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

PP-Tracking Python Deployment Example

Before deployment, two steps require confirmation

This directory provides examples that infer.py fast finishesshes the deployment of PP-Tracking 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/tracking/pptracking/python

# Download PP-Tracking model files and test videos
wget https://bj.bcebos.com/paddlehub/fastdeploy/fairmot_hrnetv2_w18_dlafpn_30e_576x320.tgz
tar -xvf fairmot_hrnetv2_w18_dlafpn_30e_576x320.tgz
wget https://bj.bcebos.com/paddlehub/fastdeploy/person.mp4
# CPU inference
python infer.py --model fairmot_hrnetv2_w18_dlafpn_30e_576x320 --video person.mp4 --device cpu
# GPU inference
python infer.py --model fairmot_hrnetv2_w18_dlafpn_30e_576x320 --video person.mp4  --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 fairmot_hrnetv2_w18_dlafpn_30e_576x320 --video person.mp4  --device gpu --use_trt True

PP-Tracking Python Interface

fd.vision.tracking.PPTracking(model_file, params_file, config_file, runtime_option=None, model_format=ModelFormat.PADDLE)

PP-Tracking model loading and initialization, among which model_file, params_file, and config_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
  • config_file(str): Inference deployment configuration file
  • 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

PPTracking.predict(frame)

Model prediction interface. Input images and output detection results.

Parameter

  • frame(np.ndarray): Input data in HWC or BGR format. The video frame is obtained through: _,frame=cap.read()

Return

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

Class Member Variable

Pre-processing Parameter

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

Other Documents