refer to [Model Zoo for PaddleYOLO](https://github.com/PaddlePaddle/PaddleYOLO/tree/develop/docs/MODEL_ZOO_en.md) ### YOLOv5 -Please refer to[YOLOv5](https://github.com/PaddlePaddle/PaddleYOLO/tree/develop/configs/yolov5) +Please refer to [YOLOv5](https://github.com/PaddlePaddle/PaddleYOLO/tree/develop/configs/yolov5) ### YOLOv6 -Please refer to[YOLOv6](https://github.com/PaddlePaddle/PaddleYOLO/tree/develop/configs/yolov6) +Please refer to [YOLOv6](https://github.com/PaddlePaddle/PaddleYOLO/tree/develop/configs/yolov6) ### YOLOv7 -Please refer to[YOLOv7](https://github.com/PaddlePaddle/PaddleYOLO/tree/develop/configs/yolov7) +Please refer to [YOLOv7](https://github.com/PaddlePaddle/PaddleYOLO/tree/develop/configs/yolov7) + +### RTMDet + +Please refer to [RTMDet](https://github.com/PaddlePaddle/PaddleYOLO/tree/develop/configs/rtmdet) + + +## Face Detection + +Please refer to [Model Zoo for Face Detection](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/face_detection) + +### BlazeFace + +Please refer to [BlazeFace](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/face_detection/) ## Rotated Object detection -[Model Zoo for Rotated Object Detection](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/rotate) +Please refer to [Model Zoo for Rotated Object Detection](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/rotate) + +### PP-YOLOE-R + +Please refer to [PP-YOLOE-R](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/rotate/ppyoloe_r) + +### FCOSR + +Please refer to [FCOSR](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/rotate/fcosr) + +### S2ANet + +Please refer to [S2ANet](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/rotate/s2anet) ## KeyPoint Detection +Please refer to [Model Zoo for KeyPoint Detection](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/keypoint) + ### PP-TinyPose -Please refer to [PP-TinyPose](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/keypoint/tiny_pose) +Please refer to [PP-TinyPose](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/keypoint/tiny_pose) + +### HRNet + +Please refer to [HRNet](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/keypoint/hrnet) -## HRNet +### Lite-HRNet -Please refer to [HRNet](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/keypoint/hrnet) +Please refer to [Lite-HRNet](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/keypoint/lite_hrnet) -## HigherHRNet +### HigherHRNet -Please refer to [HigherHRNet](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/keypoint/higherhrnet) +Please refer to [HigherHRNet](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/keypoint/higherhrnet) ## Multi-Object Tracking +Please refer to [Model Zoo for Multi-Object Tracking](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/mot) + ### DeepSORT -Please refer to [DeepSORT](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/mot/deepsort) +Please refer to [DeepSORT](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/mot/deepsort) -### JDE +### ByteTrack -Please refer to [JDE](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/mot/jde) +Please refer to [ByteTrack](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/mot/bytetrack) -### FairMOT +### OC-SORT -Please refer to [FairMOT](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/mot/fairmot) +Please refer to [OC-SORT](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/mot/ocsort) -### ByteTrack +### FairMOT/MC-FairMOT + +Please refer to [FairMOT](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/mot/fairmot) + +### JDE -Please refer to [ByteTrack](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/mot/bytetrack) +Please refer to [JDE](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/mot/jde) diff --git a/docs/feature_models/YOLOSERIES_MODEL.md b/docs/feature_models/PaddleYOLO_MODEL.md similarity index 65% rename from docs/feature_models/YOLOSERIES_MODEL.md rename to docs/feature_models/PaddleYOLO_MODEL.md index 022d4c9f549be54d20317e557e5fa4fc77245625..e63580a0aa8b91e3a8ed51213a31515d33fb70e3 100644 --- a/docs/feature_models/YOLOSERIES_MODEL.md +++ b/docs/feature_models/PaddleYOLO_MODEL.md @@ -1,24 +1,27 @@ -简体中文 | [English](YOLOSERIES_MODEL_en.md) +简体中文 | [English](MODEL_ZOO_en.md) # [**PaddleYOLO**](https://github.com/PaddlePaddle/PaddleYOLO) ## 内容 - [简介](#简介) - [模型库](#模型库) - - [PP-YOLOE](#PP-YOLOE) + - [PP-YOLOE+](#PP-YOLOE+) - [YOLOX](#YOLOX) - [YOLOv5](#YOLOv5) - [YOLOv6](#YOLOv6) - [YOLOv7](#YOLOv7) + - [RTMDet](#RTMDet) + - [VOC](#VOC) - [使用指南](#使用指南) - [一键运行全流程](#一键运行全流程) - [自定义数据集](#自定义数据集) ## 简介 -**PaddleYOLO**是基于[PaddleDetection](https://github.com/PaddlePaddle/PaddleDetection)的YOLO系列模型库，**只包含YOLO系列模型的相关代码**，支持`YOLOv3`,`PP-YOLO`,`PP-YOLOv2`,`PP-YOLOE`,`PP-YOLOE+`,`YOLOX`,`YOLOv5`,`YOLOv6`,`YOLOv7`等模型，欢迎一起使用和建设！ +**PaddleYOLO**是基于[PaddleDetection](https://github.com/PaddlePaddle/PaddleDetection)的YOLO系列模型库，**只包含YOLO系列模型的相关代码**，支持`YOLOv3`,`PP-YOLO`,`PP-YOLOv2`,`PP-YOLOE`,`PP-YOLOE+`,`YOLOX`,`YOLOv5`,`YOLOv6`,`YOLOv7`,`RTMDet`等模型，欢迎一起使用和建设！ ## 更新日志 +* 【2022/09/29】支持[RTMDet](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/rtmdet)预测和部署； * 【2022/09/26】发布[`PaddleYOLO`](https://github.com/PaddlePaddle/PaddleYOLO)模型套件； * 【2022/09/19】支持[`YOLOv6`](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov6)新版，包括n/t/s/m/l模型； * 【2022/08/23】发布`YOLOSeries`代码库: 支持`YOLOv3`,`PP-YOLOE`,`PP-YOLOE+`,`YOLOX`,`YOLOv5`,`YOLOv6`,`YOLOv7`等YOLO模型，支持`ConvNeXt`骨干网络高精度版`PP-YOLOE`,`YOLOX`和`YOLOv5`等模型，支持PaddleSlim无损加速量化训练`PP-YOLOE`,`YOLOv5`,`YOLOv6`和`YOLOv7`等模型，详情可阅读[此文章](https://mp.weixin.qq.com/s/Hki01Zs2lQgvLSLWS0btrA)； @@ -27,42 +30,29 @@ **注意:** - **PaddleYOLO**代码库协议为**GPL 3.0**，[YOLOv5](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov5),[YOLOv7](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov7)和[YOLOv6](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov6)这3类模型代码不合入[PaddleDetection](https://github.com/PaddlePaddle/PaddleDetection)，其余YOLO模型推荐在[PaddleDetection](https://github.com/PaddlePaddle/PaddleDetection)中使用，**会最先发布PP-YOLO系列特色检测模型的最新进展**；； - **PaddleYOLO**代码库**推荐使用paddlepaddle-2.3.2以上的版本**，请参考[官网](https://www.paddlepaddle.org.cn/install/quick?docurl=/documentation/docs/zh/install/pip/linux-pip.html)下载对应适合版本，**Windows平台请安装paddle develop版本**； - - -## 技术交流 - -- 如果你发现任何PaddleDetection存在的问题或者是建议, 欢迎通过[GitHub Issues](https://github.com/PaddlePaddle/PaddleDetection/issues)给我们提issues。 - -- **欢迎加入PaddleDetection 微信用户群（扫码填写问卷即可入群）** - - **入群福利 💎：获取PaddleDetection团队整理的重磅学习大礼包🎁** - - 📊 福利一：获取飞桨联合业界企业整理的开源数据集 - - 👨‍🏫 福利二：获取PaddleDetection历次发版直播视频与最新直播咨询 - - 🗳 福利三：获取垂类场景预训练模型集合，包括工业、安防、交通等5+行业场景 - - 🗂 福利四：获取10+全流程产业实操范例，覆盖火灾烟雾检测、人流量计数等产业高频场景 -
- -
+ - PaddleYOLO 的[Roadmap](https://github.com/PaddlePaddle/PaddleYOLO/issues/44) issue用于收集用户的需求，欢迎提出您的建议和需求。 + - 训练**自定义数据集**请参照[文档](#自定义数据集)和[issue](https://github.com/PaddlePaddle/PaddleYOLO/issues/43)。请首先**确保加载了COCO权重作为预训练**，YOLO检测模型建议**总`batch_size`至少大于`64`**去训练，如果资源不够请**换小模型**或**减小模型的输入尺度**，为了保障较高检测精度，**尽量不要尝试单卡训和总`batch_size`小于`32`训**； ## 模型库 -### [PP-YOLOE, PP-YOLOE+](../../configs/ppyoloe) +### [PP-YOLOE+](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/ppyoloe)
基础模型 -| 网络模型 | 输入尺寸 | 图片数/GPU | 学习率策略 | 推理耗时(ms) | mAPval
0.5:0.95 | mAPval
0.5 | Params(M) | FLOPs(G) | 下载链接 | 配置文件 | +| 网络模型 | 输入尺寸 | 图片数/GPU | 学习率策略 | TRT-FP16-Latency(ms) | mAPval
0.5:0.95 | mAPval
