diff --git a/README.md b/README.md index f637d485b5a7877f9ea47ad23abd49c21b4f1836..b6b98f9fe3184f592ba5895d924fcb80c83fadab 100644 --- a/README.md +++ b/README.md @@ -138,7 +138,7 @@ PaddleDetection新发布精度速度领先的[PP-YOLO](https://arxiv.org/abs/200 - [Anchor free模型](configs/anchor_free/README.md) - [人脸检测模型](docs/featured_model/FACE_DETECTION.md) - [YOLOv3增强模型](docs/featured_model/YOLOv3_ENHANCEMENT.md): COCO mAP高达43.6%，原论文精度为33.0% -- [PPYOLO模型](configs/ppyolo/README.md): COCO mAP高达45.3%，单卡Tesla V100预测速度高达72.9 FPS +- [PP-YOLO模型](configs/ppyolo/README.md): COCO mAP高达45.3%，单卡Tesla V100预测速度高达72.9 FPS - [行人检测预训练模型](docs/featured_model/CONTRIB_cn.md) - [车辆检测预训练模型](docs/featured_model/CONTRIB_cn.md) - [Objects365 2019 Challenge夺冠模型](docs/featured_model/champion_model/CACascadeRCNN.md) diff --git a/README_en.md b/README_en.md index 3236bc38e221c0b79e473e8e1e8a06633261da80..036f76e45299ca1e39ee48f30c1757b87813b439 100644 --- a/README_en.md +++ b/README_en.md @@ -14,7 +14,7 @@ and multi-platform deployment. [PP-YOLO](https://arxiv.org/abs/2007.12099), which is faster and has higer performance than YOLOv4, has been released, it reached mAP(0.5:0.95) as 45.2% on COCO test2019 dataset and 72.9 FPS on single -Test V100. Please refer to [PPYOLO](configs/ppyolo/README.md) for details. +Test V100. Please refer to [PP-YOLO](configs/ppyolo/README.md) for details. **Now all models in PaddleDetection require PaddlePaddle version 1.8 or higher, or suitable develop version.** @@ -110,7 +110,7 @@ The following is the relationship between COCO mAP and FPS on Tesla V100 of repr - The enhanced `YOLOv3-ResNet50vd-DCN` is 10.6 absolute percentage points higher than paper on COCO mAP, and inference speed is nearly 70% faster than the darknet framework - All these models can be get in [Model Zoo](#Model-Zoo) -The following is the relationship between COCO mAP and FPS on Tesla V100 of SOTA object detecters and PPYOLO, which is faster and has better performance than YOLOv4, and reached mAP(0.5:0.95) as 45.2% on COCO test2019 dataset and 72.9 FPS on single Test V100. Please refer to [PPYOLO](configs/ppyolo/README.md) for details. +The following is the relationship between COCO mAP and FPS on Tesla V100 of SOTA object detecters and PP-YOLO, which is faster and has better performance than YOLOv4, and reached mAP(0.5:0.95) as 45.2% on COCO test2019 dataset and 72.9 FPS on single Test V100. Please refer to [PP-YOLO](configs/ppyolo/README.md) for details.
