Skip to content

P
PaddleDetection

s920243400 / PaddleDetection
与 Fork 源项目一致

Fork自 PaddlePaddle / PaddleDetection

通知 2
Star 0
Fork 0
P
PaddleDetection
未验证 提交 8c790b97 编写于 作者: S shangliang Xu 提交者： GitHub
浏览文件
操作

[docs] update ppyoloe_plus docs, test=document_fix (#6729)

上级 89499576
隐藏空白更改
内联 并排
Showing with 93 addition and 78 deletion
configs/ppyoloe/README.md
浏览文件 @ 8c790b97
...@@ -2,6 +2,15 @@ English | [简体中文](README_cn.md) ...@@ -2,6 +2,15 @@ English | [简体中文](README_cn.md)
# PP-YOLOE # 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 ## Table of Contents
- [Introduction](#Introduction) - [Introduction](#Introduction)
- [Model Zoo](#Model-Zoo) - [Model Zoo](#Model-Zoo)
...@@ -12,10 +21,10 @@ English | [简体中文](README_cn.md) ...@@ -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 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).
<div align="center"> <div align="center">
<img src="../../docs/images/ppyoloe_map_fps.png" width=500 /> <img src="../../docs/images/ppyoloe_plus_map_fps.png" width=500 />
</div> </div>
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: PP-YOLOE is composed of following methods:
- Scalable backbone and neck - Scalable backbone and neck
...@@ -24,23 +33,21 @@ PP-YOLOE is composed of following methods: ...@@ -24,23 +33,21 @@ PP-YOLOE is composed of following methods:
- [SiLU(Swish) activation function](https://arxiv.org/abs/1710.05941) - [SiLU(Swish) activation function](https://arxiv.org/abs/1710.05941)
## Model Zoo ## Model Zoo
| Model | Epoch | GPU number | images/GPU | backbone | input shape | Box AP<sup>val<br>0.5:0.95 | Box AP<sup>test<br>0.5:0.95 | Params(M) | FLOPs(G) | V100 FP32(FPS) | V100 TensorRT FP16(FPS) | download | config | | Model | Epoch | GPU number | images/GPU | backbone | input shape | Box AP<sup>val<br>0.5:0.95 | Box AP<sup>test<br>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 | 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-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 | 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-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 | 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-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 | 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) |
| 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) |
### Comprehensive Metrics ### Comprehensive Metrics
| Model | Epoch | AP<sup>0.5:0.95 | AP<sup>0.5 | AP<sup>0.75 | AP<sup>small | AP<sup>medium | AP<sup>large | AR<sup>small | AR<sup>medium | AR<sup>large | download | config | | Model | Epoch | AP<sup>0.5:0.95 | AP<sup>0.5 | AP<sup>0.75 | AP<sup>small | AP<sup>medium | AP<sup>large | AR<sup>small | AR<sup>medium | AR<sup>large |
|:----------------------:|:-----:|:---------------:|:----------:|:-------------:| :------------:| :-----------: | :----------: |:------------:|:-------------:|:------------:| :-----: | :-----: | |:------------------------:|:-----:|:---------------:|:----------:|:------------:|:------------:| :-----------: |:------------:|:------------:|:-------------:|:------------:|
| 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 | 80 | 43.7 | 60.6 | 47.9 | 26.5 | 47.5 | 59.0 | 46.7 | 71.4 | 81.7 |
| 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 | 80 | 49.8 | 67.1 | 54.5 | 31.8 | 53.9 | 66.2 | 53.3 | 75.0 | 84.6 |
| 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 | 80 | 52.9 | 70.1 | 57.9 | 35.2 | 57.5 | 69.1 | 56.0 | 77.9 | 86.9 |
| 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 | 80 | 54.7 | 72.0 | 59.9 | 37.9 | 59.3 | 70.4 | 57.0 | 78.7 | 87.2 |
| 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)|
**Notes:** **Notes:**
...@@ -68,23 +75,24 @@ The PaddleDetection team provides configs and weights of various feature detecti ...@@ -68,23 +75,24 @@ The PaddleDetection team provides configs and weights of various feature detecti
### Training ### Training
Training PP-YOLOE with mixed precision on 8 GPUs with following command Training PP-YOLOE+ on 8 GPUs with following command
```bash ```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:** **Notes:**
- use `--amp` to train with default config to avoid out of memeory. - 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). - PaddleDetection supports multi-machine distribued training, you can refer to [DistributedTraining tutorial](../../docs/DistributedTraining_en.md).
### Evaluation ### 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 ```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`. 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 ...@@ -95,39 +103,39 @@ Inference images in single GPU with following commands, use `--infer_img` to inf
```bash ```bash
# inference single image # 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 # 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 ### Exporting models
For deployment on GPU or speed testing, model should be first exported to inference model using `tools/export_model.py`. 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 ```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 ```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). 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 ```bash
# export inference model # 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 # install paddle2onnx
pip install paddle2onnx pip install paddle2onnx
# convert to onnx # 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 ...@@ -141,20 +149,20 @@ For fair comparison, the speed in [Model Zoo](#Model-Zoo) do not contains the ti
```bash ```bash
# export inference model # 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 # 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 **Using Paddle Inference with TensorRT** to test speed, run following command
```bash ```bash
# export inference model with trt=True # 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 # 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 ...@@ -162,16 +170,16 @@ CUDA_VISIBLE_DEVICES=0 python deploy/python/infer.py --model_dir=output_inferenc
```bash ```bash
