Code Adaption of Satellite Image Time Series Classification with Pixel-Set Encoders and Temporal Self-Attention (CVPR 2020, Oral) for the ML Reproducibility Challenge 2020
Adapted PyTorch implementation of the model presented in "Satellite Image Time Series Classification with Pixel-Set Encoders and Temporal Self-Attention" published ar CVPR 2020.
- The Temporal Attention Encoder is heavily inspired by the works of Vaswani et al. on the Transformer, and this pytorch implementation served as code base for the TAE.py script.
- Credits to github.com/clcarwin/ for the pytorch implementation of the focal loss
- The original implementation https://github.com/VSainteuf/pytorch-psetae