Classification of Household Materials via Spectroscopy
Z. Erickson, N. Luskey, S. Chernova, and C. C. Kemp, "Classification of Household Materials via Spectroscopy", IEEE Robotics and Automation Letters (RA-L), 2019.
Project webpage: https://pwp.gatech.edu/hrl/smm50/
Download the SMM50 dataset
Use the following commands to download and extract the SMM50 dataset.
cd data wget -O smm50.tar.gz https://goo.gl/Xjh6x4 tar -xvzf smm50.tar.gz rm smm50.tar.gz
Running the code
Our models are implemented in Keras with the Tensorflow backend.
Results presented in table I from the paper can be computed using the following.
python learn.py -t 0
Generalization with leave-one-object-out validation results from figures 11 and 12 can be computed using the command below.
python learn.py -t 1
The generalization results with increasing numbers of objects can be recomputed using the command below. This corresponds to figure 14 in the paper.
python learn.py -t 2
Generalization results with everyday objects and a PR2 (figure 15 in the paper) can be computed using the below command.
python learn.py -t 3