# export inference model with trt=True # 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 # 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 # 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 # 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, # 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 ...@@ -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. Then, Exporting PP-YOLOE for Paddle Inference **with TensorRT**, use following command.
```bash ```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. Finally, inference in TensorRT FP16 mode.
```bash ```bash
# inference single image # 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 # 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
``` ```
......
configs/ppyoloe/README_cn.md
浏览文件 @ 8c790b97
...@@ -2,6 +2,15 @@ ...@@ -2,6 +2,15 @@
# PP-YOLOE # 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 ## 内容
- [简介](#简介) - [简介](#简介)
- [模型库](#模型库) - [模型库](#模型库)
...@@ -12,10 +21,10 @@ ...@@ -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)。
<div align="center"> <div align="center">
<img src="../../docs/images/ppyoloe_map_fps.png" width=500 /> <img src="../../docs/images/ppyoloe_plus_map_fps.png" width=500 />
</div> </div>
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 PP-YOLOE由以下方法组成
- 可扩展的backbone和neck - 可扩展的backbone和neck
...@@ -24,23 +33,21 @@ PP-YOLOE由以下方法组成 ...@@ -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) - [SiLU(Swish)激活函数](https://arxiv.org/abs/1710.05941)
## 模型库 ## 模型库
| 模型 | Epoch | GPU个数 | 每GPU图片个数 | 骨干网络 | 输入尺寸 | Box AP<sup>val<br>0.5:0.95 | Box AP<sup>test<br>0.5:0.95 | Params(M) | FLOPs(G) | V100 FP32(FPS) | V100 TensorRT FP16(FPS) | 模型下载 | 配置文件 | | 模型 | Epoch | GPU个数 | 每GPU图片个数 | 骨干网络 | 输入尺寸 | Box AP<sup>val<br>0.5:0.95 | Box AP<sup>test<br>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 | 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-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 | 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-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 | 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-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 | 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) |
| 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) |
### 综合指标 ### 综合指标
| 模型 | Epoch | AP<sup>0.5:0.95 | AP<sup>0.5 | AP<sup>0.75 | AP<sup>small | AP<sup>medium | AP<sup>large | AR<sup>small | AR<sup>medium | AR<sup>large | 模型下载 | 配置文件 | | 模型 | Epoch | AP<sup>0.5:0.95 | AP<sup>0.5 | AP<sup>0.75 | AP<sup>small | AP<sup>medium | AP<sup>large | AR<sup>small | AR<sup>medium | AR<sup>large |
|:----------------------:|:-----:|:---------------:|:----------:|:-------------:| :------------:| :-----------: | :----------: |:------------:|:-------------:|:------------:| :-----: | :-----: | |:------------------------:|:-----:|:---------------:|:----------:|:-----------:|:------------:|:-------------:|:------------:|:------------:|:-------------:|:------------:|
| 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 | 80 | 43.7 | 60.6 | 47.9 | 26.5 | 47.5 | 59.0 | 46.7 | 71.4 | 81.7 |
| 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 | 80 | 49.8 | 67.1 | 54.5 | 31.8 | 53.9 | 66.2 | 53.3 | 75.0 | 84.6 |
| 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 | 80 | 52.9 | 70.1 | 57.9 | 35.2 | 57.5 | 69.1 | 56.0 | 77.9 | 86.9 |
| 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 | 80 | 54.7 | 72.0 | 59.9 | 37.9 | 59.3 | 70.4 | 57.0 | 78.7 | 87.2 |
| 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)|
**注意:** **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 ...@@ -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 ### 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 ```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:** **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). - PaddleDetection支持多机训练，可以参考[多机训练教程](../../docs/DistributedTraining_cn.md).
### 评估 ### 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 ...@@ -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 执行以下命令在单个GPU上评估COCO val2017数据集
```bash ```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`。 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 ...@@ -94,26 +101,26 @@ CUDA_VISIBLE_DEVICES=0 python tools/eval.py -c configs/ppyoloe/ppyoloe_crn_l_300
```bash ```bash
# 推理单张图片 # 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 # 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 ### 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 当你**使用Paddle Inference但不使用TensorRT**时，运行以下的命令导出模型
```bash ```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。 当你**使用Paddle Inference且使用TensorRT**时，需要指定`-o trt=True`来导出模型。
```bash ```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 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 ...@@ -122,13 +129,13 @@ python tools/export_model.py -c configs/ppyoloe/ppyoloe_crn_l_300e_coco.yml -o w
```bash ```bash
# 导出推理模型 # 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 # 安装paddle2onnx
pip install paddle2onnx pip install paddle2onnx
# 转换成onnx格式 # 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 **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 ...@@ -141,20 +148,20 @@ paddle2onnx --model_dir output_inference/ppyoloe_crn_l_300e_coco --model_filenam
```bash ```bash
# 导出模型 # 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 # 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： **使用Paddle Inference且使用TensorRT**进行测速，执行以下命令：
```bash ```bash
# 导出模型，使用trt=True # 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 # 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 ...@@ -163,18 +170,18 @@ CUDA_VISIBLE_DEVICES=0 python deploy/python/infer.py --model_dir=output_inferenc
```bash ```bash
# 导出模型 # 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 # 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 # 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 # 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=1, 2.80ms, 357fps
# batch_size=32, 67.69ms, 472fps # batch_size=32, 67.69ms, 472fps
``` ```
...@@ -196,17 +203,17 @@ PP-YOLOE可以使用以下方式进行部署： ...@@ -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 然后，运行以下命令导出模型
```bash ```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 最后，使用TensorRT FP16进行推理
```bash ```bash
# 推理单张图片 # 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 # 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
``` ```
......
Markdown is supported
0% 或 .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑！
想要评论请 注册 或