Skip to content

P
PaddleDetection

PaddlePaddle / PaddleDetection
大约 1 年 前同步成功

通知 695
Star 11112
Fork 2696
P
PaddleDetection
未验证 提交 e3f60e23 编写于 作者: F Feng Ni 提交者： GitHub
浏览文件
操作

[cherry-pick][doc] add Comprehensive Metrics of PPYOLOE (#6306) 

* add Comprehensive Metrics of PPYOLOE, test=document_fix

* add val2017 description of Comprehensive Metrics, test=document_fix

* update readme doc, test=document_fix

* add test mAP, test=document_fix
上级 2dfb9c01
隐藏空白更改
内联 并排
Showing with 73 addition and 12 deletion
configs/ppyoloe/README.md
浏览文件 @ e3f60e23
......@@ -24,21 +24,51 @@ PP-YOLOE is composed of following methods:
- [SiLU activation function](https://arxiv.org/abs/1710.05941)
## Model Zoo
| Model | GPU number | images/GPU | backbone | input shape | Box AP<sup>val</sup> | Box AP<sup>test</sup> | Params(M) | FLOPs(G) | V100 FP32(FPS) | V100 TensorRT FP16(FPS) | download | config |
| Model | 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 | 8 | 32 | cspresnet-s | 640 | 42.7 | 43.1 | 7.93 | 17.36 | 208.3 | 333.3 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_s_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.4/configs/ppyoloe/ppyoloe_crn_s_300e_coco.yml) |
| PP-YOLOE-m | 8 | 28 | cspresnet-m | 640 | 48.6 | 48.9 | 23.43 | 49.91 | 123.4 | 208.3 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_m_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.4/configs/ppyoloe/ppyoloe_crn_m_300e_coco.yml) |
| PP-YOLOE-l | 8 | 20 | cspresnet-l | 640 | 50.9 | 51.4 | 52.20 | 110.07 | 78.1 | 149.2 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.4/configs/ppyoloe/ppyoloe_crn_l_300e_coco.yml) |
| PP-YOLOE-x | 8 | 16 | cspresnet-x | 640 | 51.9 | 52.2 | 98.42 | 206.59 | 45.0 | 95.2 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_x_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.4/configs/ppyoloe/ppyoloe_crn_x_300e_coco.yml) |
| PP-YOLOE-s | 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 | 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 | 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 | 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
| Model | 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 |
|:----------------------:|:---------------:|:----------:|:-------------:| :------------:| :-----------: | :----------: |:------------:|:-------------:|:------------:| :-----: | :-----: |
| PP-YOLOE-s | 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 | 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 | 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 | 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:**
- 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 is trained on COCO train2017 dataset and evaluated on val2017 & test-dev2017 dataset，all the model weights are trained for **300 epoches**.
- The model weights in the table of Comprehensive Metrics are **the same as** that in the original Model Zoo, and evaluated on **val2017**. To reproduce the metrics, just modify the setting of `nms` in [ppyoloe_crn.yml](_base_/ppyoloe_crn.yml):
```
nms:
name: MultiClassNMS
nms_top_k: 10000
keep_top_k: 300
score_threshold: 0.01
nms_threshold: 0.7
```
- 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`.
### Feature Models
The PaddleDetection team provides configs and weights of various feature detection models based on PP-YOLOE, which users can download for use:
|Scenarios | Related Datasets | Links|
| :--------: | :---------: | :------: |
|Pedestrian Detection | CrowdHuman | [pphuman](../pphuman) |
|Vehicle Detection | BDD100K, UA-DETRAC | [ppvehicle](../ppvehicle) |
|Small Object Detection | VisDrone | [visdrone](../visdrone) |
## Getting Start
### Training
......
configs/ppyoloe/README_cn.md
浏览文件 @ e3f60e23
......@@ -24,21 +24,52 @@ PP-YOLOE由以下方法组成
- [SiLU激活函数](https://arxiv.org/abs/1710.05941)
## 模型库
| 模型 | GPU个数 | 每GPU图片个数 | 骨干网络 | 输入尺寸 | Box AP<sup>val</sup> | Box AP<sup>test</sup> | Params(M) | FLOPs(G) | V100 FP32(FPS) | V100 TensorRT FP16(FPS) | 模型下载 | 配置文件 |
| 模型 | 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 | 8 | 32 | cspresnet-s | 640 | 42.7 | 43.1 | 7.93 | 17.36 | 208.3 | 333.3 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_s_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.4/configs/ppyoloe/ppyoloe_crn_s_300e_coco.yml) |
| PP-YOLOE-m | 8 | 28 | cspresnet-m | 640 | 48.6 | 48.9 | 23.43 | 49.91 | 123.4 | 208.3 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_m_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.4/configs/ppyoloe/ppyoloe_crn_m_300e_coco.yml) |
| PP-YOLOE-l | 8 | 20 | cspresnet-l | 640 | 50.9 | 51.4 | 52.20 | 110.07 | 78.1 | 149.2 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.4/configs/ppyoloe/ppyoloe_crn_l_300e_coco.yml) |
| PP-YOLOE-x | 8 | 16 | cspresnet-x | 640 | 51.9 | 52.2 | 98.42 | 206.59 | 45.0 | 95.2 | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_x_300e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.4/configs/ppyoloe/ppyoloe_crn_x_300e_coco.yml) |
| PP-YOLOE-s | 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 | 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 | 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 | 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
| 模型 | 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 |
|:----------------------:|:---------------:|:----------:|:-------------:| :------------:| :-----------: | :----------: |:------------:|:-------------:|:------------:| :-----: | :-----: |
| PP-YOLOE-s | 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 | 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 | 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 | 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:**
- PP-YOLOE模型使用COCO数据集中train2017作为训练集，使用val2017和test-dev2017作为测试集，Box AP<sup>test</sup>为`mAP(IoU=0.5:0.95)`评估结果。
- PP-YOLOE模型使用COCO数据集中train2017作为训练集，使用val2017和test-dev2017作为测试集，模型权重均为训练**300 epoches**得到的。
- 综合指标的表格与模型库的表格里的模型权重是**同一个权重**，综合指标是使用**val2017**作为验证精度的，如果要复现以上表格中的测试结果，只要修改[ppyoloe_crn.yml](_base_/ppyoloe_crn.yml)中的`nms`部分的设置为:
```
nms:
name: MultiClassNMS
nms_top_k: 10000
keep_top_k: 300
score_threshold: 0.01
nms_threshold: 0.7
```
- PP-YOLOE模型训练过程中使用8 GPUs进行混合精度训练，如果**GPU卡数**或者**batch size**发生了改变，你需要按照公式 **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>)** 调整学习率。
- PP-YOLOE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 7.6.5**，TensorRT推理速度测试使用**TensorRT 6.0.1.8**。
- 参考[速度测试](#速度测试)以复现PP-YOLOE推理速度测试结果。
- 如果你设置了`--run_benchmark=True`, 你首先需要安装以下依赖`pip install pynvml psutil GPUtil`。
### 垂类应用模型
PaddleDetection团队提供了基于PP-YOLOE的各种垂类检测模型的配置文件和权重，用户可以下载进行使用：
| 场景 | 相关数据集 | 链接 |
| :--------: | :---------: | :------: |
| 行人检测 | CrowdHuman | [pphuman](../pphuman) |
| 车辆检测 | BDD100K、UA-DETRAC | [ppvehicle](../ppvehicle) |
| 小目标检测 | VisDrone | [visdrone](../visdrone) |
## 使用说明
### 训练
......
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