/py-CFNet

Python (Tensorflow) implementation of CFNet tracker

Primary LanguagePython

py-CFNet

Python (Tensorflow) implementation of CFNet tracker

Settings things up with virtualenv

  1. Get virtualenv if you don't have it already pip install virtualenv
  2. Create new virtualenv with Python 2.7 virtualenv --python=/usr/bin/python2.7 ve-tracking
  3. Activate the virtualenv source ~/ve-tracking/bin/activate
  4. Clone the repository https://github.com/Wenju-Huang/py-CFNet.git
  5. cd py-CFNet
  6. Install the required packages sudo pip install -r requirements.txt
  7. mkdir pretrained data
  8. Download the pretrained networks in pretrained and unzip the archive

Running the tracker

  1. Set root_dataset in parameters/environment.json to the root path of your evaluation dataset (don't include the dataset name)
  2. Set dataset in parameters/evaluation.json to the name your evaluation dataset (e.g. "CVPR2013")
  3. Set video in parameters/evaluation.json to "all" or to a specific sequence (e.g. "vot2016_ball1")
  4. See if you are happy with the default parameters in parameters/hyperparameters.json
  5. Select the model you want to run at line 18 in python run_tracker_evaluation.py (default is 'conv2')
  6. Call the main script (within an active virtualenv session) python run_tracker_evaluation.py

Results

CFNetet-Conv2--OTB2013: Precision (20 px): 73.83 -- Success AUC: 0.55 -- FPS: 42.97 FPS

Acknowledgments

Many parts of this code are adopted from the related works siamfc-tf