diff --git a/configs/ppyoloe/README.md b/configs/ppyoloe/README.md index 9458420fc1a7b81207bd1b0397176218b84b378a..5e5bcd39636afc9ace2c128f8581d20356d989bb 100644 --- a/configs/ppyoloe/README.md +++ b/configs/ppyoloe/README.md @@ -2,6 +2,15 @@ English | [简体中文](README_cn.md) # PP-YOLOE +## Latest News +- Release PP-YOLOE+ model: **(2022.08)** + - 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) @@ -12,10 +21,10 @@ English | [简体中文](README_cn.md) 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 51.6 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+_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 composed of following methods: - Scalable backbone and neck @@ -24,23 +33,21 @@ PP-YOLOE is composed of following methods: - [SiLU(Swish) activation function](https://arxiv.org/abs/1710.05941) ## Model Zoo -| Model | Epoch | GPU number | images/GPU | backbone | input shape | Box APval
0.5:0.95 | Box APtest
0.5:0.95 | Params(M) | FLOPs(G) | V100 FP32(FPS) | V100 TensorRT FP16(FPS) | download | config | -|:------------------------:|:-------:|:-------:|:--------:|:----------:| :-------:| :------------------: | :-------------------: |:---------:|:--------:|:---------------:| :---------------------: | :------: | :------: | -| PP-YOLOE-s | 400 | 8 | 32 | cspresnet-s | 640 | 43.4 | 43.6 | 7.93 | 17.36 | 208.3 | 333.3 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_s_400e_coco.pdparams) | [config](./ppyoloe_crn_s_400e_coco.yml) | -| PP-YOLOE-s | 300 | 8 | 32 | cspresnet-s | 640 | 43.0 | 43.2 | 7.93 | 17.36 | 208.3 | 333.3 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_s_300e_coco.pdparams) | [config](./ppyoloe_crn_s_300e_coco.yml) | -| PP-YOLOE-m | 300 | 8 | 28 | cspresnet-m | 640 | 49.0 | 49.1 | 23.43 | 49.91 | 123.4 | 208.3 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_m_300e_coco.pdparams) | [config](./ppyoloe_crn_m_300e_coco.yml) | -| PP-YOLOE-l | 300 | 8 | 20 | cspresnet-l | 640 | 51.4 | 51.6 | 52.20 | 110.07 | 78.1 | 149.2 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_300e_coco.pdparams) | [config](./ppyoloe_crn_l_300e_coco.yml) | -| PP-YOLOE-x | 300 | 8 | 16 | cspresnet-x | 640 | 52.3 | 52.4 | 98.42 | 206.59 | 45.0 | 95.2 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_x_300e_coco.pdparams) | [config](./ppyoloe_crn_x_300e_coco.yml) | +| Model | Epoch | GPU number | images/GPU | backbone | input shape | Box APval
0.5:0.95 | Box APtest
0.5:0.95 | Params(M) | FLOPs(G) | V100 FP32(FPS) | V100 TensorRT FP16(FPS) | download | config | +|:--------------:|:-----:|:-------:|:----------:|:----------:| :-------:|:--------------------------:|:---------------------------:|:---------:|:--------:|:---------------:| :---------------------: |:------------------------------------------------------------------------------------:|:-------------------------------------------:| +| PP-YOLOE+_s | 80 | 8 | 8 | cspresnet-s | 640 | 43.7 | 43.9 | 7.93 | 17.36 | 208.3 | 333.3 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_plus_crn_s_80e_coco.pdparams) | [config](./ppyoloe_plus_crn_s_80e_coco.yml) | +| PP-YOLOE+_m | 80 | 8 | 8 | cspresnet-m | 640 | 49.8 | 50.0 | 23.43 | 49.91 | 123.4 | 208.3 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_plus_crn_m_80e_coco.pdparams) | [config](./ppyoloe_plus_crn_m_80e_coco.yml) | +| PP-YOLOE+_l | 80 | 8 | 8 | cspresnet-l | 640 | 52.9 | 53.3 | 52.20 | 110.07 | 78.1 | 149.2 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_plus_crn_l_80e_coco.pdparams) | [config](./ppyoloe_plus_crn_l_80e_coco.yml) | +| PP-YOLOE+_x | 80 | 8 | 8 | cspresnet-x | 640 | 54.7 | 54.9 | 98.42 | 206.59 | 45.0 | 95.2 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_plus_crn_x_80e_coco.pdparams) | [config](./ppyoloe_plus_crn_x_80e_coco.yml) | ### Comprehensive Metrics -| Model | Epoch | AP0.5:0.95 | AP0.5 | AP0.75 | APsmall | APmedium | APlarge | ARsmall | ARmedium | ARlarge | download | config | -|:----------------------:|:-----:|:---------------:|:----------:|:-------------:| :------------:| :-----------: | :----------: |:------------:|:-------------:|:------------:| :-----: | :-----: | -| PP-YOLOE-s | 400 | 43.4 | 60.0 | 47.5 | 25.7 | 47.8 | 59.2 | 43.9 | 70.8 | 81.9 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_s_400e_coco.pdparams) | [config](./ppyoloe_crn_s_400e_coco.yml)| -| PP-YOLOE-s | 300 | 43.0 | 59.6 | 47.2 | 26.0 | 47.4 | 58.7 | 45.1 | 70.6 | 81.4 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_s_300e_coco.pdparams) | [config](./ppyoloe_crn_s_300e_coco.yml)| -| PP-YOLOE-m | 300 | 49.0 | 65.9 | 53.8 | 30.9 | 53.5 | 65.3 | 50.9 | 74.4 | 84.7 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_m_300e_coco.pdparams) | [config](./ppyoloe_crn_m_300e_coco.yml)| -| PP-YOLOE-l | 300 | 51.4 | 68.6 | 56.2 | 34.8 | 56.1 | 68.0 | 53.1 | 76.8 | 85.6 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_300e_coco.pdparams) | [config](./ppyoloe_crn_l_300e_coco.yml)| -| PP-YOLOE-x | 300 | 52.3 | 69.5 | 56.8 | 35.1 | 57.0 | 68.6 | 55.5 | 76.9 | 85.7 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_x_300e_coco.pdparams) | [config](./ppyoloe_crn_x_300e_coco.yml)| +| Model | Epoch | AP0.5:0.95 | AP0.5 | AP0.75 | APsmall | APmedium | APlarge | ARsmall | ARmedium | ARlarge | +|:------------------------:|:-----:|:---------------:|:----------:|:------------:|:------------:| :-----------: |:------------:|:------------:|:-------------:|:------------:| +| PP-YOLOE+_s | 80 | 43.7 | 60.6 | 47.9 | 26.5 | 47.5 | 59.0 | 46.7 | 71.4 | 81.7 | +| PP-YOLOE+_m | 80 | 49.8 | 67.1 | 54.5 | 31.8 | 53.9 | 66.2 | 53.3 | 75.0 | 84.6 | +| PP-YOLOE+_l | 80 | 52.9 | 70.1 | 57.9 | 35.2 | 57.5 | 69.1 | 56.0 | 77.9 | 86.9 | +| PP-YOLOE+_x | 80 | 54.7 | 72.0 | 59.9 | 37.9 | 59.3 | 70.4 | 57.0 | 78.7 | 87.2 | **Notes:** @@ -68,23 +75,24 @@ The PaddleDetection team provides configs and weights of various feature detecti ### Training -Training PP-YOLOE with mixed precision on 8 GPUs with following command +Training PP-YOLOE+ on 8 GPUs with following command ```bash -python -m paddle.distributed.launch --gpus 0,1,2,3,4,5,6,7 tools/train.py -c configs/ppyoloe/ppyoloe_crn_l_300e_coco.yml --amp +python -m paddle.distributed.launch --gpus 0,1,2,3,4,5,6,7 tools/train.py -c configs/ppyoloe/ppyoloe_plus_crn_l_80e_coco.yml ``` **Notes:** - use `--amp` to train with default config to avoid out of memeory. +- If you need to evaluate while training, please add `--eval`. - PaddleDetection supports multi-machine distribued training, you can refer to [DistributedTraining tutorial](../../docs/DistributedTraining_en.md). ### Evaluation -Evaluating PP-YOLOE on COCO val2017 dataset in single GPU with following commands: +Evaluating PP-YOLOE+ on COCO val2017 dataset in single GPU with following commands: ```bash -CUDA_VISIBLE_DEVICES=0 python tools/eval.py -c configs/ppyoloe/ppyoloe_crn_l_300e_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_300e_coco.pdparams +CUDA_VISIBLE_DEVICES=0 python tools/eval.py -c configs/ppyoloe/ppyoloe_plus_crn_l_80e_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyoloe_plus_crn_l_80e_coco.pdparams ``` 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`. @@ -95,39 +103,39 @@ Inference images in single GPU with following commands, use `--infer_img` to inf ```bash # inference single image -CUDA_VISIBLE_DEVICES=0 python tools/infer.py -c configs/ppyoloe/ppyoloe_crn_l_300e_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_300e_coco.pdparams --infer_img=demo/000000014439_640x640.jpg +CUDA_VISIBLE_DEVICES=0 python tools/infer.py -c configs/ppyoloe/ppyoloe_plus_crn_l_80e_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyoloe_plus_crn_l_80e_coco.pdparams --infer_img=demo/000000014439_640x640.jpg # inference all images in the directory -CUDA_VISIBLE_DEVICES=0 python tools/infer.py -c configs/ppyoloe/ppyoloe_crn_l_300e_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_300e_coco.pdparams --infer_dir=demo +CUDA_VISIBLE_DEVICES=0 python tools/infer.py -c configs/ppyoloe/ppyoloe_plus_crn_l_80e_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyoloe_plus_crn_l_80e_coco.pdparams --infer_dir=demo ``` ### Exporting models For deployment on GPU or speed testing, model should be first exported to inference model using `tools/export_model.py`. -**Exporting PP-YOLOE for Paddle Inference without TensorRT**, use following command +**Exporting PP-YOLOE+ for Paddle Inference without TensorRT**, use following command ```bash -python tools/export_model.py -c configs/ppyoloe/ppyoloe_crn_l_300e_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_300e_coco.pdparams +python tools/export_model.py -c configs/ppyoloe/ppyoloe_plus_crn_l_80e_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyoloe_plus_crn_l_80e_coco.pdparams ``` -**Exporting PP-YOLOE for Paddle Inference with TensorRT** for better performance, use following command with extra `-o trt=True` setting. +**Exporting PP-YOLOE+ for Paddle Inference with TensorRT** for better performance, use following command with extra `-o trt=True` setting. ```bash -python tools/export_model.py -c configs/ppyoloe/ppyoloe_crn_l_300e_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_300e_coco.pdparams trt=True +python tools/export_model.py -c configs/ppyoloe/ppyoloe_plus_crn_l_80e_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyoloe_plus_crn_l_80e_coco.pdparams trt=True ``` 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). ```bash # export inference model -python tools/export_model.py -c configs/ppyoloe/ppyoloe_crn_l_300e_coco.yml --output_dir=output_inference -o weights=https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_300e_coco.pdparams +python tools/export_model.py -c configs/ppyoloe/ppyoloe_plus_crn_l_80e_coco.yml --output_dir=output_inference -o weights=https://paddledet.bj.bcebos.com/models/ppyoloe_plus_crn_l_80e_coco.pdparams # install paddle2onnx pip install paddle2onnx # convert to onnx -paddle2onnx --model_dir output_inference/ppyoloe_crn_l_300e_coco --model_filename model.pdmodel --params_filename model.pdiparams --opset_version 11 --save_file ppyoloe_crn_l_300e_coco.onnx +paddle2onnx --model_dir output_inference/ppyoloe_plus_crn_l_80e_coco --model_filename model.pdmodel --params_filename model.pdiparams --opset_version 11 --save_file ppyoloe_plus_crn_l_80e_coco.onnx ``` @@ -141,20 +149,20 @@ For fair comparison, the speed in [Model Zoo](#Model-Zoo) do not contains the ti ```bash # export inference model -python tools/export_model.py -c configs/ppyoloe/ppyoloe_crn_l_300e_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_300e_coco.pdparams exclude_nms=True +python tools/export_model.py -c configs/ppyoloe/ppyoloe_plus_crn_l_80e_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyoloe_plus_crn_l_80e_coco.pdparams exclude_nms=True # speed testing with run_benchmark=True -CUDA_VISIBLE_DEVICES=0 python deploy/python/infer.py --model_dir=output_inference/ppyoloe_crn_l_300e_coco --image_file=demo/000000014439_640x640.jpg --run_mode=paddle --device=gpu --run_benchmark=True +CUDA_VISIBLE_DEVICES=0 python deploy/python/infer.py --model_dir=output_inference/ppyoloe_plus_crn_l_80e_coco --image_file=demo/000000014439_640x640.jpg --run_mode=paddle --device=gpu --run_benchmark=True ``` **Using Paddle Inference with TensorRT** to test speed, run following command ```bash # export inference model with trt=True -python tools/export_model.py -c configs/ppyoloe/ppyoloe_crn_l_300e_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_300e_coco.pdparams