0.5 | Params(M) | FLOPs(G) | 下载链接 | 配置文件 | | :------------- | :------- | :-------: | :------: | :------------: | :---------------------: | :----------------: |:---------: | :------: |:---------------: |:-----: | -| PP-YOLOE-s | 640 | 32 | 400e | 2.9 | 43.4 | 60.0 | 7.93 | 17.36 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_s_400e_coco.pdparams) | [config](../../configs/ppyoloe/ppyoloe_crn_s_400e_coco.yml) | -| PP-YOLOE-s | 640 | 32 | 300e | 2.9 | 43.0 | 59.6 | 7.93 | 17.36 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_s_300e_coco.pdparams) | [config](../../configs/ppyoloe/ppyoloe_crn_s_300e_coco.yml) | -| PP-YOLOE-m | 640 | 28 | 300e | 6.0 | 49.0 | 65.9 | 23.43 | 49.91 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_m_300e_coco.pdparams) | [config](../../configs/ppyoloe/ppyoloe_crn_m_300e_coco.yml) | -| PP-YOLOE-l | 640 | 20 | 300e | 8.7 | 51.4 | 68.6 | 52.20 | 110.07 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_300e_coco.pdparams) | [config](../../configs/ppyoloe/ppyoloe_crn_l_300e_coco.yml) | -| PP-YOLOE-x | 640 | 16 | 300e | 14.9 | 52.3 | 69.5 | 98.42 | 206.59 |[model](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_x_300e_coco.pdparams) | [config](../../configs/ppyoloe/ppyoloe_crn_x_300e_coco.yml) | -| PP-YOLOE-tiny ConvNeXt| 640 | 16 | 36e | - | 44.6 | 63.3 | 33.04 | 13.87 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_convnext_tiny_36e_coco.pdparams) | [config](../../configs/convnext/ppyoloe_convnext_tiny_36e_coco.yml) | -| **PP-YOLOE+_s** | 640 | 8 | 80e | 2.9 | **43.7** | **60.6** | 7.93 | 17.36 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_plus_crn_s_80e_coco.pdparams) | [config](../../configs/ppyoloe/ppyoloe_plus_crn_s_80e_coco.yml) | -| **PP-YOLOE+_m** | 640 | 8 | 80e | 6.0 | **49.8** | **67.1** | 23.43 | 49.91 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_plus_crn_m_80e_coco.pdparams) | [config](../../configs/ppyoloe/ppyoloe_plus_crn_m_80e_coco.yml) | -| **PP-YOLOE+_l** | 640 | 8 | 80e | 8.7 | **52.9** | **70.1** | 52.20 | 110.07 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_plus_crn_l_80e_coco.pdparams) | [config](../../configs/ppyoloe/ppyoloe_plus_crn_l_80e_coco.yml) | -| **PP-YOLOE+_x** | 640 | 8 | 80e | 14.9 | **54.7** | **72.0** | 98.42 | 206.59 |[model](https://paddledet.bj.bcebos.com/models/ppyoloe_plus_crn_x_80e_coco.pdparams) | [config](../../configs/ppyoloe/ppyoloe_plus_crn_x_80e_coco.yml) | +| PP-YOLOE-s | 640 | 32 | 400e | 2.9 | 43.4 | 60.0 | 7.93 | 17.36 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_s_400e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/ppyoloe/ppyoloe_crn_s_400e_coco.yml) | +| PP-YOLOE-s | 640 | 32 | 300e | 2.9 | 43.0 | 59.6 | 7.93 | 17.36 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_s_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/ppyoloe/ppyoloe_crn_s_300e_coco.yml) | +| PP-YOLOE-m | 640 | 28 | 300e | 6.0 | 49.0 | 65.9 | 23.43 | 49.91 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_m_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/ppyoloe/ppyoloe_crn_m_300e_coco.yml) | +| PP-YOLOE-l | 640 | 20 | 300e | 8.7 | 51.4 | 68.6 | 52.20 | 110.07 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/ppyoloe/ppyoloe_crn_l_300e_coco.yml) | +| PP-YOLOE-x | 640 | 16 | 300e | 14.9 | 52.3 | 69.5 | 98.42 | 206.59 |[model](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_x_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/ppyoloe/ppyoloe_crn_x_300e_coco.yml) | +| PP-YOLOE-tiny ConvNeXt| 640 | 16 | 36e | - | 44.6 | 63.3 | 33.04 | 13.87 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_convnext_tiny_36e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/convnext/ppyoloe_convnext_tiny_36e_coco.yml) | +| **PP-YOLOE+_s** | 640 | 8 | 80e | 2.9 | **43.7** | **60.6** | 7.93 | 17.36 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_plus_crn_s_80e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/ppyoloe/ppyoloe_plus_crn_s_80e_coco.yml) | +| **PP-YOLOE+_m** | 640 | 8 | 80e | 6.0 | **49.8** | **67.1** | 23.43 | 49.91 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_plus_crn_m_80e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/ppyoloe/ppyoloe_plus_crn_m_80e_coco.yml) | +| **PP-YOLOE+_l** | 640 | 8 | 80e | 8.7 | **52.9** | **70.1** | 52.20 | 110.07 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_plus_crn_l_80e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/ppyoloe/ppyoloe_plus_crn_l_80e_coco.yml) | +| **PP-YOLOE+_x** | 640 | 8 | 80e | 14.9 | **54.7** | **72.0** | 98.42 | 206.59 |[model](https://paddledet.bj.bcebos.com/models/ppyoloe_plus_crn_x_80e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/ppyoloe/ppyoloe_plus_crn_x_80e_coco.yml) |
@@ -83,22 +73,22 @@ -### [YOLOX](../../configs/yolox) +### [YOLOX](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolox)
基础模型 -| 网络模型 | 输入尺寸 | 图片数/GPU | 学习率策略 | 推理耗时(ms) | mAPval
0.5:0.95 | mAPval
0.5 | Params(M) | FLOPs(G) | 下载链接 | 配置文件 | +| 网络模型 | 输入尺寸 | 图片数/GPU | 学习率策略 | TRT-FP16-Latency(ms) | mAPval
0.5:0.95 | mAPval
0.5 | Params(M) | FLOPs(G) | 下载链接 | 配置文件 | | :------------- | :------- | :-------: | :------: | :------------: | :---------------------: | :----------------: |:---------: | :------: |:---------------: |:-----: | -| YOLOX-nano | 416 | 8 | 300e | 2.3 | 26.1 | 42.0 | 0.91 | 1.08 | [model](https://paddledet.bj.bcebos.com/models/yolox_nano_300e_coco.pdparams) | [config](../../configs/yolox/yolox_nano_300e_coco.yml) | -| YOLOX-tiny | 416 | 8 | 300e | 2.8 | 32.9 | 50.4 | 5.06 | 6.45 | [model](https://paddledet.bj.bcebos.com/models/yolox_tiny_300e_coco.pdparams) | [config](../../configs/yolox/yolox_tiny_300e_coco.yml) | -| YOLOX-s | 640 | 8 | 300e | 3.0 | 40.4 | 59.6 | 9.0 | 26.8 | [model](https://paddledet.bj.bcebos.com/models/yolox_s_300e_coco.pdparams) | [config](../../configs/yolox/yolox_s_300e_coco.yml) | -| YOLOX-m | 640 | 8 | 300e | 5.8 | 46.9 | 65.7 | 25.3 | 73.8 | [model](https://paddledet.bj.bcebos.com/models/yolox_m_300e_coco.pdparams) | [config](../../configs/yolox/yolox_m_300e_coco.yml) | -| YOLOX-l | 640 | 8 | 300e | 9.3 | 50.1 | 68.8 | 54.2 | 155.6 | [model](https://paddledet.bj.bcebos.com/models/yolox_l_300e_coco.pdparams) | [config](../../configs/yolox/yolox_l_300e_coco.yml) | -| YOLOX-x | 640 | 8 | 300e | 16.6 | **51.8** | **70.6** | 99.1 | 281.9 | [model](https://paddledet.bj.bcebos.com/models/yolox_x_300e_coco.pdparams) | [config](../../configs/yolox/yolox_x_300e_coco.yml) | +| YOLOX-nano | 416 | 8 | 300e | 2.3 | 26.1 | 42.0 | 0.91 | 1.08 | [model](https://paddledet.bj.bcebos.com/models/yolox_nano_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolox/yolox_nano_300e_coco.yml) | +| YOLOX-tiny | 416 | 8 | 300e | 2.8 | 32.9 | 50.4 | 5.06 | 6.45 | [model](https://paddledet.bj.bcebos.com/models/yolox_tiny_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolox/yolox_tiny_300e_coco.yml) | +| YOLOX-s | 640 | 8 | 300e | 3.0 | 40.4 | 59.6 | 9.0 | 26.8 | [model](https://paddledet.bj.bcebos.com/models/yolox_s_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolox/yolox_s_300e_coco.yml) | +| YOLOX-m | 640 | 8 | 300e | 5.8 | 46.9 | 65.7 | 25.3 | 73.8 | [model](https://paddledet.bj.bcebos.com/models/yolox_m_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolox/yolox_m_300e_coco.yml) | +| YOLOX-l | 640 | 8 | 300e | 9.3 | 50.1 | 68.8 | 54.2 | 155.6 | [model](https://paddledet.bj.bcebos.com/models/yolox_l_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolox/yolox_l_300e_coco.yml) | +| YOLOX-x | 640 | 8 | 300e | 16.6 | **51.8** | **70.6** | 99.1 | 281.9 | [model](https://paddledet.bj.bcebos.com/models/yolox_x_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolox/yolox_x_300e_coco.yml) | YOLOX-cdn-tiny | 416 | 8 | 300e | 1.9 | 32.4 | 50.2 | 5.03 | 6.33 | [model](https://paddledet.bj.bcebos.com/models/yolox_cdn_tiny_300e_coco.pdparams) | [config](c../../onfigs/yolox/yolox_cdn_tiny_300e_coco.yml) | -| YOLOX-crn-s | 640 | 8 | 300e | 3.0 | 40.4 | 59.6 | 7.7 | 24.69 | [model](https://paddledet.bj.bcebos.com/models/yolox_crn_s_300e_coco.pdparams) | [config](../../configs/yolox/yolox_crn_s_300e_coco.yml) | -| YOLOX-s ConvNeXt| 640 | 8 | 36e | - | 44.6 | 65.3 | 36.2 | 27.52 | [model](https://paddledet.bj.bcebos.com/models/yolox_convnext_s_36e_coco.pdparams) | [config](../../configs/convnext/yolox_convnext_s_36e_coco.yml) | +| YOLOX-crn-s | 640 | 8 | 300e | 3.0 | 40.4 | 59.6 | 7.7 | 24.69 | [model](https://paddledet.bj.bcebos.com/models/yolox_crn_s_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolox/yolox_crn_s_300e_coco.yml) | +| YOLOX-s ConvNeXt| 640 | 8 | 36e | - | 44.6 | 65.3 | 36.2 | 27.52 | [model](https://paddledet.bj.bcebos.com/models/yolox_convnext_s_36e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/convnext/yolox_convnext_s_36e_coco.yml) |
@@ -121,14 +111,19 @@
基础模型 -| 网络模型 | 输入尺寸 | 图片数/GPU | 学习率策略 | 推理耗时(ms) | mAPval
0.5:0.95 | mAPval
0.5 | Params(M) | FLOPs(G) | 下载链接 | 配置文件 | +| 网络模型 | 输入尺寸 | 图片数/GPU | 学习率策略 | TRT-FP16-Latency(ms) | mAPval
0.5:0.95 | mAPval
