Update evaluation function to support calculate average inference time (#106)

* Update README.md

* Update README.md

* Update README.md

* Create README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Add evaluation calculate time and fix some bugs

* Update classification __init__

* Move to ppseg

Co-authored-by: Jason <jiangjiajun@baidu.com>
This commit is contained in:
huangjianhui
2022-08-12 17:42:09 +08:00
committed by GitHub
parent 724d3dfc85
commit 32047016d6
12 changed files with 124 additions and 62 deletions

View File

@@ -2,25 +2,53 @@
## 模型版本说明
- [PaddleClas Release/2.4](https://github.com/PaddlePaddle/PaddleClas)
- [PaddleClas Release/2.4](https://github.com/PaddlePaddle/PaddleClas/tree/release/2.4)
目前FastDeploy支持如下模型的部署
- [PP-LCNet系列模型](https://github.com/PaddlePaddle/PaddleClas/blob/release/2.4/docs/zh_CN/models/PP-LCNet.md)
- [PP-LCNetV2系列模型](https://github.com/PaddlePaddle/PaddleClas/blob/release/2.4/docs/zh_CN/models/PP-LCNetV2.md)
- [EfficientNet系列模型](https://github.com/PaddlePaddle/PaddleClas/blob/release/2.4/docs/zh_CN/models/EfficientNet_and_ResNeXt101_wsl.md)
- [GhostNet系列模型](https://github.com/PaddlePaddle/PaddleClas/blob/release/2.4/docs/zh_CN/models/Mobile.md)
- [MobileNet系列模型(包含v1,v2,v3)](https://github.com/PaddlePaddle/PaddleClas/blob/release/2.4/docs/zh_CN/models/Mobile.md)
- [ShuffleNet系列模型](https://github.com/PaddlePaddle/PaddleClas/blob/release/2.4/docs/zh_CN/models/Mobile.md)
- [SqueezeNet系列模型](https://github.com/PaddlePaddle/PaddleClas/blob/release/2.4/docs/zh_CN/models/Others.md)
- [Inception系列模型](https://github.com/PaddlePaddle/PaddleClas/blob/release/2.4/docs/zh_CN/models/Inception.md)
- [PP-HGNet系列模型](https://github.com/PaddlePaddle/PaddleClas/blob/release/2.4/docs/zh_CN/models/PP-HGNet.md)
- [ResNet系列模型包含vd系列](https://github.com/PaddlePaddle/PaddleClas/blob/develop/docs/zh_CN/models/ResNet_and_vd.md)
## 准备PaddleClas部署模型
PaddleClas模型导出请参考其文档说明[模型导出](https://github.com/PaddlePaddle/PaddleClas/blob/release/2.4/docs/zh_CN/inference_deployment/export_model.md#2-%E5%88%86%E7%B1%BB%E6%A8%A1%E5%9E%8B%E5%AF%BC%E5%87%BA)
注意PaddleClas导出的模型仅包含`inference.pdmodel``inference.pdiparams`两个文档,但为了满足部署的需求,同时也需准备其提供的[inference_cls.yaml](https://github.com/PaddlePaddle/PaddleClas/blob/release/2.4/deploy/configs/inference_cls.yaml)文件FastDeploy会从yaml文件中获取模型在推理时需要的预处理信息开发者可直接下载此文件使用。但需根据自己的需求修改yaml文件中的配置参数。
注意PaddleClas导出的模型仅包含`inference.pdmodel``inference.pdiparams`两个文档,但为了满足部署的需求,同时也需准备其提供的通用[inference_cls.yaml](https://github.com/PaddlePaddle/PaddleClas/blob/release/2.4/deploy/configs/inference_cls.yaml)文件FastDeploy会从yaml文件中获取模型在推理时需要的预处理信息开发者可直接下载此文件使用。但需根据自己的需求修改yaml文件中的配置参数具体可比照PaddleClas模型训练[config](https://github.com/PaddlePaddle/PaddleClas/tree/release/2.4/ppcls/configs/ImageNet)中的infer部分的配置信息进行修改
## 下载预训练模型
为了方便开发者的测试下面提供了PaddleClas导出的部分模型含inference_cls.yaml文件开发者可直接下载使用。
