A clean PyTorch implementation of SiamRPN tracker described in paper High Performance Visual Tracking with Siamese Region Proposal Network. The code is evaluated on 7 tracking datasets (OTB (2013/2015), VOT (2018), DTB70, TColor128, NfS and UAV123), using the GOT-10k toolkit.

The scores surpass the highest performance on GOT-10k leaderboard (AO 0.374, SR_0.50 0.404) by a large margin.

However, since SiamRPN is trained on 4 extra datasets (ILSVRC-VID, YouTube-BB, ImageNet Detection and COCO) and it does not follow the one-shot principle (zero-overlap between training and test object classes) of GOT-10k, the comparison may not be fair.

Install PyTorch, opencv-python and GOT-10k toolkit:

pip install torch
pip install opencv-python
pip install --upgrade git+https://github.com/got-10k/toolkit.git@master

GOT-10k toolkit is a visual tracking toolkit that implements evaluation metrics and tracking pipelines for 7 main datasets (GOT-10k, OTB, VOT, UAV123, NfS, etc.).

In the root directory of siamrpn-pytorch:

1. Download pretrained model.pth from Baidu Yun or Google Drive, and put the file under pretrained/siamrpn.

2. Create a symbolic link data to your datasets folder (e.g., data/OTB, data/UAV123, data/GOT-10k).

3. Run:

python run_tracking.py

By default, the tracking experiments will be executed and evaluated over all 7 datasets. Comment lines in run_tracker.py as you wish if you need to skip some experiments.