exclude_nms=True trt=True +python tools/export_model.py -c configs/ppyoloe/ppyoloe_plus_crn_l_80e_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyoloe_plus_crn_l_80e_coco.pdparams exclude_nms=True trt=True # speed testing with run_benchmark=True,run_mode=trt_fp32/trt_fp16 -CUDA_VISIBLE_DEVICES=0 python deploy/python/infer.py --model_dir=output_inference/ppyoloe_crn_l_300e_coco --image_file=demo/000000014439_640x640.jpg --run_mode=trt_fp16 --device=gpu --run_benchmark=True +CUDA_VISIBLE_DEVICES=0 python deploy/python/infer.py --model_dir=output_inference/ppyoloe_plus_crn_l_80e_coco --image_file=demo/000000014439_640x640.jpg --run_mode=trt_fp16 --device=gpu --run_benchmark=True ``` @@ -162,16 +170,16 @@ CUDA_VISIBLE_DEVICES=0 python deploy/python/infer.py --model_dir=output_inferenc ```bash # export inference model with trt=True -python tools/export_model.py -c configs/ppyoloe/ppyoloe_crn_s_300e_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyoloe_crn_s_300e_coco.pdparams exclude_nms=True trt=True +python tools/export_model.py -c configs/ppyoloe/ppyoloe_plus_crn_s_80e_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyoloe_plus_crn_s_80e_coco.pdparams exclude_nms=True trt=True # convert to onnx -paddle2onnx --model_dir output_inference/ppyoloe_crn_s_300e_coco --model_filename model.pdmodel --params_filename model.pdiparams --opset_version 12 --save_file ppyoloe_crn_s_300e_coco.onnx +paddle2onnx --model_dir output_inference/ppyoloe_plus_crn_s_80e_coco --model_filename model.pdmodel --params_filename model.pdiparams --opset_version 12 --save_file ppyoloe_plus_crn_s_80e_coco.onnx # trt inference using fp16 and batch_size=1 -trtexec --onnx=./ppyoloe_crn_s_300e_coco.onnx --saveEngine=./ppyoloe_s_bs1.engine --workspace=1024 --avgRuns=1000 --shapes=image:1x3x640x640,scale_factor:1x2 --fp16 +trtexec --onnx=./ppyoloe_plus_crn_s_80e_coco.onnx --saveEngine=./ppyoloe_s_bs1.engine --workspace=1024 --avgRuns=1000 --shapes=image:1x3x640x640,scale_factor:1x2 --fp16 # trt inference using fp16 and batch_size=32 -trtexec --onnx=./ppyoloe_crn_s_300e_coco.onnx --saveEngine=./ppyoloe_s_bs32.engine --workspace=1024 --avgRuns=1000 --shapes=image:32x3x640x640,scale_factor:32x2 --fp16 +trtexec --onnx=./ppyoloe_plus_crn_s_80e_coco.onnx --saveEngine=./ppyoloe_s_bs32.engine --workspace=1024 --avgRuns=1000 --shapes=image:32x3x640x640,scale_factor:32x2 --fp16 # Using the above script, T4 and tensorrt 7.2 machine, the speed of PPYOLOE-s model is as follows, @@ -196,17 +204,17 @@ First, refer to [Paddle Inference Docs](https://www.paddlepaddle.org.cn/inferenc Then, Exporting PP-YOLOE for Paddle Inference **with TensorRT**, use following command. ```bash -python tools/export_model.py -c configs/ppyoloe/ppyoloe_crn_l_300e_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_300e_coco.pdparams trt=True +python tools/export_model.py -c configs/ppyoloe/ppyoloe_plus_crn_l_80e_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyoloe_plus_crn_l_80e_coco.pdparams trt=True ``` Finally, inference in TensorRT FP16 mode. ```bash # inference single image -CUDA_VISIBLE_DEVICES=0 python deploy/python/infer.py --model_dir=output_inference/ppyoloe_crn_l_300e_coco --image_file=demo/000000014439_640x640.jpg --device=gpu --run_mode=trt_fp16 +CUDA_VISIBLE_DEVICES=0 python deploy/python/infer.py --model_dir=output_inference/ppyoloe_plus_crn_l_80e_coco --image_file=demo/000000014439_640x640.jpg --device=gpu --run_mode=trt_fp16 # inference all images in the directory -CUDA_VISIBLE_DEVICES=0 python deploy/python/infer.py --model_dir=output_inference/ppyoloe_crn_l_300e_coco --image_dir=demo/ --device=gpu --run_mode=trt_fp16 +CUDA_VISIBLE_DEVICES=0 python deploy/python/infer.py --model_dir=output_inference/ppyoloe_plus_crn_l_80e_coco --image_dir=demo/ --device=gpu --run_mode=trt_fp16 ``` diff --git a/configs/ppyoloe/README_cn.md b/configs/ppyoloe/README_cn.md index 71ef0198feac0b2f913e05a2c92cc58c8d079d67..0ca5bbd217a00da80d13171f741ab3e020220d6c 100644 --- a/configs/ppyoloe/README_cn.md +++ b/configs/ppyoloe/README_cn.md @@ -2,6 +2,15 @@ # PP-YOLOE +## 最新动态 +- 发布PP-YOLOE+模型: **(2022.08)** + - 使用大规模数据集obj365预训练模型 + - 在backbone中block分支中增加alpha参数 + - 优化端到端推理速度，提升训练收敛速度 + +## 历史版本模型 +- 详情请参考：[PP-YOLOE 2022.03版本](./README_legacy.md) + ## 内容 - [简介](#简介) - [模型库](#模型库) @@ -12,10 +21,10 @@ PP-YOLOE是基于PP-YOLOv2的卓越的单阶段Anchor-free模型，超越了多种流行的YOLO模型。PP-YOLOE有一系列的模型，即s/m/l/x，可以通过width multiplier和depth multiplier配置。PP-YOLOE避免了使用诸如Deformable Convolution或者Matrix NMS之类的特殊算子，以使其能轻松地部署在多种多样的硬件上。更多细节可以参考我们的[report](https://arxiv.org/abs/2203.16250)。
- +
-PP-YOLOE-l在COCO test-dev2017达到了51.6的mAP, 同时其速度在Tesla V100上达到了78.1 FPS。PP-YOLOE-s/m/x同样具有卓越的精度速度性价比, 其精度速度可以在[模型库](#模型库)中找到。 +PP-YOLOE+_l在COCO test-dev2017达到了53.3的mAP, 同时其速度在Tesla V100上达到了78.1 FPS。PP-YOLOE+_s/m/x同样具有卓越的精度速度性价比, 其精度速度可以在[模型库](#模型库)中找到。 PP-YOLOE由以下方法组成 - 可扩展的backbone和neck @@ -24,23 +33,21 @@ PP-YOLOE由以下方法组成 - [SiLU(Swish)激活函数](https://arxiv.org/abs/1710.05941) ## 模型库 -| 模型 | Epoch | GPU个数 | 每GPU图片个数 | 骨干网络 | 输入尺寸 | Box APval
0.5:0.95 | Box APtest
0.5:0.95 | Params(M) | FLOPs(G) | V100 FP32(FPS) | V100 TensorRT FP16(FPS) | 模型下载 | 配置文件 | -|:------------------------:|:-------:|:-------:|:--------:|:----------:| :-------:| :------------------: | :-------------------: |:---------:|:--------:|:---------------:| :---------------------: | :------: | :------: | -| PP-YOLOE-s | 400 | 8 | 32 | cspresnet-s | 640 | 43.4 | 43.6 | 7.93 | 17.36 | 208.3 | 333.3 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_s_400e_coco.pdparams) | [config](./ppyoloe_crn_s_400e_coco.yml) | -| PP-YOLOE-s | 300 | 8 | 32 | cspresnet-s | 640 | 43.0 | 43.2 | 7.93 | 17.36 | 208.3 | 333.3 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_s_300e_coco.pdparams) | [config](./ppyoloe_crn_s_300e_coco.yml) | -| PP-YOLOE-m | 300 | 8 | 28 | cspresnet-m | 640 | 49.0 | 49.1 | 23.43 | 49.91 | 123.4 | 208.3 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_m_300e_coco.pdparams) | [config](./ppyoloe_crn_m_300e_coco.yml) | -| PP-YOLOE-l | 300 | 8 | 20 | cspresnet-l | 640 | 51.4 | 51.6 | 52.20 | 110.07 | 78.1 | 149.2 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_300e_coco.pdparams) | [config](./ppyoloe_crn_l_300e_coco.yml) | -| PP-YOLOE-x | 300 | 8 | 16 | cspresnet-x | 640 | 52.3 | 52.4 | 98.42 | 206.59 | 45.0 | 95.2 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_x_300e_coco.pdparams) | [config](./ppyoloe_crn_x_300e_coco.yml) | +| 模型 | Epoch | GPU个数 | 每GPU图片个数 | 骨干网络 | 输入尺寸 | Box APval
0.5:0.95 | Box APtest
0.5:0.95 | Params(M) | FLOPs(G) | V100 FP32(FPS) | V100 TensorRT FP16(FPS) | 模型下载 | 配置文件 | +|:---------------:|:-----:|:---------:|:--------:|:----------:|:----------:|:--------------------------:|:---------------------------:|:---------:|:--------:|:---------------:| :---------------------: |:------------------------------------------------------------------------------------:|:-------------------------------------------:| +| PP-YOLOE+_s | 80 | 8 | 8 | cspresnet-s | 640 | 43.7 | 43.9 | 7.93 | 17.36 | 208.3 | 333.3 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_plus_crn_s_80e_coco.pdparams) | [config](./ppyoloe_plus_crn_s_80e_coco.yml) | +| PP-YOLOE+_m | 80 | 8 | 8 | cspresnet-m | 640 | 49.8 | 50.0 | 23.43 | 49.91 | 123.4 | 208.3 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_plus_crn_m_80e_coco.pdparams) | [config](./ppyoloe_plus_crn_m_80e_coco.yml) | +| PP-YOLOE+_l | 80 | 8 | 8 | cspresnet-l | 640 | 52.9 | 53.3 | 52.20 | 110.07 | 78.1 | 149.2 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_plus_crn_l_80e_coco.pdparams) | [config](./ppyoloe_plus_crn_l_80e_coco.yml) | +| PP-YOLOE+_x | 80 | 8 | 8 | cspresnet-x | 640 | 54.7 | 54.9 | 98.42 | 206.59 | 45.0 | 95.2 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_plus_crn_x_80e_coco.pdparams) | [config](./ppyoloe_plus_crn_x_80e_coco.yml) | ### 综合指标 -| 模型 | Epoch | AP0.5:0.95 | AP0.5 | AP0.75 | APsmall | APmedium | APlarge | ARsmall | ARmedium | ARlarge | 模型下载 | 配置文件 | -|:----------------------:|:-----:|:---------------:|:----------:|:-------------:| :------------:| :-----------: | :----------: |:------------:|:-------------:|:------------:| :-----: | :-----: | -| PP-YOLOE-s | 400 | 43.4 | 60.0 | 47.5 | 25.7 | 47.8 | 59.2 | 43.9 | 70.8 | 81.9 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_s_400e_coco.pdparams) | [config](./ppyoloe_crn_s_400e_coco.yml)| -| PP-YOLOE-s | 300 | 43.0 | 59.6 | 47.2 | 26.0 | 47.4 | 58.7 | 45.1 | 70.6 | 81.4 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_s_300e_coco.pdparams) | [config](./ppyoloe_crn_s_300e_coco.yml)| -| PP-YOLOE-m | 300 | 49.0 | 65.9 | 53.8 | 30.9 | 53.5 | 65.3 | 50.9 | 74.4 | 84.7 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_m_300e_coco.pdparams) | [config](./ppyoloe_crn_m_300e_coco.yml)| -| PP-YOLOE-l | 300 | 51.4 | 68.6 | 56.2 | 34.8 | 56.1 | 68.0 | 53.1 | 76.8 | 85.6 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_300e_coco.pdparams) | [config](./ppyoloe_crn_l_300e_coco.yml)| -| PP-YOLOE-x | 300 | 52.3 | 69.5 | 56.8 | 35.1 | 57.0 | 68.6 | 55.5 | 76.9 | 85.7 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_x_300e_coco.pdparams) | [config](./ppyoloe_crn_x_300e_coco.yml)| +| 模型 | Epoch | AP0.5:0.95 | AP0.5 | AP0.75 | APsmall | APmedium | APlarge | ARsmall | ARmedium | ARlarge | +|:------------------------:|:-----:|:---------------:|:----------:|:-----------:|:------------:|:-------------:|:------------:|:------------:|:-------------:|:------------:| +| PP-YOLOE+_s | 80 | 43.7 | 60.6 | 47.9 | 26.5 | 47.5 | 59.0 | 46.7 | 71.4 | 81.7 | +| PP-YOLOE+_m | 80 | 49.8 | 67.1 | 54.5 | 31.8 | 53.9 | 66.2 | 53.3 | 75.0 | 84.6 | +| PP-YOLOE+_l | 80 | 52.9 | 70.1 | 57.9 | 35.2 | 57.5 | 69.1 | 56.0 | 77.9 | 86.9 | +| PP-YOLOE+_x | 80 | 54.7 | 72.0 | 59.9 | 37.9 | 59.3 | 70.4 | 57.0 | 78.7 | 87.2 | **注意:** @@ -68,13 +75,13 @@ PaddleDetection团队提供了基于PP-YOLOE的各种垂类检测模型的配置 ### 训练 -执行以下指令使用混合精度训练PP-YOLOE +请执行以下指令训练PP-YOLOE+ ```bash -python -m paddle.distributed.launch --gpus 0,1,2,3,4,5,6,7 tools/train.py -c configs/ppyoloe/ppyoloe_crn_l_300e_coco.yml --amp +python -m paddle.distributed.launch --gpus 0,1,2,3,4,5,6,7 tools/train.py -c configs/ppyoloe/ppyoloe_plus_crn_l_80e_coco.yml ``` **注意:** -- 使用默认配置训练需要设置`--amp`以避免显存溢出. +- 如果需要边训练边评估，请添加`--eval`. - PaddleDetection支持多机训练，可以参考[多机训练教程](../../docs/DistributedTraining_cn.md). ### 评估 @@ -82,7 +89,7 @@ python -m paddle.distributed.launch --gpus 0,1,2,3,4,5,6,7 tools/train.py -c con 执行以下命令在单个GPU上评估COCO val2017数据集 ```bash -CUDA_VISIBLE_DEVICES=0 python tools/eval.py -c configs/ppyoloe/ppyoloe_crn_l_300e_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_300e_coco.pdparams +CUDA_VISIBLE_DEVICES=0 python tools/eval.py -c configs/ppyoloe/ppyoloe_plus_crn_l_80e_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyoloe_plus_crn_l_80e_coco.pdparams ``` 在coco test-dev2017上评估，请先从[COCO数据集下载](https://cocodataset.org/#download)下载COCO test-dev2017数据集，然后解压到COCO数据集文件夹并像`configs/ppyolo/ppyolo_test.yml`一样配置`EvalDataset`。 @@ -94,26 +101,26 @@ CUDA_VISIBLE_DEVICES=0 python tools/eval.py -c configs/ppyoloe/ppyoloe_crn_l_300 ```bash # 推理单张图片 -CUDA_VISIBLE_DEVICES=0 python tools/infer.py -c configs/ppyoloe/ppyoloe_crn_l_300e_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_300e_coco.pdparams --infer_img=demo/000000014439_640x640.jpg +CUDA_VISIBLE_DEVICES=0 python tools/infer.py -c configs/ppyoloe/ppyoloe_plus_crn_l_80e_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyoloe_plus_crn_l_80e_coco.pdparams --infer_img=demo/000000014439_640x640.jpg # 推理文件中的所有图片 -CUDA_VISIBLE_DEVICES=0 python tools/infer.py -c configs/ppyoloe/ppyoloe_crn_l_300e_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_300e_coco.pdparams --infer_dir=demo +CUDA_VISIBLE_DEVICES=0 python tools/infer.py -c configs/ppyoloe/ppyoloe_plus_crn_l_80e_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyoloe_plus_crn_l_80e_coco.pdparams --infer_dir=demo ``` ### 模型导出 -PP-YOLOE在GPU上部署或者速度测试需要通过`tools/export_model.py`导出模型。 +PP-YOLOE+在GPU上部署或者速度测试需要通过`tools/export_model.py`导出模型。 当你**使用Paddle Inference但不使用TensorRT**时，运行以下的命令导出模型 ```bash -python tools/export_model.py -c configs/ppyoloe/ppyoloe_crn_l_300e_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_300e_coco.pdparams +python tools/export_model.py -c configs/ppyoloe/ppyoloe_plus_crn_l_80e_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyoloe_plus_crn_l_80e_coco.pdparams ``` 当你**使用Paddle Inference且使用TensorRT**时，需要指定`-o trt=True`来导出模型。 ```bash -python tools/export_model.py -c configs/ppyoloe/ppyoloe_crn_l_300e_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_300e_coco.pdparams trt=True +python tools/export_model.py -c configs/ppyoloe/ppyoloe_plus_crn_l_80e_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyoloe_plus_crn_l_80e_coco.pdparams trt=True ``` 如果你想将PP-YOLOE模型导出为**ONNX格式**，参考 @@ -122,13 +129,13 @@ python tools/export_model.py -c configs/ppyoloe/ppyoloe_crn_l_300e_coco.yml -o w ```bash # 导出推理模型 -python tools/export_model.py -c configs/ppyoloe/ppyoloe_crn_l_300e_coco.yml --output_dir=output_inference -o weights=https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_300e_coco.pdparams +python tools/export_model.py -c configs/ppyoloe/ppyoloe_plus_crn_l_80e_coco.yml --output_dir=output_inference -o weights=https://paddledet.bj.bcebos.com/models/ppyoloe_plus_crn_l_80e_coco.pdparams # 安装paddle2onnx pip install paddle2onnx # 转换成onnx格式 -paddle2onnx --model_dir output_inference/ppyoloe_crn_l_300e_coco --model_filename model.pdmodel --params_filename model.pdiparams --opset_version 11 --save_file ppyoloe_crn_l_300e_coco.onnx +paddle2onnx --model_dir output_inference/ppyoloe_plus_crn_l_80e_coco --model_filename model.pdmodel --params_filename model.pdiparams --opset_version 11 --save_file ppyoloe_plus_crn_l_80e_coco.onnx ``` **注意：** ONNX模型目前只支持batch_size=1 @@ -141,20 +148,20 @@ paddle2onnx --model_dir output_inference/ppyoloe_crn_l_300e_coco --model_filenam ```bash # 导出模型 -python tools/export_model.py -c configs/ppyoloe/ppyoloe_crn_l_300e_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_300e_coco.pdparams exclude_nms=True +python tools/export_model.py -c configs/ppyoloe/ppyoloe_plus_crn_l_80e_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyoloe_plus_crn_l_80e_coco.pdparams exclude_nms=True # 速度测试，使用run_benchmark=True -CUDA_VISIBLE_DEVICES=0 python deploy/python/infer.py --model_dir=output_inference/ppyoloe_crn_l_300e_coco --image_file=demo/000000014439_640x640.jpg --run_mode=paddle --device=gpu --run_benchmark=True +CUDA_VISIBLE_DEVICES=0 python deploy/python/infer.py --model_dir=output_inference/ppyoloe_plus_crn_l_80e_coco --image_file=demo/000000014439_640x640.jpg --run_mode=paddle --device=gpu --run_benchmark=True ``` **使用Paddle Inference且使用TensorRT**进行测速，执行以下命令： ```bash # 导出模型，使用trt=True -python tools/export_model.py -c configs/ppyoloe/ppyoloe_crn_l_300e_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_300e_coco.pdparams exclude_nms=True trt=True +python tools/export_model.py -c configs/ppyoloe/ppyoloe_plus_crn_l_80e_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyoloe_plus_crn_l_80e_coco.pdparams exclude_nms=True trt=True # 速度测试，使用run_benchmark=True, run_mode=trt_fp32/trt_fp16 -CUDA_VISIBLE_DEVICES=0 python deploy/python/infer.py --model_dir=output_inference/ppyoloe_crn_l_300e_coco --image_file=demo/000000014439_640x640.jpg --run_mode=trt_fp16 --device=gpu --run_benchmark=True +CUDA_VISIBLE_DEVICES=0 python deploy/python/infer.py --model_dir=output_inference/ppyoloe_plus_crn_l_80e_coco --image_file=demo/000000014439_640x640.jpg --run_mode=trt_fp16 --device=gpu --run_benchmark=True ``` @@ -163,18 +170,18 @@ CUDA_VISIBLE_DEVICES=0 python deploy/python/infer.py --model_dir=output_inferenc ```bash # 导出模型 -python tools/export_model.py -c configs/ppyoloe/ppyoloe_crn_s_300e_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyoloe_crn_s_300e_coco.pdparams exclude_nms=True trt=True +python tools/export_model.py -c configs/ppyoloe/ppyoloe_plus_crn_s_80e_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyoloe_plus_crn_s_80e_coco.pdparams exclude_nms=True trt=True # 转化成ONNX格式 -paddle2onnx --model_dir output_inference/ppyoloe_crn_s_300e_coco --model_filename model.pdmodel --params_filename model.pdiparams --opset_version 12 --save_file ppyoloe_crn_s_300e_coco.onnx +paddle2onnx --model_dir output_inference/ppyoloe_plus_crn_s_80e_coco --model_filename model.pdmodel --params_filename model.pdiparams --opset_version 12 --save_file ppyoloe_plus_crn_s_80e_coco.onnx # 测试速度，半精度，batch_size=1 -trtexec --onnx=./ppyoloe_crn_s_300e_coco.onnx --saveEngine=./ppyoloe_s_bs1.engine --workspace=1024 --avgRuns=1000 --shapes=image:1x3x640x640,scale_factor:1x2 --fp16 +trtexec --onnx=./ppyoloe_plus_crn_s_80e_coco.onnx --saveEngine=./ppyoloe_s_bs1.engine --workspace=1024 --avgRuns=1000 --shapes=image:1x3x640x640,scale_factor:1x2 --fp16 # 测试速度，半精度，batch_size=32 -trtexec --onnx=./ppyoloe_crn_s_300e_coco.onnx --saveEngine=./ppyoloe_s_bs32.engine --workspace=1024 --avgRuns=1000 --shapes=image:32x3x640x640,scale_factor:32x2 --fp16 +trtexec --onnx=./ppyoloe_plus_crn_s_80e_coco.onnx --saveEngine=./ppyoloe_s_bs32.engine --workspace=1024 --avgRuns=1000 --shapes=image:32x3x640x640,scale_factor:32x2 --fp16 -# 使用上边的脚本, 在T4 和 TensorRT 7.2的环境下，PPYOLOE-s模型速度如下 +# 使用上边的脚本, 在T4 和 TensorRT 7.2的环境下，PPYOLOE-plus-s模型速度如下 # batch_size=1, 2.80ms, 357fps # batch_size=32, 67.69ms, 472fps ``` @@ -196,17 +203,17 @@ PP-YOLOE可以使用以下方式进行部署： 然后，运行以下命令导出模型 ```bash -python tools/export_model.py -c configs/ppyoloe/ppyoloe_crn_l_300e_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_300e_coco.pdparams trt=True +python tools/export_model.py -c configs/ppyoloe/ppyoloe_plus_crn_l_80e_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyoloe_plus_crn_l_80e_coco.pdparams trt=True ``` 最后，使用TensorRT FP16进行推理 ```bash # 推理单张图片 -CUDA_VISIBLE_DEVICES=0 python deploy/python/infer.py --model_dir=output_inference/ppyoloe_crn_l_300e_coco --image_file=demo/000000014439_640x640.jpg --device=gpu --run_mode=trt_fp16 +CUDA_VISIBLE_DEVICES=0 python deploy/python/infer.py --model_dir=output_inference/ppyoloe_plus_crn_l_80e_coco --image_file=demo/000000014439_640x640.jpg --device=gpu --run_mode=trt_fp16 # 推理文件夹下的所有图片 -CUDA_VISIBLE_DEVICES=0 python deploy/python/infer.py --model_dir=output_inference/ppyoloe_crn_l_300e_coco --image_dir=demo/ --device=gpu --run_mode=trt_fp16 +CUDA_VISIBLE_DEVICES=0 python deploy/python/infer.py --model_dir=output_inference/ppyoloe_plus_crn_l_80e_coco --image_dir=demo/ --device=gpu --run_mode=trt_fp16 ``` diff --git a/docs/images/ppyoloe_map_fps.png b/docs/images/ppyoloe_map_fps.png deleted file mode 100644 index 17186cda3202952c805a1ddcf50a071a66c1a4ff..0000000000000000000000000000000000000000 Binary files a/docs/images/ppyoloe_map_fps.png and /dev/null differ diff --git a/docs/images/ppyoloe_plus_map_fps.png b/docs/images/ppyoloe_plus_map_fps.png new file mode 100644 index 0000000000000000000000000000000000000000..dbc0e4cca60775103fd655c36c3c4092f57a24a5 Binary files /dev/null and b/docs/images/ppyoloe_plus_map_fps.png differ