dl-4-tsc

Why we included this project

This is the companion repo to a well-known survey on using deep learning for time series classification. It ships the actual code for the architectures the paper reviews, including FCN, ResNet, and a handful of other CNN and RNN models, so you can run them on UCR/UEA datasets with a single command. That combination matters if you want to compare a new method against solid baselines without reimplementing everything yourself. Because the classifiers live as separate modules behind one entry point, swapping a model or dataset for your own experiments is easy. For teams new to the field, the paper plus runnable code gives you both the overview of what works and a place to start building.