- We use a multi-scale evaluation strategy to get the mAP in `Easy/Medium/Hard Set`. Please refer to the [evaluation on the WIDER FACE dataset](#Evaluated-on-the-WIDER-FACE-Dataset) for details.
@@ -46,7 +46,7 @@ We also release [PP-TinyPose](./tiny_pose/README_en.md), a real-time keypoint de
### 1. Environmental Installation
Please refer to [PaddleDetection Installation Guild](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/docs/tutorials/INSTALL.md) to install PaddlePaddle and PaddleDetection correctly.
Please refer to [PaddleDetection Installation Guild](https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.4/docs/tutorials/INSTALL.md) to install PaddlePaddle and PaddleDetection correctly.
@@ -17,7 +17,7 @@ The network for detecting vehicles is YOLOv3, the backbone of which is Dacknet53
### 2. Configuration for training
PaddleDetection provides users with a configuration file [yolov3_darknet53_270e_coco.yml](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/configs/yolov3/yolov3_darknet53_270e_coco.yml) to train YOLOv3 on the COCO dataset, compared with this file, we modify some parameters as followed to conduct the training for pedestrian detection:
PaddleDetection provides users with a configuration file [yolov3_darknet53_270e_coco.yml](https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.4/configs/yolov3/yolov3_darknet53_270e_coco.yml) to train YOLOv3 on the COCO dataset, compared with this file, we modify some parameters as followed to conduct the training for pedestrian detection:
在模型压缩中，常见的稀疏方式为结构化稀疏和非结构化稀疏，前者在某个特定维度（特征通道、卷积核等等）上对卷积、矩阵乘法进行剪枝操作，然后生成一个更小的模型结构，这样可以复用已有的卷积、矩阵乘计算，无需特殊实现推理算子；后者以每一个参数为单元进行稀疏化，然而并不会改变参数矩阵的形状，所以更依赖于推理库、硬件对于稀疏后矩阵运算的加速能力。我们在 PP-PicoDet （以下简称PicoDet） 模型上运用了非结构化稀疏技术，在精度损失较小时，获得了在 ARM CPU 端推理的显著性能提升。本文档会介绍如何非结构化稀疏训练 PicoDet，关于非结构化稀疏的更多介绍请参照[这里](https://github.com/PaddlePaddle/PaddleSlim/tree/develop/demo/dygraph/unstructured_pruning)。
在模型压缩中，常见的稀疏方式为结构化稀疏和非结构化稀疏，前者在某个特定维度（特征通道、卷积核等等）上对卷积、矩阵乘法进行剪枝操作，然后生成一个更小的模型结构，这样可以复用已有的卷积、矩阵乘计算，无需特殊实现推理算子；后者以每一个参数为单元进行稀疏化，然而并不会改变参数矩阵的形状，所以更依赖于推理库、硬件对于稀疏后矩阵运算的加速能力。我们在 PP-PicoDet （以下简称PicoDet） 模型上运用了非结构化稀疏技术，在精度损失较小时，获得了在 ARM CPU 端推理的显著性能提升。本文档会介绍如何非结构化稀疏训练 PicoDet，关于非结构化稀疏的更多介绍请参照[这里](https://github.com/PaddlePaddle/PaddleSlim/tree/release/2.4/demo/dygraph/unstructured_pruning)。
- PP-YOLO is trained on COCO train2017 dataset and evaluated on val2017 & test-dev2017 dataset，Box AP<sup>test</sup> is evaluation results of `mAP(IoU=0.5:0.95)`.
- PP-YOLO used 8 GPUs for training and mini-batch size as 24 on each GPU, if GPU number and mini-batch size is changed, learning rate and iteration times should be adjusted according [FAQ](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/docs/tutorials/FAQ).
- PP-YOLO used 8 GPUs for training and mini-batch size as 24 on each GPU, if GPU number and mini-batch size is changed, learning rate and iteration times should be adjusted according [FAQ](https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.4/docs/tutorials/FAQ).
- PP-YOLO inference speed is tesed on single Tesla V100 with batch size as 1, CUDA 10.2, CUDNN 7.5.1, TensorRT 5.1.2.2 in TensorRT mode.
- PP-YOLO FP32 inference speed testing uses inference model exported by `tools/export_model.py` and benchmarked by running `depoly/python/infer.py` with `--run_benchmark`. All testing results do not contains the time cost of data reading and post-processing(NMS), which is same as [YOLOv4(AlexyAB)](https://github.com/AlexeyAB/darknet) in testing method.
- TensorRT FP16 inference speed testing exclude the time cost of bounding-box decoding(`yolo_box`) part comparing with FP32 testing above, which means that data reading, bounding-box decoding and post-processing(NMS) is excluded(test method same as [YOLOv4(AlexyAB)](https://github.com/AlexeyAB/darknet) too)
...
...
@@ -69,26 +69,26 @@ PP-YOLO and PP-YOLOv2 improved performance and speed of YOLOv3 with following me
| Model | GPU number | images/GPU | Model Size | input shape | Box AP<sup>val</sup> | Box AP50<sup>val</sup> | Kirin 990 1xCore(FPS) | download | config |
- PP-YOLO_MobileNetV3 is trained on COCO train2017 datast and evaluated on val2017 dataset，Box AP<sup>val</sup> is evaluation results of `mAP(IoU=0.5:0.95)`, Box AP<sup>val</sup> is evaluation results of `mAP(IoU=0.5)`.
- PP-YOLO_MobileNetV3 used 4 GPUs for training and mini-batch size as 32 on each GPU, if GPU number and mini-batch size is changed, learning rate and iteration times should be adjusted according [FAQ](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/docs/tutorials/FAQ).
