The results of all tested classic machine learning approaches can be found in results.xlsx.
Test script for neural network based non-BIT models can be found in NN/test_nonBIT.py To test neural network based BIT models please follow the original codes:
https://github.com/google-research/big_transfer
Pre-trained models can be found at:
https://drive.google.com/drive/folders/1joNbyYU_lSVU4XTbcNrRMPi4lYjIn9CL?usp=sharing
Exemplary code for neural network training can be found in NN/Train_nonBIT.py
Other supplementary materials for classic machine learning approach can be found at:
https://drive.google.com/drive/folders/1GgMLRTARCbLOXYlHIEJ4V0ipc3u4gEfk?usp=sharing
If you find our research useful, please consider to cite the following related paper:
Neduchal, Petr, Ivan Gruber, and Miloš Železný.
"Indoor vs. Outdoor Scene Classification for Mobile Robots."
International Conference on Interactive Collaborative Robotics.
Springer, Cham, 2020.
This work was supported by the Ministry of Education of the Czech Republic, project No. LTARF18017.
Access to computing and storage facilities owned by parties and projects contributing to the National Grid Infrastructure MetaCentrum provided under the programme "Projects of Large Research, Development, and Innovations Infrastructures" (CESNET LM2015042), is greatly appreciated.}