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

RobustVideoMatting Python Deployment Example

Before deployment, two steps require confirmation

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

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

# Download RobustVideoMatting model files, test images and videos
## Original ONNX Model
wget https://bj.bcebos.com/paddlehub/fastdeploy/rvm_mobilenetv3_fp32.onnx
## Specially process the ONNX model for loading TRT
wget https://bj.bcebos.com/paddlehub/fastdeploy/rvm_mobilenetv3_trt.onnx
wget https://bj.bcebos.com/paddlehub/fastdeploy/matting_input.jpg
wget https://bj.bcebos.com/paddlehub/fastdeploy/matting_bgr.jpg
wget https://bj.bcebos.com/paddlehub/fastdeploy/video.mp4

# CPU inference
## image
python infer.py --model rvm_mobilenetv3_fp32.onnx --image matting_input.jpg --bg matting_bgr.jpg --device cpu
## video
python infer.py --model rvm_mobilenetv3_fp32.onnx --video video.mp4 --bg matting_bgr.jpg --device cpu
# GPU inference
## image
python infer.py --model rvm_mobilenetv3_fp32.onnx --image matting_input.jpg --bg matting_bgr.jpg --device gpu
## video
python infer.py --model rvm_mobilenetv3_fp32.onnx --video video.mp4 --bg matting_bgr.jpg --device gpu
# TRT inference
## image
python infer.py --model rvm_mobilenetv3_trt.onnx --image matting_input.jpg --bg matting_bgr.jpg --device gpu --use_trt True
## video
python infer.py --model rvm_mobilenetv3_trt.onnx --video video.mp4 --bg matting_bgr.jpg --device gpu --use_trt True

The visualized result after running is as follows

RobustVideoMatting Python Interface

fd.vision.matting.RobustVideoMatting(model_file, params_file=None, runtime_option=None, model_format=ModelFormat.ONNX)

RobustVideoMatting 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

RobustVideoMatting.predict(input_image)

Model prediction interface. Input images and output matting results.

Parameter

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

Return

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

Other Documents