| 模型 | 大小 |输入Shape | 精度 |
|:---------------------------------------------------------------- |:----- |:----- | :----- |
| [PPLCNet]() | 141MB | 224x224 |51.4% |
| [PPLCNetv2]() | 10MB | 224x224 |51.4% |
| [EfficientNet]() | | 224x224 | |
| 模型 | 参数文件大小 |输入Shape | Top1 | Top5 |
|:---------------------------------------------------------------- |:----- |:----- | :----- | :----- |
| [PPLCNet_x1_0](https://bj.bcebos.com/paddlehub/fastdeploy/PPLCNet_x1_0_infer.tgz) | 12MB | 224x224 |71.32% | 90.03% |
| [PPLCNetV2_base](https://bj.bcebos.com/paddlehub/fastdeploy/PPLCNetV2_base_infer.tgz) | 26MB | 224x224 |77.04% | 93.27% |
| [EfficientNetB7](https://bj.bcebos.com/paddlehub/fastdeploy/EfficientNetB7_infer.tgz) | 255MB | 600x600 | 84.3% | 96.9% |
| [EfficientNetB0_small](https://bj.bcebos.com/paddlehub/fastdeploy/EfficientNetB0_small_infer.tgz)| 18MB | 224x224 | 75.8% | 75.8% |
| [GhostNet_x1_3_ssld](https://bj.bcebos.com/paddlehub/fastdeploy/GhostNet_x1_3_ssld_infer.tgz) | 29MB | 224x224 | 75.7% | 92.5% |
| [GhostNet_x0_5_ssld](https://bj.bcebos.com/paddlehub/fastdeploy/GhostNet_x0_5_infer.tgz) | 10MB | 224x224 | 66.8% | 86.9% |
| [MobileNetV1_x0_25](https://bj.bcebos.com/paddlehub/fastdeploy/MobileNetV1_x0_25_infer.tgz) | 1.9MB | 224x224 | 51.4% | 75.5% |
| [MobileNetV1_ssld](https://bj.bcebos.com/paddlehub/fastdeploy/MobileNetV1_ssld_infer.tgz) | 17MB | 224x224 | 77.9% | 93.9% |
| [MobileNetV2_x0_25](https://bj.bcebos.com/paddlehub/fastdeploy/MobileNetV2_x0_25_infer.tgz) | 5.9MB | 224x224 | 53.2% | 76.5% |
| [MobileNetV2_ssld](https://bj.bcebos.com/paddlehub/fastdeploy/MobileNetV2_ssld_infer.tgz) | 14MB | 224x224 | 76.74% | 93.39% |
| [MobileNetV3_small_x0_35_ssld](https://bj.bcebos.com/paddlehub/fastdeploy/MobileNetV3_small_x0_35_ssld_infer.tgz) | 6.4MB | 224x224 | 55.55% | 77.71% |
| [MobileNetV3_large_x1_0_ssld](https://bj.bcebos.com/paddlehub/fastdeploy/MobileNetV3_large_x1_0_ssld_infer.tgz) | 22MB | 224x224 | 78.96% | 94.48% |
| [ShuffleNetV2_x0_25](https://bj.bcebos.com/paddlehub/fastdeploy/ShuffleNetV2_x0_25_infer.tgz) | 2.4MB | 224x224 | 49.9% | 73.79% |
| [ShuffleNetV2_x2_0](https://bj.bcebos.com/paddlehub/fastdeploy/ShuffleNetV2_x2_0_infer.tgz) | 29MB | 224x224 | 73.15% | 91.2% |
| [SqueezeNet1_1](https://bj.bcebos.com/paddlehub/fastdeploy/SqueezeNet1_1_infer.tgz) | 4.8MB | 224x224 | 60.1% | 81.9% |
| [InceptionV3](https://bj.bcebos.com/paddlehub/fastdeploy/InceptionV3_infer.tgz) | 92MB | 299x299 | 79.14% | 94.59% |
| [PPHGNet_tiny_ssld](https://bj.bcebos.com/paddlehub/fastdeploy/PPHGNet_tiny_ssld_infer.tgz) | 57MB | 224x224 | 81.95% | 96.12% |
| [PPHGNet_base_ssld](https://bj.bcebos.com/paddlehub/fastdeploy/PPHGNet_base_ssld_infer.tgz) | 274MB | 224x224 | 85.0% | 97.35% |
| [ResNet50_vd](https://bj.bcebos.com/paddlehub/fastdeploy/ResNet50_vd_infer.tgz) | 98MB | 224x224 | 79.12% | 94.44% |
## 详细部署文档