0.5 | Params(M) | FLOPs(G) | 下载链接 | 配置文件 | | :------------- | :------- | :-------: | :------: | :------------: | :---------------------: | :----------------: |:---------: | :------: |:---------------: |:-----: | | YOLOv5-n | 640 | 16 | 300e | 2.6 | 28.0 | 45.7 | 1.87 | 4.52 | [model](https://paddledet.bj.bcebos.com/models/yolov5_n_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov5/yolov5_n_300e_coco.yml) | -| YOLOv5-s | 640 | 8 | 300e | 3.2 | 37.0 | 55.9 | 7.24 | 16.54 | [model](https://paddledet.bj.bcebos.com/models/yolov5_s_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov5/yolov5_s_300e_coco.yml) | -| YOLOv5-m | 640 | 5 | 300e | 5.2 | 45.3 | 63.8 | 21.19 | 49.08 | [model](https://paddledet.bj.bcebos.com/models/yolov5_m_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov5/yolov5_m_300e_coco.yml) | -| YOLOv5-l | 640 | 3 | 300e | 7.9 | 48.6 | 66.9 | 46.56 | 109.32 | [model](https://paddledet.bj.bcebos.com/models/yolov5_l_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov5/yolov5_l_300e_coco.yml) | -| YOLOv5-x | 640 | 2 | 300e | 13.7 | **50.6** | **68.7** | 86.75 | 205.92 | [model](https://paddledet.bj.bcebos.com/models/yolov5_x_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov5/yolov5_x_300e_coco.yml) | +| YOLOv5-s | 640 | 16 | 300e | 3.2 | 37.6 | 56.7 | 7.24 | 16.54 | [model](https://paddledet.bj.bcebos.com/models/yolov5_s_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov5/yolov5_s_300e_coco.yml) | +| YOLOv5-m | 640 | 16 | 300e | 5.2 | 45.4 | 64.1 | 21.19 | 49.08 | [model](https://paddledet.bj.bcebos.com/models/yolov5_m_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov5/yolov5_m_300e_coco.yml) | +| YOLOv5-l | 640 | 16 | 300e | 7.9 | 48.9 | 67.1 | 46.56 | 109.32 | [model](https://paddledet.bj.bcebos.com/models/yolov5_l_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov5/yolov5_l_300e_coco.yml) | +| YOLOv5-x | 640 | 16 | 300e | 13.7 | 50.6 | 68.7 | 86.75 | 205.92 | [model](https://paddledet.bj.bcebos.com/models/yolov5_x_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov5/yolov5_x_300e_coco.yml) | | YOLOv5-s ConvNeXt| 640 | 8 | 36e | - | 42.4 | 65.3 | 34.54 | 17.96 | [model](https://paddledet.bj.bcebos.com/models/yolov5_convnext_s_36e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov5/yolov5_convnext_s_36e_coco.yml) | +| *YOLOv5p6-n | 1280 | 16 | 300e | - | 35.9 | 54.2 | 3.25 | 9.23 | [model](https://paddledet.bj.bcebos.com/models/yolov5p6_n_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov5/yolov5p6_n_300e_coco.yml) | +| *YOLOv5p6-s | 1280 | 16 | 300e | - | 44.5 | 63.3 | 12.63 | 33.81 | [model](https://paddledet.bj.bcebos.com/models/yolov5p6_s_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov5/yolov5p6_s_300e_coco.yml) | +| *YOLOv5p6-m | 1280 | 16 | 300e | - | 51.1 | 69.0 | 35.73 | 100.21 | [model](https://paddledet.bj.bcebos.com/models/yolov5p6_m_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov5/yolov5p6_m_300e_coco.yml) | +| *YOLOv5p6-l | 1280 | 8 | 300e | - | 53.4 | 71.0 | 76.77 | 223.09 | [model](https://paddledet.bj.bcebos.com/models/yolov5p6_l_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov5/yolov5p6_l_300e_coco.yml) | +| *YOLOv5p6-x | 1280 | 8 | 300e | - | 54.7 | 72.4 | 140.80 | 420.03 | [model](https://paddledet.bj.bcebos.com/models/yolov5p6_x_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov5/yolov5p6_x_300e_coco.yml) |
@@ -150,10 +145,10 @@
基础模型 -| 网络网络 | 输入尺寸 | 图片数/GPU | 学习率策略 | 模型推理耗时(ms) | mAP | AP50 | Params(M) | FLOPs(G) | 下载链接 | 配置文件 | +| 网络网络 | 输入尺寸 | 图片数/GPU | 学习率策略 | TRT-FP16-Latency(ms) | mAP | AP50 | Params(M) | FLOPs(G) | 下载链接 | 配置文件 | | :------------- | :------- | :-------: | :------: | :---------: | :-----: |:-----: | :-----: |:-----: | :-------------: | :-----: | -| *YOLOv6-n | 416 | 32 | 400e | 1.0 | 31.1 | 45.3 | 4.74 | 5.16 |[model](https://paddledet.bj.bcebos.com/models/yolov6_n_416_400e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov6/yolov6_n_416_400e_coco.yml) | -| *YOLOv6-n | 640 | 32 | 400e | 1.3 | 36.1 | 51.9 | 4.74 | 12.21 |[model](https://paddledet.bj.bcebos.com/models/yolov6_n_400e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov6/yolov6_n_400e_coco.yml) | +| YOLOv6-n | 416 | 32 | 400e | 1.0 | 31.1 | 45.3 | 4.74 | 5.16 |[model](https://paddledet.bj.bcebos.com/models/yolov6_n_416_400e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov6/yolov6_n_416_400e_coco.yml) | +| YOLOv6-n | 640 | 32 | 400e | 1.3 | 36.1 | 51.9 | 4.74 | 12.21 |[model](https://paddledet.bj.bcebos.com/models/yolov6_n_400e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov6/yolov6_n_400e_coco.yml) | | *YOLOv6-t | 640 | 32 | 400e | 2.1 | 40.7 | 57.4 | 10.63 | 27.29 |[model](https://paddledet.bj.bcebos.com/models/yolov6_t_400e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov6/yolov6_t_400e_coco.yml) | | *YOLOv6-s | 640 | 32 | 400e | 2.6 | 43.4 | 60.5 | 18.87 | 48.35 |[model](https://paddledet.bj.bcebos.com/models/yolov6_s_400e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov6/yolov6_s_400e_coco.yml) | | *YOLOv6-m | 640 | 32 | 300e | 5.0 | 49.0 | 66.5 | 37.17 | 88.82 |[model](https://paddledet.bj.bcebos.com/models/yolov6_m_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov6/yolov6_m_300e_coco.yml) | @@ -182,7 +177,7 @@
基础模型 -| 网络模型 | 输入尺寸 | 图片数/GPU | 学习率策略 | 推理耗时(ms) | mAPval
0.5:0.95 | mAPval
0.5 | Params(M) | FLOPs(G) | 下载链接 | 配置文件 | +| 网络模型 | 输入尺寸 | 图片数/GPU | 学习率策略 | TRT-FP16-Latency(ms) | mAPval
0.5:0.95 | mAPval
0.5 | Params(M) | FLOPs(G) | 下载链接 | 配置文件 | | :------------- | :------- | :-------: | :------: | :------------: | :---------------------: | :----------------: |:---------: | :------: |:---------------: |:-----: | | YOLOv7-L | 640 | 32 | 300e | 7.4 | 51.0 | 70.2 | 37.62 | 106.08 |[model](https://paddledet.bj.bcebos.com/models/yolov7_l_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov7/yolov7_l_300e_coco.yml) | | *YOLOv7-X | 640 | 32 | 300e | 12.2 | 53.0 | 70.8 | 71.34 | 190.08 | [model](https://paddledet.bj.bcebos.com/models/yolov7_x_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov7/yolov7_x_300e_coco.yml) | @@ -213,11 +208,40 @@
+### [RTMDet](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/rtmdet) + +
+ 基础模型 + +| 网络网络 | 输入尺寸 | 图片数/GPU | 学习率策略 | TRT-FP16-Latency(ms) | mAP | AP50 | Params(M) | FLOPs(G) | 下载链接 | 配置文件 | +| :------------- | :------- | :-------: | :------: | :---------: | :-----: |:-----: | :-----: |:-----: | :-------------: | :-----: | +| *RTMDet-t | 640 | 32 | 300e | 2.8 | 40.9 | 57.9 | 4.90 | 16.21 |[下载链接](https://paddledet.bj.bcebos.com/models/rtmdet_t_300e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/rtmdet/rtmdet_t_300e_coco.yml) | +| *RTMDet-s | 640 | 32 | 300e | 3.3 | 44.5 | 62.0 | 8.89 | 29.71 |[下载链接](https://paddledet.bj.bcebos.com/models/rtmdet_s_300e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/rtmdet/rtmdet_s_300e_coco.yml) | +| *RTMDet-m | 640 | 32 | 300e | 6.4 | 49.1 | 66.8 | 24.71 | 78.47 |[下载链接](https://paddledet.bj.bcebos.com/models/rtmdet_m_300e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/rtmdet/rtmdet_m_300e_coco.yml) | +| *RTMDet-l | 640 | 32 | 300e | 10.2 | 51.2 | 68.8 | 52.31 | 160.32 |[下载链接](https://paddledet.bj.bcebos.com/models/rtmdet_l_300e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/rtmdet/rtmdet_l_300e_coco.yml) | +| *RTMDet-x | 640 | 32 | 300e | 18.0 | 52.6 | 70.4 | 94.86 | 283.12 |[下载链接](https://paddledet.bj.bcebos.com/models/rtmdet_x_300e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/rtmdet/rtmdet_x_300e_coco.yml) | + +
+ +
+ 部署模型 + +| 网络模型 | 输入尺寸 | 导出后的权重(w/o NMS) | ONNX(w/o NMS) | +| :-------- | :--------: | :---------------------: | :----------------: | +| RTMDet-t | 640 | [( w/ nms)](https://paddledet.bj.bcebos.com/deploy/yoloseries/rtmdet/rtmdet_t_300e_coco_w_nms.zip) | [( w/o nms)](https://paddledet.bj.bcebos.com/deploy/yoloseries/rtmdet/rtmdet_t_300e_coco_wo_nms.zip) | [( w/ nms)](https://paddledet.bj.bcebos.com/deploy/yoloseries/rtmdet/rtmdet_t_300e_coco_w_nms.onnx) | [( w/o nms)](https://paddledet.bj.bcebos.com/deploy/yoloseries/rtmdet/rtmdet_t_300e_coco_wo_nms.onnx) | +| RTMDet-s | 640 | [( w/ nms)](https://paddledet.bj.bcebos.com/deploy/yoloseries/rtmdet/rtmdet_s_300e_coco_w_nms.zip) | [( w/o nms)](https://paddledet.bj.bcebos.com/deploy/yoloseries/rtmdet/rtmdet_s_300e_coco_wo_nms.zip) | [( w/ nms)](https://paddledet.bj.bcebos.com/deploy/yoloseries/rtmdet/rtmdet_s_300e_coco_w_nms.onnx) | [( w/o nms)](https://paddledet.bj.bcebos.com/deploy/yoloseries/rtmdet/rtmdet_s_300e_coco_wo_nms.onnx) | +| RTMDet-m | 640 | [( w/ nms)](https://paddledet.bj.bcebos.com/deploy/yoloseries/rtmdet/rtmdet_m_300e_coco_w_nms.zip) | [( w/o nms)](https://paddledet.bj.bcebos.com/deploy/yoloseries/rtmdet/rtmdet_m_300e_coco_wo_nms.zip) | [( w/ nms)](https://paddledet.bj.bcebos.com/deploy/yoloseries/rtmdet/rtmdet_m_300e_coco_w_nms.onnx) | [( w/o nms)](https://paddledet.bj.bcebos.com/deploy/yoloseries/rtmdet/rtmdet_m_300e_coco_wo_nms.onnx) | +| RTMDet-l | 640 | [( w/ nms)](https://paddledet.bj.bcebos.com/deploy/yoloseries/rtmdet/rtmdet_l_300e_coco_w_nms.zip) | [( w/o nms)](https://paddledet.bj.bcebos.com/deploy/yoloseries/rtmdet/rtmdet_l_300e_coco_wo_nms.zip) | [( w/ nms)](https://paddledet.bj.bcebos.com/deploy/yoloseries/rtmdet/rtmdet_l_300e_coco_w_nms.onnx) | [( w/o nms)](https://paddledet.bj.bcebos.com/deploy/yoloseries/rtmdet/rtmdet_l_300e_coco_wo_nms.onnx) | +| RTMDet-x | 640 | [( w/ nms)](https://paddledet.bj.bcebos.com/deploy/yoloseries/rtmdet/rtmdet_x_300e_coco_w_nms.zip) | [( w/o nms)](https://paddledet.bj.bcebos.com/deploy/yoloseries/rtmdet/rtmdet_x_300e_coco_wo_nms.zip) | [( w/ nms)](https://paddledet.bj.bcebos.com/deploy/yoloseries/rtmdet/rtmdet_x_300e_coco_w_nms.onnx) | [( w/o nms)](https://paddledet.bj.bcebos.com/deploy/yoloseries/rtmdet/rtmdet_x_300e_coco_wo_nms.onnx) | + +
