Sequence Models Python Packages

crested

CREsted is a Python package for training sequence-based deep learning models on scATAC-seq data, for capturing enhancer code and for designing cell type-specific sequences.

nervaluate

Full named-entity (i.e., not tag/token) evaluation metrics based on SemEval’13

nlp-datasets

A dataset utils repository based on tf.data API.

long-range-models

Simple implementations of long-range sequence models (LRU, S5, S4, and more).

geotorchai

GeoTorchAI: A Framework for Training and Using Spatiotemporal Deep Learning Models at Scale

chlengmo

A fast Character-Level N-Gram Model