View File

@@ -5,67 +5,71 @@
- 1. 软硬件环境满足要求,参考[FastDeploy环境要求](../../../../../docs/quick_start/requirements.md)
- 2. FastDeploy Python whl包安装参考[FastDeploy Python安装](../../../../../docs/quick_start/install.md)
本目录下提供`infer.py`快速完成YOLOv7在CPU/GPU以及GPU上通过TensorRT加速部署的示例。执行如下脚本即可完成
本目录下提供`infer.py`快速完成ResNet50_vd在CPU/GPU以及GPU上通过TensorRT加速部署的示例。执行如下脚本即可完成
```
# 下载yolov7模型文件和测试图片
wget https://bj.bcebos.com/paddlehub/fastdeploy/yolov7.onnx
wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
# 下载ResNet50_vd模型文件和测试图片
wget https://bj.bcebos.com/paddlehub/fastdeploy/ResNet50_vd_infer.tgz
tar -xvf ResNet50_vd_infer.tgz
wget https://gitee.com/paddlepaddle/PaddleClas/raw/release/2.4/deploy/images/ImageNet/ILSVRC2012_val_00000010.jpeg
#下载部署示例代码
git clone https://github.com/PaddlePaddle/FastDeploy.git
cd examples/vison/detection/yolov7/python/
cd examples/vision/classification/paddleclas/python
# CPU推理
python infer.py --model yolov7.onnx --image 000000087038.jpg --device cpu
python infer.py --model ResNet50_vd_infer --image ILSVRC2012_val_00000010.jpeg --device cpu
# GPU推理
python infer.py --model yolov7.onnx --image 000000087038.jpg --device gpu
python infer.py --model ResNet50_vd_infer --image ILSVRC2012_val_00000010.jpeg --device gpu
# GPU上使用TensorRT推理 注意TensorRT推理第一次运行有序列化模型的操作有一定耗时需要耐心等待
python infer.py --model yolov7.onnx --image 000000087038.jpg --device gpu --use_trt True
python infer.py --model ResNet50_vd_infer --image ILSVRC2012_val_00000010.jpeg --device gpu --use_trt True
```
运行完成可视化结果如下所示
## YOLOv7 Python接口
运行完成后返回结果如下所示
```
fastdeploy.vision.detection.YOLOv7(model_file, params_file=None, runtime_option=None, model_format=Frontend.ONNX)
ClassifyResult(
label_ids: 153,
scores: 0.686229,
)
```
YOLOv7模型加载和初始化其中model_file为导出的ONNX模型格式
## PaddleClasModel Python接口
```
fd.vision.classification.PaddleClasModel(model_file, params_file, config_file, runtime_option=None, model_format=Frontend.PADDLE)
```
PaddleClas模型加载和初始化其中model_file, params_file为训练模型导出的Paddle inference文件具体请参考其文档说明[模型导出](https://github.com/PaddlePaddle/PaddleClas/blob/release/2.4/docs/zh_CN/inference_deployment/export_model.md#2-%E5%88%86%E7%B1%BB%E6%A8%A1%E5%9E%8B%E5%AF%BC%E5%87%BA)
**参数**
> * **model_file**(str): 模型文件路径
> * **params_file**(str): 参数文件路径当模型格式为ONNX格式时此参数无需设定
> * **params_file**(str): 参数文件路径
> * **config_file**(str): 推理部署配置文件
> * **runtime_option**(RuntimeOption): 后端推理配置默认为None即采用默认配置
> * **model_format**(Frontend): 模型格式,默认为ONNX
> * **model_format**(Frontend): 模型格式,默认为Paddle格式
### predict函数
> ```
> YOLOv7.predict(image_data, conf_threshold=0.25, nms_iou_threshold=0.5)
> PaddleClasModel.predict(input_image, topk=1)
> ```
>
> 模型预测结口,输入图像直接输出检测结果。
>
> **参数**
>
> > * **image_data**(np.ndarray): 输入数据注意需为HWCBGR格式
> > * **conf_threshold**(float): 检测框置信度过滤阈值
> > * **nms_iou_threshold**(float): NMS处理过程中iou阈值
> > * **input_image**(np.ndarray): 输入数据注意需为HWCBGR格式
> > * **topk**(int):返回预测概率最高的topk个分类结果
> **返回**
>
> > 返回`fastdeploy.vision.DetectionResult`结构体,结构体说明参考文档[视觉模型预测结果](../../../../../docs/api/vision_results/)
> > 返回`fastdeploy.vision.ClassifyResult`结构体,结构体说明参考文档[视觉模型预测结果](../../../../../docs/api/vision_results/)
### 类成员属性
> > * **size**(list | tuple): 通过此参数修改预处理过程中resize的大小包含两个整型元素表示[width, height], 默认值为[640, 640]
## 其它文档
- [YOLOv7 模型介绍](..)
- [YOLOv7 C++部署](../cpp)
- [PaddleClas 模型介绍](..)
- [PaddleClas C++部署](../cpp)
- [模型预测结果说明](../../../../../docs/api/vision_results/)