@@ -157,7 +157,7 @@ The following is the relationship between COCO mAP and FPS on Tesla V100 of SOTA - [Pretrained models for pedestrian detection](docs/featured_model/CONTRIB.md) - [Pretrained models for vehicle detection](docs/featured_model/CONTRIB.md) - [YOLOv3 enhanced model](docs/featured_model/YOLOv3_ENHANCEMENT.md): Compared to MAP of 33.0% in paper, enhanced YOLOv3 reaches the MAP of 43.6%, and inference speed is improved as well -- [PPYOLO](configs/ppyolo/README.md): PPYOLO reeached mAP as 45.3% on COCO dataset，and 72.9 FPS on single Tesla V100 +- [PP-YOLO](configs/ppyolo/README.md): PP-YOLO reeached mAP as 45.3% on COCO dataset，and 72.9 FPS on single Tesla V100 - [Objects365 2019 Challenge champion model](docs/featured_model/champion_model/CACascadeRCNN.md) - [Best single model of Open Images 2019-Object Detction](docs/featured_model/champion_model/OIDV5_BASELINE_MODEL.md) - [Practical Server-side detection method](configs/rcnn_enhance/README_en.md): Inference speed on single V100 GPU can reach 20FPS when COCO mAP is 47.8%. diff --git a/configs/ppyolo/README.md b/configs/ppyolo/README.md index c2aa81d99fdc5c4d708600f016dec250f79250be..179fe725d75db2e6e8e593d7b4e1ea441adbe97f 100644 --- a/configs/ppyolo/README.md +++ b/configs/ppyolo/README.md @@ -11,7 +11,7 @@ [PP-YOLO](https://arxiv.org/abs/2007.12099)的PaddleDetection优化和改进的YOLOv3的模型，其精度(COCO数据集mAP)和推理速度均优于[YOLOv4](https://arxiv.org/abs/2004.10934)模型，要求使用PaddlePaddle 1.8.4(2020年8月中旬发布)或适当的[develop版本](https://www.paddlepaddle.org.cn/documentation/docs/zh/install/Tables.html#whl-dev)。 -PP-YOLO在[COCO](http://cocodataset.org) test-dev2019数据集上精度达到45.2%，在单卡V100上FP32推理速度为72.9 FPS, V100上开启TensorRT下FP16推理速度为155.6 FPS。 +PP-YOLO在[COCO](http://cocodataset.org) test-dev2017数据集上精度达到45.2%，在单卡V100上FP32推理速度为72.9 FPS, V100上开启TensorRT下FP16推理速度为155.6 FPS。
@@ -45,7 +45,7 @@ PP-YOLO从如下方面优化和提升YOLOv3模型的精度和速度： **注意:** -- PP-YOLO模型使用COCO数据集中train2017作为训练集，使用test-dev2019左右测试集。 +- PP-YOLO模型使用COCO数据集中train2017作为训练集，使用test-dev2017左右测试集。 - PP-YOLO模型训练过程中使用8GPU，每GPU batch size为24进行训练，如训练GPU数和batch size不使用上述配置，须参考[FAQ](../../docs/FAQ.md)调整学习率和迭代次数。 - PP-YOLO模型推理速度测试采用单卡V100，batch size=1进行测试，使用CUDA 10.2, CUDNN 7.5.1，TensorRT推理速度测试使用TensorRT 5.1.2.2。 - PP-YOLO模型推理速度测试数据为使用`tools/export_model.py`脚本导出模型后，使用`deploy/python/infer.py`脚本中的`--run_benchnark`参数使用Paddle预测库进行推理速度benchmark测试结果, 且测试的均为不包含数据预处理和模型输出后处理(NMS)的数据(与[YOLOv4(AlexyAB)](https://github.com/AlexeyAB/darknet)测试方法一致)。 @@ -76,7 +76,7 @@ CUDA_VISIBLE_DEVICES=0 python tools/eval.py -c configs/ppyolo/ppyolo.yml -o weig CUDA_VISIBLE_DEVICES=0 python tools/eval.py -c configs/ppyolo/ppyolo.yml -o weights=output/ppyolo/best_model ``` -我们提供了`configs/ppyolo/ppyolo_test.yml`用于评估COCO test-dev2019数据集的效果，评估COCO test-dev2019数据集的效果须先从[COCO数据集下载页](https://cocodataset.org/#download)下载test-dev2019数据集，解压到`configs/ppyolo/ppyolo_test.yml`中`EvalReader.dataset`中配置的路径，并使用如下命令进行评估 +我们提供了`configs/ppyolo/ppyolo_test.yml`用于评估COCO test-dev2017数据集的效果，评估COCO test-dev2017数据集的效果须先从[COCO数据集下载页](https://cocodataset.org/#download)下载test-dev2017数据集，解压到`configs/ppyolo/ppyolo_test.yml`中`EvalReader.dataset`中配置的路径，并使用如下命令进行评估 ```bash # 使用PaddleDetection发布的权重