- PP-YOLO_MobileNetV3 used 4 GPUs for training and mini-batch size as 32 on each GPU, if GPU number and mini-batch size is changed, learning rate and iteration times should be adjusted according [FAQ](https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.4/docs/tutorials/FAQ).
- PP-YOLO_MobileNetV3 inference speed is tested on Kirin 990 with 1 thread.
### PP-YOLO tiny
| Model | GPU number | images/GPU | Model Size | Post Quant Model Size | input shape | Box AP<sup>val</sup> | Kirin 990 4xCore(FPS) | download | config | post quant model |
- PP-YOLO-tiny is trained on COCO train2017 datast and evaluated on val2017 dataset，Box AP<sup>val</sup> is evaluation results of `mAP(IoU=0.5:0.95)`, Box AP<sup>val</sup> is evaluation results of `mAP(IoU=0.5)`.
- PP-YOLO-tiny used 8 GPUs for training and mini-batch size as 32 on each GPU, if GPU number and mini-batch size is changed, learning rate and iteration times should be adjusted according [FAQ](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/docs/tutorials/FAQ/README.md).
- PP-YOLO-tiny used 8 GPUs for training and mini-batch size as 32 on each GPU, if GPU number and mini-batch size is changed, learning rate and iteration times should be adjusted according [FAQ](https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.4/docs/tutorials/FAQ/README.md).
- PP-YOLO-tiny inference speed is tested on Kirin 990 with 4 threads by arm8
- we alse provide PP-YOLO-tiny post quant inference model, which can compress model to **1.3MB** with nearly no inference on inference speed and performance
...
...
@@ -98,9 +98,9 @@ PP-YOLO trained on Pascal VOC dataset as follows:
| Model | GPU number | images/GPU | backbone | input shape | Box AP50<sup>val</sup> | download | config |
@@ -212,7 +212,7 @@ Optimizing method and ablation experiments of PP-YOLO compared with YOLOv3.
- Performance and inference spedd are measure with input shape as 608
- All models are trained on COCO train2017 datast and evaluated on val2017 & test-dev2017 dataset，`Box AP` is evaluation results as `mAP(IoU=0.5:0.95)`.
- Inference speed is tested on single Tesla V100 with batch size as 1 following test method and environment configuration in benchmark above.
-[YOLOv3-DarkNet53](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/yolov3/yolov3_darknet53_270e_coco.yml) with mAP as 39.0 is optimized YOLOv3 model in PaddleDetection，see [YOLOv3](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/configs/yolov3/README.md) for details.
-[YOLOv3-DarkNet53](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.4/configs/yolov3/yolov3_darknet53_270e_coco.yml) with mAP as 39.0 is optimized YOLOv3 model in PaddleDetection，see [YOLOv3](https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.4/configs/yolov3/README.md) for details.
- PP-YOLOE is trained on COCO train2017 dataset and evaluated on val2017 & test-dev2017 dataset，Box AP<sup>test</sup> is evaluation results of `mAP(IoU=0.5:0.95)`.
- PP-YOLOE used 8 GPUs for mixed precision training, if GPU number and mini-batch size is changed, learning rate and iteration times should be adjusted according [FAQ](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/docs/tutorials/FAQ).
- PP-YOLOE used 8 GPUs for mixed precision training, if GPU number and mini-batch size is changed, learning rate and iteration times should be adjusted according [FAQ](https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.4/docs/tutorials/FAQ).
- PP-YOLOE inference speed is tesed on single Tesla V100 with batch size as 1, CUDA 10.2, CUDNN 7.6.5, TensorRT 6.0.1.8 in TensorRT mode.
- PP-YOLOE inference speed testing uses inference model exported by `tools/export_model.py` with `-o exclude_nms=True` and benchmarked by running `depoly/python/infer.py` with `--run_benchmark`. All testing results do not contains the time cost of data reading and post-processing(NMS), which is same as [YOLOv4(AlexyAB)](https://github.com/AlexeyAB/darknet) in testing method.
- If you set `--run_benchmark=True`，you should install these dependencies at first, `pip install pynvml psutil GPUtil`.
| Backbone | Network type | Number of images per GPU | Learning rate strategy | Inferring time(fps) | Box AP | Mask AP | Download | Configuration File |
- The above V100 prediction delay non-quantified model is tested by TensorRT FP32, and the quantified model is tested by TensorRT INT8, and both of them include NMS time.
...
...
@@ -151,8 +151,8 @@ Description:
| Model | Compression Strategy | Input Size | Box AP | Download | Model Configuration File | Compression Strategy Configuration File |
COCO数据集作为目标检测任务的训练目标难度更大，意味着teacher网络会预测出更多的背景bbox，如果直接用teacher的预测输出作为student学习的`soft label`会有严重的类别不均衡问题。解决这个问题需要引入新的方法，详细背景请参考论文:[Object detection at 200 Frames Per Second](https://arxiv.org/abs/1805.06361)。
**Attention:** Due to the overall upgrade of the dynamic graph framework, the weighting model published by PaddleDetection of PAF Net needs to be evaluated with a --bias field, for example
@@ -17,7 +17,7 @@ The network for detecting vehicles is YOLOv3, the backbone of which is Dacknet53
### 2. Configuration for training
PaddleDetection provides users with a configuration file [yolov3_darknet53_270e_coco.yml](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/configs/yolov3/yolov3_darknet53_270e_coco.yml) to train YOLOv3 on the COCO dataset, compared with this file, we modify some parameters as followed to conduct the training for vehicle detection:
PaddleDetection provides users with a configuration file [yolov3_darknet53_270e_coco.yml](https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.4/configs/yolov3/yolov3_darknet53_270e_coco.yml) to train YOLOv3 on the COCO dataset, compared with this file, we modify some parameters as followed to conduct the training for vehicle detection:
