- Pre training model using large-scale data set obj365
- In the backbone, add the alpha parameter to the block branch
- Optimize the end-to-end inference speed and improve the training convergence speed
## Legacy model
- Please refer to：[PP-YOLOE 2022.03](./README_legacy.md) for details
## Table of Contents
-[Introduction](#Introduction)
-[Model Zoo](#Model-Zoo)
-[Getting Start](#Getting-Start)
-[Appendix](#Appendix)
## Introduction
PP-YOLOE is an excellent single-stage anchor-free model based on PP-YOLOv2, surpassing a variety of popular YOLO models. PP-YOLOE has a series of models, named s/m/l/x, which are configured through width multiplier and depth multiplier. PP-YOLOE avoids using special operators, such as Deformable Convolution or Matrix NMS, to be deployed friendly on various hardware. For more details, please refer to our [report](https://arxiv.org/abs/2203.16250).
PP-YOLOE+_l achieves 53.3 mAP on COCO test-dev2017 dataset with 78.1 FPS on Tesla V100. While using TensorRT FP16, PP-YOLOE+_l can be further accelerated to 149.2 FPS. PP-YOLOE+_s/m/x also have excellent accuracy and speed performance, which can be found in [Model Zoo](#Model-Zoo)
- PP-YOLOE is trained on COCO train2017 dataset and evaluated on val2017 & test-dev2017 dataset.
- The model weights in the table of Comprehensive Metrics are **the same as** that in the original Model Zoo, and evaluated on **val2017**.
- PP-YOLOE used 8 GPUs for mixed precision training, if **GPU number** or **mini-batch size** is changed, **learning rate** should be adjusted according to the formula **lr<sub>new</sub> = lr<sub>default</sub> * (batch_size<sub>new</sub> * GPU_number<sub>new</sub>) / (batch_size<sub>default</sub> * GPU_number<sub>default</sub>)**.
- 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.
- Refer to [Speed testing](#Speed-testing) to reproduce the speed testing results of PP-YOLOE.
- If you set `--run_benchmark=True`，you should install these dependencies at first, `pip install pynvml psutil GPUtil`.
- End-to-end speed test includes pre-processing + inference + post-processing and NMS time, using **Intel(R) Xeon(R) Gold 5117 CPU @ 2.00GHz**, **single Tesla V100**, **CUDA 11.2**, **CUDNN 8.2.0**, **TensorRT 8.0.1.6**.
- The Details for multiple machine and multi-gpu training, see [DistributedTraining](../../docs/tutorials/DistributedTraining_en.md)
- For Objects365 dataset download, please refer to [objects365 official website](http://www.objects365.org/overview.html). The specific category list can be downloaded from [objects365_detection_label_list.txt](https://bj.bcebos.com/v1/paddledet/data/objects365/objects365_detection_label_list.txt) organized by PaddleDetection team. It should be stored in `dataset/objects365/`, and each line represents one category. The categories need to be read when exporting the model or doing inference. If the json file is not exist, you can make the following changes to `configs/datasets/objects365_detection.yml`:
- For the format of COCO style dataset, please refer to [format-data](https://cocodataset.org/#format-data) and [format-results](https://cocodataset.org/#format-results).
- For the evaluation metric of COCO, please refer to [detection-eval](https://cocodataset.org/#detection-eval), and install [cocoapi](https://github.com/cocodataset/cocoapi) at first.
- For the evaluation metric of VOC, please refer to [VOC2012](http://host.robots.ox.ac.uk/pascal/VOC/voc2012/index.html).
### Custom dataset
1.For the annotation of custom dataset, please refer to [DetAnnoTools](https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.5/docs/tutorials/data/DetAnnoTools_en.md);
2.For training preparation of custom dataset，please refer to [PrepareDataSet](https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.5/docs/tutorials/data/PrepareDetDataSet_en.md).
### Training
Training PP-YOLOE+ on 8 GPUs with following command
- PaddleDetection supports multi-machine distributed training, you can refer to [DistributedTraining tutorial](../../docs/tutorials/DistributedTraining_en.md).
### Evaluation
Evaluating PP-YOLOE+ on COCO val2017 dataset in single GPU with following commands:
For evaluation on COCO test-dev2017 dataset, please download COCO test-dev2017 dataset from [COCO dataset download](https://cocodataset.org/#download) and decompress to COCO dataset directory and configure `EvalDataset` like `configs/ppyolo/ppyolo_test.yml`.
### Inference
Inference images in single GPU with following commands, use `--infer_img` to inference a single image and `--infer_dir` to inference all images in the directory.
If you want to export PP-YOLOE model to **ONNX format**, use following command refer to [PaddleDetection Model Export as ONNX Format Tutorial](../../deploy/EXPORT_ONNX_MODEL_en.md).
**Notes:** ONNX model only supports batch_size=1 now
### Speed testing
For fair comparison, the speed in [Model Zoo](#Model-Zoo) 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. Thus, you should export model with extra `-o exclude_nms=True` setting.
**Using Paddle Inference without TensorRT** to test speed, run following command
Next, we will introduce how to use Paddle Inference to deploy PP-YOLOE models in TensorRT FP16 mode.
First, refer to [Paddle Inference Docs](https://www.paddlepaddle.org.cn/inference/master/user_guides/download_lib.html#python), download and install packages corresponding to CUDA, CUDNN and TensorRT version.
Then, Exporting PP-YOLOE for Paddle Inference **with TensorRT**, use following command.
- TensorRT will perform optimization for the current hardware platform according to the definition of the network, generate an inference engine and serialize it into a file. This inference engine is only applicable to the current hardware hardware platform. If your hardware and software platform has not changed, you can set `use_static=True` in [enable_tensorrt_engine](https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.4/deploy/python/infer.py#L660). In this way, the serialized file generated will be saved in the `output_inference` folder, and the saved serialized file will be loaded the next time when TensorRT is executed.
- PaddleDetection release/2.4 and later versions will support NMS calling TensorRT, which requires PaddlePaddle release/2.3 and later versions.
- Here, we use [VisDrone](https://github.com/VisDrone/VisDrone-Dataset) dataset, and to detect 9 objects including `person, bicycles, car, van, truck, tricycle, awning-tricycle, bus, motor`.
- Above models trained using official default config, and load pretrained parameters on COCO dataset.
-*Due to the limited time, more verification results will be supplemented in the future. You are also welcome to contribute to PP-YOLOE*
- PP-YOLOE is trained on COCO train2017 dataset and evaluated on val2017 & test-dev2017 dataset.
- The model weights in the table of Comprehensive Metrics are **the same as** that in the original Model Zoo, and evaluated on **val2017**.
- PP-YOLOE used 8 GPUs for training, if **GPU number** or **mini-batch size** is changed, **learning rate** should be adjusted according to the formula **lr<sub>new</sub> = lr<sub>default</sub> * (batch_size<sub>new</sub> * GPU_number<sub>new</sub>) / (batch_size<sub>default</sub> * GPU_number<sub>default</sub>)**.
- 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.
