This code has been tested on windows 10, Python 3.7.9, Pytorch 1.7.0, CUDA 10.0. Please install related libraries before running this code:

pip install -r requirements.txt

Download the pretrained model and put them into tools/snapshot directory.
From BaiduYun:

• SiamMSS extract code: k9vh
• our_train_baseline extract code: gcvw
• baseline

If you want to test the tracker on a new dataset, please refer to pysot-toolkit to set test_dataset.

The tracking result can be download from BaiduYun (extract code: 50fq) for comparision.

python testTracker.py \    
        --config ../experiments/siamsmm_googlenet/config.yaml \
	--dataset LSOTB \                                 # dataset_name
	--snapshot snapshot/siamsmm.pth              # tracker_name

The testing result will be saved in the results/dataset_name/tracker_name directory.

Download the datasets：

• LSOTB
• GOT-10K

Note: training_dataset/dataset_name/readme.md has listed detailed operations about how to generate training datasets.

Download pretrained backbones from link and put them into pretrained_models directory.

To train the SiamSMM model, run train.py with the desired configs:

cd tools
python train.py

The code is implemented based on pysot and SiamGAT. We would like to express our sincere thanks to the contributors.