+ + ### **注意:** - 所有模型均使用COCO train2017作为训练集，在COCO val2017上验证精度，模型前带*表示训练更新中。 - - 具体精度和速度细节请查看[PP-YOLOE](../../configs/ppyoloe),[YOLOX](../../configs/yolox),[YOLOv5](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov5),[YOLOv6](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov6),[YOLOv7](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov7)，**其中YOLOv5,YOLOv6,YOLOv7评估并未采用`multi_label`形式**。 -- 模型推理耗时(ms)为TensorRT-FP16下测试的耗时，不包含数据预处理和模型输出后处理(NMS)的耗时。测试采用单卡V100，batch size=1，测试环境为**paddlepaddle-2.3.0**, **CUDA 11.2**, **CUDNN 8.2**, **GCC-8.2**, **TensorRT 8.0.3.4**，具体请参考各自模型主页。 -- **统计FLOPs(G)**，首先安装[PaddleSlim](https://github.com/PaddlePaddle/PaddleSlim), `pip install paddleslim`，然后设置[runtime.yml](../../configs/runtime.yml)里`print_flops: True`，并且注意确保是**单尺度**下如640x640，**打印的是MACs，FLOPs=2*MACs**。 + - 具体精度和速度细节请查看[PP-YOLOE](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/ppyoloe),[YOLOX](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolox),[YOLOv5](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov5),[YOLOv6](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov6),[YOLOv7](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov7)，**其中YOLOv5,YOLOv6,YOLOv7评估并未采用`multi_label`形式**。 +- 模型推理耗时(ms)为TensorRT-FP16下测试的耗时，**不包含数据预处理和模型输出后处理(NMS)的耗时**。测试采用**单卡Tesla T4 GPU，batch size=1**，测试环境为**paddlepaddle-2.3.2**, **CUDA 11.2**, **CUDNN 8.2**, **GCC-8.2**, **TensorRT 8.0.3.4**，具体请参考各自模型主页。 +- **统计FLOPs(G)和Params(M)**，首先安装[PaddleSlim](https://github.com/PaddlePaddle/PaddleSlim), `pip install paddleslim`，然后设置[runtime.yml](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/runtime.yml)里`print_flops: True`和`print_params: True`，并且注意确保是**单尺度**下如640x640，**打印的是MACs，FLOPs=2*MACs**。 - 各模型导出后的权重以及ONNX，分为**带(w)**和**不带(wo)**后处理NMS，都提供了下载链接，请参考各自模型主页下载。`w_nms`表示**带NMS后处理**，可以直接使用预测出最终检测框结果如```python deploy/python/infer.py --model_dir=ppyoloe_crn_l_300e_coco_w_nms/ --image_file=demo/000000014439.jpg --device=GPU```；`wo_nms`表示**不带NMS后处理**，是**测速**时使用，如需预测出检测框结果需要找到**对应head中的后处理相关代码**并修改为如下： ``` if self.exclude_nms: @@ -232,6 +256,29 @@ - 基于[PaddleSlim](https://github.com/PaddlePaddle/PaddleSlim)对YOLO系列模型进行量化训练，可以实现精度基本无损，速度普遍提升30%以上，具体请参照[模型自动化压缩工具ACT](https://github.com/PaddlePaddle/PaddleSlim/tree/develop/example/auto_compression)。 +### [VOC](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/voc) + +
+ 基础模型 + +| 网络模型 | 输入尺寸 | 图片数/GPU | 学习率策略 | TRT-FP16-Latency(ms) | mAP(0.50,11point) | Params(M) | FLOPs(G) | 下载链接 | 配置文件 | +| :-----------: | :-------: | :-------: | :------: | :------------: | :---------------: | :------------------: |:-----------------: | :------: | :------: | +| YOLOv5-s | 640 | 16 | 60e | 3.2 | 80.3 | 7.24 | 16.54 | [下载链接](https://paddledet.bj.bcebos.com/models/yolov5_s_60e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/voc/yolov5_s_60e_voc.yml) | +| YOLOv6-s | 640 | 32 | 40e | 2.7 | 84.7 | 18.87 | 48.35 | [下载链接](https://paddledet.bj.bcebos.com/models/yolov6_s_40e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/voc/yolov6_s_40e_voc.yml) | +| YOLOv7-tiny | 640 | 32 | 60e | 2.6 | 80.2 | 6.23 | 6.90 | [下载链接](https://paddledet.bj.bcebos.com/models/yolov7_tiny_60e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/voc/yolov7_tiny_60e_voc.yml) | +| YOLOX-s | 640 | 8 | 40e | 3.0 | 82.9 | 9.0 | 26.8 | [下载链接](https://paddledet.bj.bcebos.com/models/yolox_s_40e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/voc/yolox_s_40e_voc.yml) | +| PP-YOLOE+_s | 640 | 8 | 30e | 2.9 | 86.7 | 7.93 | 17.36 | [下载链接](https://paddledet.bj.bcebos.com/models/ppyoloe_plus_crn_s_30e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/voc/ppyoloe_plus_crn_s_30e_voc.yml) | + +
+ +**注意:** + - VOC数据集训练的mAP为`mAP(IoU=0.5)`的结果，且评估未使用`multi_label`等trick； + - 所有YOLO VOC模型均加载各自模型的COCO权重作为预训练，各个配置文件的配置均为默认使用8卡GPU，可作为自定义数据集设置参考，具体精度会因数据集而异； + - YOLO检测模型建议**总`batch_size`至少大于`64`**去训练，如果资源不够请**换小模型**或**减小模型的输入尺度**，为了保障较高检测精度，**尽量不要尝试单卡训和总`batch_size`小于`64`训**； + - Params(M)和FLOPs(G)均为训练时所测，YOLOv7没有s模型，故选用tiny模型； + - TRT-FP16-Latency(ms)测速相关请查看各YOLO模型的config的主页； + + ## 使用指南 下载MS-COCO数据集，[官网](https://cocodataset.org)下载地址为: [annotations](http://images.cocodataset.org/annotations/annotations_trainval2017.zip), [train2017](http://images.cocodataset.org/zips/train2017.zip), [val2017](http://images.cocodataset.org/zips/val2017.zip), [test2017](http://images.cocodataset.org/zips/test2017.zip)。 @@ -239,50 +286,52 @@ PaddleDetection团队提供的下载链接为：[coco](https://bj.bcebos.com/v1/ ### **一键运行全流程** -``` -model_type=ppyoloe # 可修改，如 yolov7 -job_name=ppyoloe_crn_l_300e_coco # 可修改，如 yolov7_l_300e_coco -config=configs/${model_type}/${job_name}.yml +将以下命令写在一个脚本文件里如```run.sh```，一键运行命令为：```sh run.sh```，也可命令行一句句去运行。 + +```bash +model_name=ppyoloe # 可修改，如 yolov7 +job_name=ppyoloe_plus_crn_l_300e_coco # 可修改，如 yolov7_tiny_300e_coco + +config=configs/${model_name}/${job_name}.yml log_dir=log_dir/${job_name} # weights=https://bj.bcebos.com/v1/paddledet/models/${job_name}.pdparams weights=output/${job_name}/model_final.pdparams # 1.训练（单卡/多卡） -# CUDA_VISIBLE_DEVICES=0 python3.7 tools/train.py -c ${config} --eval --amp -python3.7 -m paddle.distributed.launch --log_dir=${log_dir} --gpus 0,1,2,3,4,5,6,7 tools/train.py -c ${config} --eval --amp +# CUDA_VISIBLE_DEVICES=0 python tools/train.py -c ${config} --eval --amp +python -m paddle.distributed.launch --log_dir=${log_dir} --gpus 0,1,2,3,4,5,6,7 tools/train.py -c ${config} --eval --amp # 2.评估 -CUDA_VISIBLE_DEVICES=0 python3.7 tools/eval.py -c ${config} -o weights=${weights} --classwise +CUDA_VISIBLE_DEVICES=0 python tools/eval.py -c ${config} -o weights=${weights} --classwise # 3.直接预测 -CUDA_VISIBLE_DEVICES=0 python3.7 tools/infer.py -c ${config} -o weights=${weights} --infer_img=demo/000000014439_640x640.jpg --draw_threshold=0.5 +CUDA_VISIBLE_DEVICES=0 python tools/infer.py -c ${config} -o weights=${weights} --infer_img=demo/000000014439_640x640.jpg --draw_threshold=0.5 # 4.导出模型 -CUDA_VISIBLE_DEVICES=0 python3.7 tools/export_model.py -c ${config} -o weights=${weights} # exclude_nms=True trt=True +CUDA_VISIBLE_DEVICES=0 python tools/export_model.py -c ${config} -o weights=${weights} # exclude_nms=True trt=True # 5.部署预测 -CUDA_VISIBLE_DEVICES=0 python3.7 deploy/python/infer.py --model_dir=output_inference/${job_name} --image_file=demo/000000014439_640x640.jpg --device=GPU +CUDA_VISIBLE_DEVICES=0 python deploy/python/infer.py --model_dir=output_inference/${job_name} --image_file=demo/000000014439_640x640.jpg --device=GPU -# 6.部署测速 -CUDA_VISIBLE_DEVICES=0 python3.7 deploy/python/infer.py --model_dir=output_inference/${job_name} --image_file=demo/000000014439_640x640.jpg --device=GPU --run_benchmark=True # --run_mode=trt_fp16 +# 6.部署测速，加 “--run_mode=trt_fp16” 表示在TensorRT FP16模式下测速 +CUDA_VISIBLE_DEVICES=0 python deploy/python/infer.py --model_dir=output_inference/${job_name} --image_file=demo/000000014439_640x640.jpg --device=GPU --run_benchmark=True # --run_mode=trt_fp16 # 7.onnx导出 paddle2onnx --model_dir output_inference/${job_name} --model_filename model.pdmodel --params_filename model.pdiparams --opset_version 12 --save_file ${job_name}.onnx # 8.onnx测速 /usr/local/TensorRT-8.0.3.4/bin/trtexec --onnx=${job_name}.onnx --workspace=4096 --avgRuns=10 --shapes=input:1x3x640x640 --fp16 - ``` -**注意:** -- 将以上命令写在一个脚本文件里如```run.sh```，一键运行命令为：```sh run.sh```，也可命令行一句句去运行。 - 如果想切换模型，只要修改开头两行即可，如: ``` - model_type=yolov7 + model_name=yolov7 job_name=yolov7_l_300e_coco ``` -- **统计FLOPs(G)**，首先安装[PaddleSlim](https://github.com/PaddlePaddle/PaddleSlim), `pip install paddleslim`，然后设置[runtime.yml](../../configs/runtime.yml)里`print_flops: True`，并且注意确保是**单尺度**下如640x640，**打印的是MACs，FLOPs=2*MACs**。 +- 导出**onnx**，首先安装[Paddle2ONNX](https://github.com/PaddlePaddle/Paddle2ONNX)，`pip install paddle2onnx`； +- **统计FLOPs(G)和Params(M)**，首先安装[PaddleSlim](https://github.com/PaddlePaddle/PaddleSlim)，`pip install paddleslim`，然后设置[runtime.yml](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/runtime.yml)里`print_flops: True`和`print_params: True`，并且注意确保是**单尺度**下如640x640，**打印的是MACs，FLOPs=2*MACs**。 + ### 自定义数据集 @@ -299,10 +348,10 @@ paddle2onnx --model_dir output_inference/${job_name} --model_filename model.pdmo ```base # 单卡fintune训练： -# CUDA_VISIBLE_DEVICES=0 python3.7 tools/train.py -c ${config} --eval --amp -o pretrain_weights=https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_300e_coco.pdparams +# CUDA_VISIBLE_DEVICES=0 python tools/train.py -c ${config} --eval --amp -o pretrain_weights=https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_300e_coco.pdparams # 多卡fintune训练： -python3.7 -m paddle.distributed.launch --log_dir=./log_dir --gpus 0,1,2,3,4,5,6,7 tools/train.py -c ${config} --eval --amp -o pretrain_weights=https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_300e_coco.pdparams +python -m paddle.distributed.launch --log_dir=./log_dir --gpus 0,1,2,3,4,5,6,7 tools/train.py -c ${config} --eval --amp -o pretrain_weights=https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_300e_coco.pdparams ``` **注意:** diff --git a/docs/feature_models/YOLOSERIES_MODEL_en.md b/docs/feature_models/PaddleYOLO_MODEL_en.md similarity index 66% rename from docs/feature_models/YOLOSERIES_MODEL_en.md rename to docs/feature_models/PaddleYOLO_MODEL_en.md index bba334f47b02c1fe60bc971ef484c3c7391e16dc..46d3483589bf52b5874fd2c31f1adfd5d69af4b5 100644 --- a/docs/feature_models/YOLOSERIES_MODEL_en.md +++ b/docs/feature_models/PaddleYOLO_MODEL_en.md @@ -1,25 +1,28 @@ -[简体中文](YOLOSERIES_MODEL.md) | English +[简体中文](MODEL_ZOO_cn.md) | English # [**PaddleYOLO**](https://github.com/PaddlePaddle/PaddleYOLO) ## Introduction - [Introduction](#Introduction) - [ModelZoo](#ModelZoo) - - [PP-YOLOE](#PP-YOLOE) + - [PP-YOLOE+](#PP-YOLOE+) - [YOLOX](#YOLOX) - [YOLOv5](#YOLOv5) - [YOLOv6](#YOLOv6) - [YOLOv7](#YOLOv7) + - [RTMDet](#RTMDet) + - [VOC](#VOC) - [UserGuide](#UserGuide) - [Pipeline](#Pipeline) - [CustomDataset](#CustomDataset) ## Introduction -**PaddleYOLO** is a YOLO Series toolbox based on [PaddleDetection](https://github.com/PaddlePaddle/PaddleDetection), **only relevant codes of YOLO series models are included**. It supports `YOLOv3`,`PP-YOLO`,`PP-YOLOv2`,`PP-YOLOE`,`PP-YOLOE+`,`YOLOX`,`YOLOv5`,`YOLOv6`,`YOLOv7` and so on. Welcome to use and build it together! +**PaddleYOLO** is a YOLO Series toolbox based on [PaddleDetection](https://github.com/PaddlePaddle/PaddleDetection), **only relevant codes of YOLO series models are included**. It supports `YOLOv3`,`PP-YOLO`,`PP-YOLOv2`,`PP-YOLOE`,`PP-YOLOE+`,`YOLOX`,`YOLOv5`,`YOLOv6`,`YOLOv7`,`RTMDet` and so on. Welcome to use and build it together! ## Updates +* 【2022/09/29】Support [RTMDet](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/rtmdet) inference and deploy; * 【2022/09/26】Release [`PaddleYOLO`](https://github.com/PaddlePaddle/PaddleYOLO); * 【2022/09/19】Support the new version of [`YOLOv6`](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov6), including n/t/s/m/l model; * 【2022/08/23】Release `YOLOSeries` codebase: support `YOLOv3`,`PP-YOLOE`,`PP-YOLOE+`,`YOLOX`,`YOLOv5`,`YOLOv6` and `YOLOv7`; support using `ConvNeXt` backbone to get high-precision version of `PP-YOLOE`,`YOLOX` and `YOLOv5`; support PaddleSlim accelerated quantitative training `PP-YOLOE`,`YOLOv5`,`YOLOv6` and `YOLOv7`. For details, please read this [article](https://mp.weixin.qq.com/s/Hki01Zs2lQgvLSLWS0btrA)； @@ -27,39 +30,28 @@ **Notes：** - The Licence of **PaddleYOLO** is **GPL 3.0**, the codes of [YOLOv5](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov5),[YOLOv7](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov7) and [YOLOv6](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov6) will not be merged into [PaddleDetection](https://github.com/PaddlePaddle/PaddleDetection). Except for these three YOLO models, other YOLO models are recommended to use in [PaddleDetection](https://github.com/PaddlePaddle/PaddleDetection), **which will be the first to release the latest progress of PP-YOLO series detection model**; - - To use **PaddleYOLO**, **PaddlePaddle-2.3.2 or above is recommended**，please refer to the [official website](https://www.paddlepaddle.org.cn/install/quick?docurl=/documentation/docs/zh/install/pip/linux-pip.html) to download the appropriate version. **For Windows platforms, please install the paddle develop version **; - - -## Exchanges - -- If you have any question or suggestion, please give us your valuable input via [GitHub Issues](https://github.com/PaddlePaddle/PaddleDetection/issues) - - Welcome to join PaddleDetection user groups on WeChat (scan the QR code, add and reply "D" to the assistant) - -
- -
- + - To use **PaddleYOLO**, **PaddlePaddle-2.3.2 or above is recommended**，please refer to the [official website](https://www.paddlepaddle.org.cn/install/quick?docurl=/documentation/docs/zh/install/pip/linux-pip.html) to download the appropriate version. **For Windows platforms, please install the paddle develop version**; + - Training **Custom dataset** please refer to [doc](#CustomDataset) and [issue](https://github.com/PaddlePaddle/PaddleYOLO/issues/43). Please **ensure COCO trained weights are loaded as pre-train** at first. We recommend to use YOLO detection model **with a total `batch_size` at least greater than `64` to train**. If the resources are insufficient, please **use the smaller model** or **reduce the input size of the model**. To ensure high detection accuracy, **you'd better never try to using single GPU or total `batch_size` less than `32` for training**; ## ModelZoo -### [PP-YOLOE, PP-YOLOE+](../../configs/ppyoloe) +### [PP-YOLOE+](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/ppyoloe)
Baseline | Model | Input Size | images/GPU | Epoch | TRT-FP16-Latency(ms) | mAPval
0.5:0.95 | mAPval
0.5 | Params(M) | FLOPs(G) | download | config | | :------------- | :------- | :-------: | :------: | :------------: | :---------------------: | :----------------: |:---------: | :------: |:---------------: |:-----: | -| PP-YOLOE-s | 640 | 32 | 400e | 2.9 | 43.4 | 60.0 | 7.93 | 17.36 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_s_400e_coco.pdparams) | [config](../../configs/ppyoloe/ppyoloe_crn_s_400e_coco.yml) | -| PP-YOLOE-s | 640 | 32 | 300e | 2.9 | 43.0 | 59.6 | 7.93 | 17.36 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_s_300e_coco.pdparams) | [config](../../configs/ppyoloe/ppyoloe_crn_s_300e_coco.yml) | -| PP-YOLOE-m | 640 | 28 | 300e | 6.0 | 49.0 | 65.9 | 23.43 | 49.91 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_m_300e_coco.pdparams) | [config](../../configs/ppyoloe/ppyoloe_crn_m_300e_coco.yml) | -| PP-YOLOE-l | 640 | 20 | 300e | 8.7 | 51.4 | 68.6 | 52.20 | 110.07 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_300e_coco.pdparams) | [config](../../configs/ppyoloe/ppyoloe_crn_l_300e_coco.yml) | -| PP-YOLOE-x | 640 | 16 | 300e | 14.9 | 52.3 | 69.5 | 98.42 | 206.59 |[model](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_x_300e_coco.pdparams) | [config](../../configs/ppyoloe/ppyoloe_crn_x_300e_coco.yml) | -| PP-YOLOE-tiny ConvNeXt| 640 | 16 | 36e | - | 44.6 | 63.3 | 33.04 | 13.87 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_convnext_tiny_36e_coco.pdparams) | [config](../../configs/convnext/ppyoloe_convnext_tiny_36e_coco.yml) | -| **PP-YOLOE+_s** | 640 | 8 | 80e | 2.9 | **43.7** | **60.6** | 7.93 | 17.36 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_plus_crn_s_80e_coco.pdparams) | [config](../../configs/ppyoloe/ppyoloe_plus_crn_s_80e_coco.yml) | -| **PP-YOLOE+_m** | 640 | 8 | 80e | 6.0 | **49.8** | **67.1** | 23.43 | 49.91 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_plus_crn_m_80e_coco.pdparams) | [config](../../configs/ppyoloe/ppyoloe_plus_crn_m_80e_coco.yml) | -| **PP-YOLOE+_l** | 640 | 8 | 80e | 8.7 | **52.9** | **70.1** | 52.20 | 110.07 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_plus_crn_l_80e_coco.pdparams) | [config](../../configs/ppyoloe/ppyoloe_plus_crn_l_80e_coco.yml) | -| **PP-YOLOE+_x** | 640 | 8 | 80e | 14.9 | **54.7** | **72.0** | 98.42 | 206.59 |[model](https://paddledet.bj.bcebos.com/models/ppyoloe_plus_crn_x_80e_coco.pdparams) | [config](../../configs/ppyoloe/ppyoloe_plus_crn_x_80e_coco.yml) | +| PP-YOLOE-s | 640 | 32 | 400e | 2.9 | 43.4 | 60.0 | 7.93 | 17.36 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_s_400e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/ppyoloe/ppyoloe_crn_s_400e_coco.yml) | +| PP-YOLOE-s | 640 | 32 | 300e | 2.9 | 43.0 | 59.6 | 7.93 | 17.36 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_s_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/ppyoloe/ppyoloe_crn_s_300e_coco.yml) | +| PP-YOLOE-m | 640 | 28 | 300e | 6.0 | 49.0 | 65.9 | 23.43 | 49.91 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_m_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/ppyoloe/ppyoloe_crn_m_300e_coco.yml) | +| PP-YOLOE-l | 640 | 20 | 300e | 8.7 | 51.4 | 