GammaLearn is a collaborative project to apply deep learning to the analysis of low-level Imaging Atmospheric Cherenkov Telescopes such as CTA.
The project focus both on improving reconstruction performances but also providing an environment for the analysis of CTA data with DL.
- effortless data loading, filtering, augmenting, balancing for DL studies
- multi-process abilities for image pre-processing
- ability to plot features map and convolution kernels
GammaBoard is a dashboard as a notebook app to:
- ease book-keeping and experiment reproducibility
- plot high-level resolution curves
- easy comparison between exeperiments and CTA requirements/performances
Standard convolution in frameworks such as Pytorch or Tensorflow has been developed for Cartesian lattices adapted to pixel grids in standard images. However, in many scientific experiments, sensors are arranged with different lattices. This is also the case for CTA cameras. We developed convolution and pooling kernels to be used in Pytorch in order to be able to apply these operations on any data given that all pixel neighbours are known and provided.
A publication on this work is under preparation.