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

EDVR Python Deployment Example

Before deployment, two steps require confirmation

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

# Download deployment example code 
git clone https://github.com/PaddlePaddle/FastDeploy.git
cd FastDeploy/examples/vision/sr/edvr/python

# Download VSR model files and test videos
wget https://bj.bcebos.com/paddlehub/fastdeploy/EDVR_M_wo_tsa_SRx4.tar
tar -xvf EDVR_M_wo_tsa_SRx4.tar
wget https://bj.bcebos.com/paddlehub/fastdeploy/vsr_src.mp4
# CPU inference
python infer.py --model EDVR_M_wo_tsa_SRx4 --video vsr_src.mp4 --frame_num 5 --device cpu
# GPU inference
python infer.py --model EDVR_M_wo_tsa_SRx4 --video vsr_src.mp4 --frame_num 5 --device gpu
# TensorRT inference on GPU (Attention: It is somewhat time-consuming for the operation of model serialization when running TensorRT inference for the first time. Please be patient.)
python infer.py --model EDVR_M_wo_tsa_SRx4 --video vsr_src.mp4 --frame_num 5 --device gpu --use_trt True

EDVR Python Interface

fd.vision.sr.EDVR(model_file, params_file, runtime_option=None, model_format=ModelFormat.PADDLE)

EDVR model loading and initialization, among which model_file and params_file are the Paddle inference files exported from the training model. Refer to Model Export for more information

Parameter

  • model_file(str): Model file path
  • params_file(str): Parameter file path
  • 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

EDVR.predict(frames)

Model prediction interface. Input images and output detection results.

Parameter

  • frames(list[np.ndarray]): Input data in HWC or BGR format. Frames are video frame sequences.

Return list[np.ndarray] is the video frame sequence after SR

Other Documents