Skip to content

Latest commit

 

History

History
32 lines (14 loc) · 478 Bytes

README.md

File metadata and controls

32 lines (14 loc) · 478 Bytes

DANet

This is our implementation for the paper:

DANet: Deformable Attentive Network for Deep Reinforcement Tracking Approach

Environments

  • python 3.8
  • pytorch 1.4.0
  • ninja 1.9.0
  • numpy 1.18.1

Example to run the codes

The implemention of data preprocessing is modified based on this

Run our tracker:

python run_tracker.py atom default --dataset otb --sequence Basketball --debug 1 --threads 0