Skip to content

Latest commit

 

History

History
 
 

python

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
README.md
README.md
 
 
README_CN.md
README_CN.md
 
 
infer.py
infer.py
 
 

README.md

English | 简体中文

MODNet Python Deployment Example

Before deployment, two steps require confirmation

This directory provides examples that infer.py fast finishes the deployment of MODNet on CPU/GPU and GPU accelerated by TensorRT. The script is as follows

# Download the example code for deployment
git clone https://github.com/PaddlePaddle/FastDeploy.git
cd examples/vision/matting/modnet/python/

# Download modnet model files and test images
wget https://bj.bcebos.com/paddlehub/fastdeploy/modnet_photographic_portrait_matting.onnx
wget https://bj.bcebos.com/paddlehub/fastdeploy/matting_input.jpg
wget https://bj.bcebos.com/paddlehub/fastdeploy/matting_bgr.jpg

# CPU inference
python infer.py --model modnet_photographic_portrait_matting.onnx --image matting_input.jpg --bg matting_bgr.jpg --device cpu
# GPU inference
python infer.py --model modnet_photographic_portrait_matting.onnx --image matting_input.jpg --bg matting_bgr.jpg --device gpu
# TensorRT inference on GPU 
python infer.py --model modnet_photographic_portrait_matting.onnx --image matting_input.jpg --bg matting_bgr.jpg --device gpu --use_trt True

The visualized result after running is as follows

MODNet Python Interface

fastdeploy.vision.matting.MODNet(model_file, params_file=None, runtime_option=None, model_format=ModelFormat.ONNX)

MODNet model loading and initialization, among which model_file is the exported ONNX model format

Parameter

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

predict function

MODNet.predict(image_data)

Model prediction interface. Input images and output matting results.

Parameter

  • image_data(np.ndarray): Input data in HWC or BGR format

Return

Return fastdeploy.vision.MattingResult structure. Refer to Vision Model Prediction Results for its description.

Class Member Property

Pre-processing Parameter

Users can modify the following pre-processing parameters to their needs, which affects the final inference and deployment results

  • size(list[int]): This parameter changes the size of the resize during preprocessing, containing two integer elements for [width, height] with default value [256, 256]
  • alpha(list[float]): Preprocess normalized alpha, and calculated as x'=x*alpha+beta. alpha defaults to [1. / 127.5, 1.f / 127.5, 1. / 127.5]
  • beta(list[float]): Preprocess normalized beta, and calculated as x'=x*alpha+beta. beta defaults to [-1.f, -1.f, -1.f]
  • swap_rb(bool): Whether to convert BGR to RGB in pre-processing. Default True

Other Documents