- Python – 3.7.3
- Tensorflow – 1.13.1
- Pillow – 6.1.0
- Numpy – 1.18.1
- Matplotlib – 3.1.3
- Scipy – 1.4.1
- H5py – 2.10.0
- Hdf5storage – 0.1.15
- Hdf5 – 1.10.4
- Opencv-python – 4.2.0.32
- ‘parameters’ : Contains different parameters which can be changed to configure the execution environment
- ‘pretrained’ : Contains pretrained cfnet network weights
- ‘src’ : Contains list of procedures for the Siamese FC implementation
- All the initial parameters regarding loading the data, enabling the visualization, loading the pretrained cfnet weights and the hyperparameters have been assigned in the code.
- Run the ‘run_tracker_evaluation_meanshift.py’ file to execute the SiameseFC tracker integrated with the Mean Shift filter.
- Run the ‘run_tracker_evaluation_lucaskanade.py’ file to execute the SiameseFC tracker integrated with the Lucas Kanade algorithm.