tyyyang / memtrack Goto Github PK

We extend our MemTrack with Distractor Template Canceling mechamism in our journal verison, please check our new method MemDTC. Code is availabe at MemDTC-code

This is the Tensorflow implementation of our MemTrack tracker published in ECCV, 2018. Detailed comparision results can be found in the author's webpage

• Python 3.5 or higher
• Tensorflow 1.2.1 or higher
• CUDA 8.0

Set proper home_path in config.py accordingly in order to proceed the following step. Make sure that you place the tracking data properly according to your path setting.

You can use our pretrained model to test our tracker first.

1. Download the model from the link: GoogleDrive
2. Put the model into directory ./output/models
3. Run python3 demo.py in directory ./tracking

1. Download the ILSRVC data from the official website and extract it to proper place according to the path in config.py.
2. Then run the sh process_data.sh in ./build_tfrecords directory to convert ILSVRC data to tfrecords.
3. Run python3 experiment.py to train the model.

If you find the code is helpful, please cite

@inproceedings{Yang2018,
	author = {Yang, Tianyu and Chan, Antoni B.},
	booktitle = {ECCV},
	title = {{Learning Dynamic Memory Networks for Object
	Tracking}},
	year = {2018}
}