English | [简体中文](README_CN.md)
# BlazeFace Python Deployment Example

Before deployment, two steps require confirmation

- 1. Software and hardware should meet the requirements. Please refer to [FastDeploy Environment Requirements](../../../../../docs/en/build_and_install/download_prebuilt_libraries.md)  
- 2. Install FastDeploy Python whl package. Refer to [FastDeploy Python Installation](../../../../../docs/en/build_and_install/download_prebuilt_libraries.md)

This directory provides examples that `infer.py` fast finishes the deployment of BlazeFace on CPU/GPU.

```bash
# Download the example code for deployment
git clone https://github.com/PaddlePaddle/FastDeploy.git
cd examples/vision/facedet/blazeface/python/

# Download BlazeFace model files and test images
wget https://raw.githubusercontent.com/DefTruth/lite.ai.toolkit/main/examples/lite/resources/test_lite_face_detector_3.jpg
wget https://bj.bcebos.com/paddlehub/fastdeploy/blazeface-1000e.tgz

# Use blazeface-1000e model
# CPU Inference
python infer.py --model blazeface-1000e/ --image test_lite_face_detector_3.jpg --device cpu
# GPU Inference
python infer.py --model blazeface-1000e/ --image test_lite_face_detector_3.jpg --device gpu
```

The visualized result after running is as follows

<img width="640" src="https://user-images.githubusercontent.com/67993288/184301839-a29aefae-16c9-4196-bf9d-9c6cf694f02d.jpg">

## BlazeFace Python Interface

```python
fastdeploy.vision.facedet.BlzaeFace(model_file, params_file=None, runtime_option=None, config_file=None, model_format=ModelFormat.PADDLE)
```

BlazeFace model loading and initialization, among which model_file is the exported PADDLE model format

**Parameter**

> * **model_file**(str): Model file path
> * **params_file**(str): Parameter file path. No need to set when the model is in PADDLE format
> * **config_file**(str): config file path. No need to set when the model is in PADDLE format
> * **runtime_option**(RuntimeOption): Backend inference configuration. None by default, which is the default configuration
> * **model_format**(ModelFormat):  Model format. PADDLE format by default

### predict function

> ```python
> BlazeFace.predict(input_image)
> ```
> Through let BlazeFace.postprocessor.conf_threshold = 0.2，to modify conf_threshold
>
> Model prediction interface. Input images and output detection results.
>
> **Parameter**
>
> > * **input_image**(np.ndarray): Input image in HWC or BGR format

> **Return**
>
> > Return`fastdeploy.vision.FaceDetectionResult` structure. Refer to [Vision Model Prediction Results](../../../../../docs/api/vision_results/) for its description.

## Other Documents

- [BlazeFace Model Description](..)
- [BlazeFace C++ Deployment](../cpp)
- [Model Prediction Results](../../../../../docs/api/vision_results/)