got-10k / siamfc

A minimal example (SiamFC in PyTorch) showing how to train and evaluate trackers using GOT-10k toolkit.

SiamFC

A minimal example showing how to train a tracker on GOT-10k/VID and evaluate its performance on GOT-10k as well as 6 other tracking datasets (OTB (2013/2015), VOT (2013~2018), DTB70, TColor128, NfS and UAV123), using the GOT-10k toolkit.

Performance

GOT-10k

Dataset	AO	SR0.50	SR0.75
GOT-10k	0.355	0.390	0.118

The scores are comparable with state-of-the-art results on GOT-10k leaderboard.

OTB / UAV123 / DTB70 / TColor128 / NfS

Dataset	Success Score	Precision Score
OTB2013	0.589	0.781
OTB2015	0.578	0.765
UAV123	0.523	0.731
UAV20L	0.423	0.572
DTB70	0.493	0.731
TColor128	0.510	0.691
NfS (30 fps)	-	-
NfS (240 fps)	0.520	0.624

VOT2018

Dataset	Accuracy	Robustness (unnormalized)
VOT2018	0.502	37.25

Dependencies

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

pip install torch opencv-python got10k

Running the tracker

In the root directory of siamfc:

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

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

ln -s ./data /path/to/your/data/folder

3. Run:

python test.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.

Training the tracker

1. Assume the GOT-10k dataset is located at data/GOT-10K.

2. Run:

python train.py