68.6 | 52.20 | 110.07 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/ppyoloe/ppyoloe_crn_l_300e_coco.yml) | +| PP-YOLOE-x | 640 | 16 | 300e | 14.9 | 52.3 | 69.5 | 98.42 | 206.59 |[model](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_x_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/ppyoloe/ppyoloe_crn_x_300e_coco.yml) | +| PP-YOLOE-tiny ConvNeXt| 640 | 16 | 36e | - | 44.6 | 63.3 | 33.04 | 13.87 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_convnext_tiny_36e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/convnext/ppyoloe_convnext_tiny_36e_coco.yml) | +| **PP-YOLOE+_s** | 640 | 8 | 80e | 2.9 | **43.7** | **60.6** | 7.93 | 17.36 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_plus_crn_s_80e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/ppyoloe/ppyoloe_plus_crn_s_80e_coco.yml) | +| **PP-YOLOE+_m** | 640 | 8 | 80e | 6.0 | **49.8** | **67.1** | 23.43 | 49.91 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_plus_crn_m_80e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/ppyoloe/ppyoloe_plus_crn_m_80e_coco.yml) | +| **PP-YOLOE+_l** | 640 | 8 | 80e | 8.7 | **52.9** | **70.1** | 52.20 | 110.07 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_plus_crn_l_80e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/ppyoloe/ppyoloe_plus_crn_l_80e_coco.yml) | +| **PP-YOLOE+_x** | 640 | 8 | 80e | 14.9 | **54.7** | **72.0** | 98.42 | 206.59 |[model](https://paddledet.bj.bcebos.com/models/ppyoloe_plus_crn_x_80e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/ppyoloe/ppyoloe_plus_crn_x_80e_coco.yml) |
@@ -80,22 +72,22 @@
-### [YOLOX](../../configs/yolox) +### [YOLOX](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolox)
Baseline | Model | Input Size | images/GPU | Epoch | TRT-FP16-Latency(ms) | mAPval
0.5:0.95 | mAPval
0.5 | Params(M) | FLOPs(G) | download | config | | :------------- | :------- | :-------: | :------: | :------------: | :---------------------: | :----------------: |:---------: | :------: |:---------------: |:-----: | -| YOLOX-nano | 416 | 8 | 300e | 2.3 | 26.1 | 42.0 | 0.91 | 1.08 | [model](https://paddledet.bj.bcebos.com/models/yolox_nano_300e_coco.pdparams) | [config](../../configs/yolox/yolox_nano_300e_coco.yml) | -| YOLOX-tiny | 416 | 8 | 300e | 2.8 | 32.9 | 50.4 | 5.06 | 6.45 | [model](https://paddledet.bj.bcebos.com/models/yolox_tiny_300e_coco.pdparams) | [config](../../configs/yolox/yolox_tiny_300e_coco.yml) | -| YOLOX-s | 640 | 8 | 300e | 3.0 | 40.4 | 59.6 | 9.0 | 26.8 | [model](https://paddledet.bj.bcebos.com/models/yolox_s_300e_coco.pdparams) | [config](../../configs/yolox/yolox_s_300e_coco.yml) | -| YOLOX-m | 640 | 8 | 300e | 5.8 | 46.9 | 65.7 | 25.3 | 73.8 | [model](https://paddledet.bj.bcebos.com/models/yolox_m_300e_coco.pdparams) | [config](../../configs/yolox/yolox_m_300e_coco.yml) | -| YOLOX-l | 640 | 8 | 300e | 9.3 | 50.1 | 68.8 | 54.2 | 155.6 | [model](https://paddledet.bj.bcebos.com/models/yolox_l_300e_coco.pdparams) | [config](../../configs/yolox/yolox_l_300e_coco.yml) | -| YOLOX-x | 640 | 8 | 300e | 16.6 | **51.8** | **70.6** | 99.1 | 281.9 | [model](https://paddledet.bj.bcebos.com/models/yolox_x_300e_coco.pdparams) | [config](../../configs/yolox/yolox_x_300e_coco.yml) | +| YOLOX-nano | 416 | 8 | 300e | 2.3 | 26.1 | 42.0 | 0.91 | 1.08 | [model](https://paddledet.bj.bcebos.com/models/yolox_nano_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolox/yolox_nano_300e_coco.yml) | +| YOLOX-tiny | 416 | 8 | 300e | 2.8 | 32.9 | 50.4 | 5.06 | 6.45 | [model](https://paddledet.bj.bcebos.com/models/yolox_tiny_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolox/yolox_tiny_300e_coco.yml) | +| YOLOX-s | 640 | 8 | 300e | 3.0 | 40.4 | 59.6 | 9.0 | 26.8 | [model](https://paddledet.bj.bcebos.com/models/yolox_s_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolox/yolox_s_300e_coco.yml) | +| YOLOX-m | 640 | 8 | 300e | 5.8 | 46.9 | 65.7 | 25.3 | 73.8 | [model](https://paddledet.bj.bcebos.com/models/yolox_m_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolox/yolox_m_300e_coco.yml) | +| YOLOX-l | 640 | 8 | 300e | 9.3 | 50.1 | 68.8 | 54.2 | 155.6 | [model](https://paddledet.bj.bcebos.com/models/yolox_l_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolox/yolox_l_300e_coco.yml) | +| YOLOX-x | 640 | 8 | 300e | 16.6 | **51.8** | **70.6** | 99.1 | 281.9 | [model](https://paddledet.bj.bcebos.com/models/yolox_x_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolox/yolox_x_300e_coco.yml) | YOLOX-cdn-tiny | 416 | 8 | 300e | 1.9 | 32.4 | 50.2 | 5.03 | 6.33 | [model](https://paddledet.bj.bcebos.com/models/yolox_cdn_tiny_300e_coco.pdparams) | [config](c../../onfigs/yolox/yolox_cdn_tiny_300e_coco.yml) | -| YOLOX-crn-s | 640 | 8 | 300e | 3.0 | 40.4 | 59.6 | 7.7 | 24.69 | [model](https://paddledet.bj.bcebos.com/models/yolox_crn_s_300e_coco.pdparams) | [config](../../configs/yolox/yolox_crn_s_300e_coco.yml) | -| YOLOX-s ConvNeXt| 640 | 8 | 36e | - | 44.6 | 65.3 | 36.2 | 27.52 | [model](https://paddledet.bj.bcebos.com/models/yolox_convnext_s_36e_coco.pdparams) | [config](../../configs/convnext/yolox_convnext_s_36e_coco.yml) | +| YOLOX-crn-s | 640 | 8 | 300e | 3.0 | 40.4 | 59.6 | 7.7 | 24.69 | [model](https://paddledet.bj.bcebos.com/models/yolox_crn_s_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolox/yolox_crn_s_300e_coco.yml) | +| YOLOX-s ConvNeXt| 640 | 8 | 36e | - | 44.6 | 65.3 | 36.2 | 27.52 | [model](https://paddledet.bj.bcebos.com/models/yolox_convnext_s_36e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/convnext/yolox_convnext_s_36e_coco.yml) |
@@ -122,11 +114,16 @@ | Model | Input Size | images/GPU | Epoch | TRT-FP16-Latency(ms) | mAPval
0.5:0.95 | mAPval
0.5 | Params(M) | FLOPs(G) | download | config | | :------------- | :------- | :-------: | :------: | :------------: | :---------------------: | :----------------: |:---------: | :------: |:---------------: |:-----: | | YOLOv5-n | 640 | 16 | 300e | 2.6 | 28.0 | 45.7 | 1.87 | 4.52 | [model](https://paddledet.bj.bcebos.com/models/yolov5_n_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov5/yolov5_n_300e_coco.yml) | -| YOLOv5-s | 640 | 8 | 300e | 3.2 | 37.0 | 55.9 | 7.24 | 16.54 | [model](https://paddledet.bj.bcebos.com/models/yolov5_s_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov5/yolov5_s_300e_coco.yml) | -| YOLOv5-m | 640 | 5 | 300e | 5.2 | 45.3 | 63.8 | 21.19 | 49.08 | [model](https://paddledet.bj.bcebos.com/models/yolov5_m_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov5/yolov5_m_300e_coco.yml) | -| YOLOv5-l | 640 | 3 | 300e | 7.9 | 48.6 | 66.9 | 46.56 | 109.32 | [model](https://paddledet.bj.bcebos.com/models/yolov5_l_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov5/yolov5_l_300e_coco.yml) | -| YOLOv5-x | 640 | 2 | 300e | 13.7 | **50.6** | **68.7** | 86.75 | 205.92 | [model](https://paddledet.bj.bcebos.com/models/yolov5_x_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov5/yolov5_x_300e_coco.yml) | +| YOLOv5-s | 640 | 16 | 300e | 3.2 | 37.6 | 56.7 | 7.24 | 16.54 | [model](https://paddledet.bj.bcebos.com/models/yolov5_s_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov5/yolov5_s_300e_coco.yml) | +| YOLOv5-m | 640 | 16 | 300e | 5.2 | 45.4 | 64.1 | 21.19 | 49.08 | [model](https://paddledet.bj.bcebos.com/models/yolov5_m_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov5/yolov5_m_300e_coco.yml) | +| YOLOv5-l | 640 | 16 | 300e | 7.9 | 48.9 | 67.1 | 46.56 | 109.32 | [model](https://paddledet.bj.bcebos.com/models/yolov5_l_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov5/yolov5_l_300e_coco.yml) | +| YOLOv5-x | 640 | 16 | 300e | 13.7 | 50.6 | 68.7 | 86.75 | 205.92 | [model](https://paddledet.bj.bcebos.com/models/yolov5_x_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov5/yolov5_x_300e_coco.yml) | | YOLOv5-s ConvNeXt| 640 | 8 | 36e | - | 42.4 | 65.3 | 34.54 | 17.96 | [model](https://paddledet.bj.bcebos.com/models/yolov5_convnext_s_36e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov5/yolov5_convnext_s_36e_coco.yml) | +| *YOLOv5p6-n | 1280 | 16 | 300e | - | 35.9 | 54.2 | 3.25 | 9.23 | [model](https://paddledet.bj.bcebos.com/models/yolov5p6_n_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov5/yolov5p6_n_300e_coco.yml) | +| *YOLOv5p6-s | 1280 | 16 | 300e | - | 44.5 | 63.3 | 12.63 | 33.81 | [model](https://paddledet.bj.bcebos.com/models/yolov5p6_s_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov5/yolov5p6_s_300e_coco.yml) | +| *YOLOv5p6-m | 1280 | 16 | 300e | - | 51.1 | 69.0 | 35.73 | 100.21 | [model](https://paddledet.bj.bcebos.com/models/yolov5p6_m_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov5/yolov5p6_m_300e_coco.yml) | +| *YOLOv5p6-l | 1280 | 8 | 300e | - | 53.4 | 71.0 | 76.77 | 223.09 | [model](https://paddledet.bj.bcebos.com/models/yolov5p6_l_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov5/yolov5p6_l_300e_coco.yml) | +| *YOLOv5p6-x | 1280 | 8 | 300e | - | 54.7 | 72.4 | 140.80 | 420.03 | [model](https://paddledet.bj.bcebos.com/models/yolov5p6_x_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov5/yolov5p6_x_300e_coco.yml) | @@ -150,8 +147,8 @@ | Model | Input Size | images/GPU | Epoch | TRT-FP16-Latency(ms) | mAPval
