search

QVPR / VPRSNN

Code for our IEEE RAL + ICRA 2022 paper "Spiking Neural Networks for Visual Place Recognition via Weighted Neuronal Assignments", and our ICRA2023 paper "Ensembles of Compact, Region-specific & Regularized Spiking Neural Networks for Scalable Place Recognition"
MIT License
40 stars 6 forks source link

Could you release the trained models? #4

Closed YuhangMing closed 7 months ago

YuhangMing commented 7 months ago

Hi @Somayeh-h,

We are really interested in this work and would like to play with it. We would like to know if releasing some trained models is possible. Thanks!

Best, Yuhang

Somayeh-h commented 7 months ago

Hi @YuhangMing,

Thank you for your interest in our work. Yes, we've now made the learned weights of our Modular SNN available. Please see the link below to find the learned weights of our Modular SNN from the Nordland dataset, trained on Spring and Fall traverses (Reference dataset), and calibrated on Summer traverse. The learned weights include the outputs of train, record and calibration processes that is needed for the neuronal assignments, hyperactive neuron detection, and hyperparameter calibration processes. Please see modular_snn/modular_snn_processing.py and modular_snn/modular_snn_evaluation.py files for config information.

Nordland dataset: https://cloudstor.aarnet.edu.au/plus/s/2LtwUtLUFpUiUC8 Modular SNN learned weights: https://drive.google.com/drive/u/1/folders/1Qwp3h6D1s2CMLXisAUDVGN1Z9EOAQbwA

Please let me know if you encounter any access issues with the links provided above.

Best, Somayeh