0.5:0.95 | mAPval
0.5 | Params(M) | FLOPs(G) | download | config | | :------------- | :------- | :-------: | :------: | :---------: | :-----: |:-----: | :-----: |:-----: | :-------------: | :-----: | -| *YOLOv6-n | 416 | 32 | 400e | 1.0 | 31.1 | 45.3 | 4.74 | 5.16 |[model](https://paddledet.bj.bcebos.com/models/yolov6_n_416_400e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov6/yolov6_n_416_400e_coco.yml) | -| *YOLOv6-n | 640 | 32 | 400e | 1.3 | 36.1 | 51.9 | 4.74 | 12.21 |[model](https://paddledet.bj.bcebos.com/models/yolov6_n_400e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov6/yolov6_n_400e_coco.yml) | +| YOLOv6-n | 416 | 32 | 400e | 1.0 | 31.1 | 45.3 | 4.74 | 5.16 |[model](https://paddledet.bj.bcebos.com/models/yolov6_n_416_400e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov6/yolov6_n_416_400e_coco.yml) | +| YOLOv6-n | 640 | 32 | 400e | 1.3 | 36.1 | 51.9 | 4.74 | 12.21 |[model](https://paddledet.bj.bcebos.com/models/yolov6_n_400e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov6/yolov6_n_400e_coco.yml) | | *YOLOv6-t | 640 | 32 | 400e | 2.1 | 40.7 | 57.4 | 10.63 | 27.29 |[model](https://paddledet.bj.bcebos.com/models/yolov6_t_400e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov6/yolov6_t_400e_coco.yml) | | *YOLOv6-s | 640 | 32 | 400e | 2.6 | 43.4 | 60.5 | 18.87 | 48.35 |[model](https://paddledet.bj.bcebos.com/models/yolov6_s_400e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov6/yolov6_s_400e_coco.yml) | | *YOLOv6-m | 640 | 32 | 300e | 5.0 | 49.0 | 66.5 | 37.17 | 88.82 |[model](https://paddledet.bj.bcebos.com/models/yolov6_m_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov6/yolov6_m_300e_coco.yml) | @@ -211,12 +208,65 @@ + +### [RTMDet](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/rtmdet) + +
+ Baseline + +| Model | Input Size | images/GPU | Epoch | TRT-FP16-Latency(ms) | mAPval
0.5:0.95 | mAPval
0.5 | Params(M) | FLOPs(G) | download | config | +| :------------- | :------- | :-------: | :------: | :------------: | :---------------------: | :----------------: |:---------: | :------: |:---------------: |:-----: | +| *RTMDet-t | 640 | 32 | 300e | 2.8 | 40.9 | 57.9 | 4.90 | 16.21 |[model](https://paddledet.bj.bcebos.com/models/rtmdet_t_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/rtmdet/rtmdet_t_300e_coco.yml) | +| *RTMDet-s | 640 | 32 | 300e | 3.3 | 44.5 | 62.0 | 8.89 | 29.71 |[model](https://paddledet.bj.bcebos.com/models/rtmdet_s_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/rtmdet/rtmdet_s_300e_coco.yml) | +| *RTMDet-m | 640 | 32 | 300e | 6.4 | 49.1 | 66.8 | 24.71 | 78.47 |[model](https://paddledet.bj.bcebos.com/models/rtmdet_m_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/rtmdet/rtmdet_m_300e_coco.yml) | +| *RTMDet-l | 640 | 32 | 300e | 10.2 | 51.2 | 68.8 | 52.31 | 160.32 |[model](https://paddledet.bj.bcebos.com/models/rtmdet_l_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/rtmdet/rtmdet_l_300e_coco.yml) | +| *RTMDet-x | 640 | 32 | 300e | 18.0 | 52.6 | 70.4 | 94.86 | 283.12 |[model](https://paddledet.bj.bcebos.com/models/rtmdet_x_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/rtmdet/rtmdet_x_300e_coco.yml) | + +
+ +
+ Deploy Models + +| Model | Input Size | Exported weights(w/o NMS) | ONNX(w/o NMS) | +| :-------- | :--------: | :---------------------: | :----------------: | +| RTMDet-t | 640 | [( w/ nms)](https://paddledet.bj.bcebos.com/deploy/yoloseries/rtmdet/rtmdet_t_300e_coco_w_nms.zip) | [( w/o nms)](https://paddledet.bj.bcebos.com/deploy/yoloseries/rtmdet/rtmdet_t_300e_coco_wo_nms.zip) | [( w/ nms)](https://paddledet.bj.bcebos.com/deploy/yoloseries/rtmdet/rtmdet_t_300e_coco_w_nms.onnx) | [( w/o nms)](https://paddledet.bj.bcebos.com/deploy/yoloseries/rtmdet/rtmdet_t_300e_coco_wo_nms.onnx) | +| RTMDet-s | 640 | [( w/ nms)](https://paddledet.bj.bcebos.com/deploy/yoloseries/rtmdet/rtmdet_s_300e_coco_w_nms.zip) | [( w/o nms)](https://paddledet.bj.bcebos.com/deploy/yoloseries/rtmdet/rtmdet_s_300e_coco_wo_nms.zip) | [( w/ nms)](https://paddledet.bj.bcebos.com/deploy/yoloseries/rtmdet/rtmdet_s_300e_coco_w_nms.onnx) | [( w/o nms)](https://paddledet.bj.bcebos.com/deploy/yoloseries/rtmdet/rtmdet_s_300e_coco_wo_nms.onnx) | +| RTMDet-m | 640 | [( w/ nms)](https://paddledet.bj.bcebos.com/deploy/yoloseries/rtmdet/rtmdet_m_300e_coco_w_nms.zip) | [( w/o nms)](https://paddledet.bj.bcebos.com/deploy/yoloseries/rtmdet/rtmdet_m_300e_coco_wo_nms.zip) | [( w/ nms)](https://paddledet.bj.bcebos.com/deploy/yoloseries/rtmdet/rtmdet_m_300e_coco_w_nms.onnx) | [( w/o nms)](https://paddledet.bj.bcebos.com/deploy/yoloseries/rtmdet/rtmdet_m_300e_coco_wo_nms.onnx) | +| RTMDet-l | 640 | [( w/ nms)](https://paddledet.bj.bcebos.com/deploy/yoloseries/rtmdet/rtmdet_l_300e_coco_w_nms.zip) | [( w/o nms)](https://paddledet.bj.bcebos.com/deploy/yoloseries/rtmdet/rtmdet_l_300e_coco_wo_nms.zip) | [( w/ nms)](https://paddledet.bj.bcebos.com/deploy/yoloseries/rtmdet/rtmdet_l_300e_coco_w_nms.onnx) | [( w/o nms)](https://paddledet.bj.bcebos.com/deploy/yoloseries/rtmdet/rtmdet_l_300e_coco_wo_nms.onnx) | +| RTMDet-x | 640 | [( w/ nms)](https://paddledet.bj.bcebos.com/deploy/yoloseries/rtmdet/rtmdet_x_300e_coco_w_nms.zip) | [( w/o nms)](https://paddledet.bj.bcebos.com/deploy/yoloseries/rtmdet/rtmdet_x_300e_coco_wo_nms.zip) | [( w/ nms)](https://paddledet.bj.bcebos.com/deploy/yoloseries/rtmdet/rtmdet_x_300e_coco_w_nms.onnx) | [( w/o nms)](https://paddledet.bj.bcebos.com/deploy/yoloseries/rtmdet/rtmdet_x_300e_coco_wo_nms.onnx) | + +
+ + ### **Notes：** - All the models are trained on COCO train2017 dataset and evaluated on val2017 dataset. The * in front of the model indicates that the training is being updated. - - Please check the specific accuracy and speed details in [PP-YOLOE](../../configs/ppyoloe),[YOLOX](../../configs/yolox),[YOLOv5](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov5),[YOLOv6](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov6),[YOLOv7](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov7). **Note that YOLOv5, YOLOv6 and YOLOv7 have not adopted `multi_label` to eval**。 -- TRT-FP16-Latency(ms) is the time spent in testing under TensorRT-FP16, excluding data preprocessing and model output post-processing (NMS). The test adopts single card V100, batch size=1, and the test environment is **paddlepaddle-2.3.0**, **CUDA 11.2**, **CUDNN 8.2**, **GCC-8.2**, **TensorRT 8.0.3.4**. Please refer to the respective model homepage for details. -- For **FLOPs(G)**, you should first install [PaddleSlim](https://github.com/PaddlePaddle/PaddleSlim), `pip install paddleslim`, then set `print_flops: True` in [runtime.yml](../../configs/runtime.yml). Make sure **single scale** like 640x640, **MACs are printed，FLOPs=2*MACs**。 - - Based on [PaddleSlim](https://github.com/PaddlePaddle/PaddleSlim), quantitative training of YOLO series models can achieve basically lossless accuracy and generally improve the speed by more than 30%. For details, please refer to [auto_compression](https://github.com/PaddlePaddle/PaddleSlim/tree/develop/example/auto_compression)。 + - Please check the specific accuracy and speed details in [PP-YOLOE](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/ppyoloe),[YOLOX](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolox),[YOLOv5](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov5),[YOLOv6](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov6),[YOLOv7](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov7). **Note that YOLOv5, YOLOv6 and YOLOv7 have not adopted `multi_label` to eval**. +- TRT-FP16-Latency(ms) is the time spent in testing under TensorRT-FP16, **excluding data preprocessing and model output post-processing (NMS)**. The test adopts single card **Tesla T4 GPU, batch size=1**, and the test environment is **paddlepaddle-2.3.2**, **CUDA 11.2**, **CUDNN 8.2**, **GCC-8.2**, **TensorRT 8.0.3.4**. Please refer to the respective model homepage for details. +- For **FLOPs(G) and Params(M)**, you should first install [PaddleSlim](https://github.com/PaddlePaddle/PaddleSlim), `pip install paddleslim`, then set `print_flops: True` and `print_params: True` in [runtime.yml](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/runtime.yml). Make sure **single scale** like 640x640, **MACs are printed，FLOPs=2*MACs**. + - Based on [PaddleSlim](https://github.com/PaddlePaddle/PaddleSlim), quantitative training of YOLO series models can achieve basically lossless accuracy and generally improve the speed by more than 30%. For details, please refer to [auto_compression](https://github.com/PaddlePaddle/PaddleSlim/tree/develop/example/auto_compression). + + +### [VOC](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/voc) + +
+ Baseline + +| Model | Input Size | images/GPU | Epoch | TRT-FP16-Latency(ms) | mAP(0.50,11point) | Params(M) | FLOPs(G) | download | config | +| :-----------: | :-------: | :-------: | :------: | :------------: | :---------------: | :------------------: |:-----------------: | :------: | :------: | +| YOLOv5-s | 640 | 16 | 60e | 3.2 | 80.3 | 7.24 | 16.54 | [model](https://paddledet.bj.bcebos.com/models/yolov5_s_60e_voc.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/voc/yolov5_s_60e_voc.yml) | +| YOLOv6-s | 640 | 32 | 40e | 2.7 | 84.7 | 18.87 | 48.35 | [model](https://paddledet.bj.bcebos.com/models/yolov6_s_40e_voc.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/voc/yolov6_s_40e_voc.yml) | +| YOLOv7-tiny | 640 | 32 | 60e | 2.6 | 80.2 | 6.23 | 6.90 | [model](https://paddledet.bj.bcebos.com/models/yolov7_tiny_60e_voc.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/voc/yolov7_tiny_60e_voc.yml) | +| YOLOX-s | 640 | 8 | 40e | 3.0 | 82.9 | 9.0 | 26.8 | [model](https://paddledet.bj.bcebos.com/models/yolox_s_40e_voc.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/voc/yolox_s_40e_voc.yml) | +| PP-YOLOE+_s | 640 | 8 | 30e | 2.9 | 86.7 | 7.93 | 17.36 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_plus_crn_s_30e_voc.pdparams) | [config](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/voc/ppyoloe_plus_crn_s_30e_voc.yml) | + +
+ +**Note:** + - The VOC mAP is `mAP(IoU=0.5)`, and all the models **have not adopted `multi_label` to eval**. + - All YOLO VOC models are loaded with the COCO weights of their respective models as pre-train weights. Each config file uses 8 GPUs by default, which can be used as a reference for setting custom datasets. The specific mAP will vary depending on the datasets; + - We recommend to use YOLO detection model **with a total `batch_size` at least greater than `64` to train**. If the resources are insufficient, please **use the smaller model** or **reduce the input size of the model**. To ensure high detection accuracy, **you'd better not try to using single GPU or total `batch_size` less than `64` for training**; + - Params (M) and FLOPs (G) are measured during training. YOLOv7 has no s model, so tiny model is selected; + - For TRT-FP16 Latency (ms) speed measurement, please refer to the config homepage of each YOLO model; ## UserGuide @@ -226,50 +276,53 @@ The download link provided by PaddleDetection team is: [coco](https://bj.bcebos. ### **Pipeline** -``` -model_type=ppyoloe # can modify to 'yolov7' -job_name=ppyoloe_crn_l_300e_coco # can modify to 'yolov7_l_300e_coco' -config=configs/${model_type}/${job_name}.yml +Write the following commands in a script file, such as ```run.sh```, and run as：```sh run.sh```. You can also run the command line sentence by sentence. + +```bash +model_name=ppyoloe # yolov7 +job_name=ppyoloe_plus_crn_l_80e_coco # yolov7_tiny_300e_coco + +config=configs/${model_name}/${job_name}.yml log_dir=log_dir/${job_name} # weights=https://bj.bcebos.com/v1/paddledet/models/${job_name}.pdparams weights=output/${job_name}/model_final.pdparams # 1.training（single GPU / multi GPU） -# CUDA_VISIBLE_DEVICES=0 python3.7 tools/train.py -c ${config} --eval --amp -python3.7 -m paddle.distributed.launch --log_dir=${log_dir} --gpus 0,1,2,3,4,5,6,7 tools/train.py -c ${config} --eval --amp +# CUDA_VISIBLE_DEVICES=0 python tools/train.py -c ${config} --eval --amp +python -m paddle.distributed.launch --log_dir=${log_dir} --gpus 0,1,2,3,4,5,6,7 tools/train.py -c ${config} --eval --amp # 2.eval -CUDA_VISIBLE_DEVICES=0 python3.7 tools/eval.py -c ${config} -o weights=${weights} --classwise +CUDA_VISIBLE_DEVICES=0 python tools/eval.py -c ${config} -o weights=${weights} --classwise # 3.infer -CUDA_VISIBLE_DEVICES=0 python3.7 tools/infer.py -c ${config} -o weights=${weights} --infer_img=demo/000000014439_640x640.jpg --draw_threshold=0.5 +CUDA_VISIBLE_DEVICES=0 python tools/infer.py -c ${config} -o weights=${weights} --infer_img=demo/000000014439_640x640.jpg --draw_threshold=0.5 # 4.export -CUDA_VISIBLE_DEVICES=0 python3.7 tools/export_model.py -c ${config} -o weights=${weights} # exclude_nms=True trt=True +CUDA_VISIBLE_DEVICES=0 python tools/export_model.py -c ${config} -o weights=${weights} # exclude_nms=True trt=True # 5.deploy infer -CUDA_VISIBLE_DEVICES=0 python3.7 deploy/python/infer.py --model_dir=output_inference/${job_name} --image_file=demo/000000014439_640x640.jpg --device=GPU +CUDA_VISIBLE_DEVICES=0 python deploy/python/infer.py --model_dir=output_inference/${job_name} --image_file=demo/000000014439_640x640.jpg --device=GPU -# 6.deploy speed -CUDA_VISIBLE_DEVICES=0 python3.7 deploy/python/infer.py --model_dir=output_inference/${job_name} --image_file=demo/000000014439_640x640.jpg --device=GPU --run_benchmark=True # --run_mode=trt_fp16 +# 6.deploy speed, add '--run_mode=trt_fp16' to test in TensorRT FP16 mode +CUDA_VISIBLE_DEVICES=0 python deploy/python/infer.py --model_dir=output_inference/${job_name} --image_file=demo/000000014439_640x640.jpg --device=GPU --run_benchmark=True # --run_mode=trt_fp16 # 7.export onnx paddle2onnx --model_dir output_inference/${job_name} --model_filename model.pdmodel --params_filename model.pdiparams --opset_version 12 --save_file ${job_name}.onnx # 8.onnx speed /usr/local/TensorRT-8.0.3.4/bin/trtexec --onnx=${job_name}.onnx --workspace=4096 --avgRuns=10 --shapes=input:1x3x640x640 --fp16 - ``` **Note：** -- Write the above commands in a script file, such as ```run.sh```, and run as：```sh run.sh```,You can also run the command line sentence by sentence. - If you want to switch models, just modify the first two lines, such as: ``` - model_type=yolov7 - job_name=yolov7_l_300e_coco + model_name=yolov7 + job_name=yolov7_tiny_300e_coco ``` -- For **FLOPs(G)**, you should first install [PaddleSlim](https://github.com/PaddlePaddle/PaddleSlim), `pip install paddleslim`, then set `print_flops: True` in [runtime.yml](../../configs/runtime.yml). Make sure **single scale** like 640x640, **MACs are printed，FLOPs=2*MACs**。 +- For **exporting onnx**, you should install [Paddle2ONNX](https://github.com/PaddlePaddle/Paddle2ONNX) by `pip install paddle2onnx` at first. +- For **FLOPs(G) and Params(M)**, you should install [PaddleSlim](https://github.com/PaddlePaddle/PaddleSlim) by `pip install paddleslim` at first, then set `print_flops: True` and `print_params: True` in [runtime.yml](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/runtime.yml). Make sure **single scale** like 640x640, **MACs are printed，FLOPs=2*MACs**. + ### CustomDataset @@ -277,7 +330,7 @@ paddle2onnx --model_dir output_inference/${job_name} --model_filename model.pdmo 1.For the annotation of custom dataset, please refer to[DetAnnoTools](../tutorials/data/DetAnnoTools.md); -2.For training preparation of custom dataset，please refer to[PrepareDataSet](../tutorials/PrepareDataSet.md)。 +2.For training preparation of custom dataset，please refer to[PrepareDataSet](../tutorials/PrepareDataSet.md). #### fintune： @@ -286,10 +339,10 @@ In addition to changing the path of the dataset, it is generally recommended to ```base # fintune with single GPU： -# CUDA_VISIBLE_DEVICES=0 python3.7 tools/train.py -c ${config} --eval --amp -o pretrain_weights=https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_300e_coco.pdparams +# CUDA_VISIBLE_DEVICES=0 python tools/train.py -c ${config} --eval --amp -o pretrain_weights=https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_300e_coco.pdparams # fintune with multi GPU： -python3.7 -m paddle.distributed.launch --log_dir=./log_dir --gpus 0,1,2,3,4,5,6,7 tools/train.py -c ${config} --eval --amp -o pretrain_weights=https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_300e_coco.pdparams +python -m paddle.distributed.launch --log_dir=./log_dir --gpus 0,1,2,3,4,5,6,7 tools/train.py -c ${config} --eval --amp -o pretrain_weights=https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_300e_coco.pdparams ``` **Note:**