Scanning all new published packages on PyPI I know that the quality is often quite bad. I try to filter out the worst ones and list here the ones which might be worth a look, being followed or inspire you in some way.

• neuraxle-tensorflow
TensorFlow steps, savers, and utilities for Neuraxle. Neuraxle is a Machine Learning (ML) library for building neat pipelines, providing the right abstractions to both ease research, development, and deployment of your ML applications.

• pdfner
Information extraction and named-entity recognition for indexing PDFs

• plaidml2-keras
PlaidML Keras backend implementation

• renku-r-tools
A toolbox to work with R projects on Renku

• rsgt
Implementaton of random smooth grayvalue transformations for training grayvalue independent neural networks

• soldai-utils
Soldai utilities for machine learning and text processing. This repository contains a set of tools to deal with machine learning and natural language processing tasks, including classes to make quick experimentation of different classifacation models.

• soldai-utils-maxsob86
Soldai utilities for machine learning and text processing. This repository contains a set of tools to deal with machine learning and natural language processing tasks, including classes to make quick experimentation of different classifacation models.

• bentley-ottmann
Bentley-Ottmann algorithm for searching line segments intersections.

• ComputationalGraphPrimer
An educational module meant to serve as a prelude to talking about automatic differentiation in deep learning frameworks (such as in the Autograd module of PyTorch)

• coriander
A simple library for intent classification and named-entity recognition using templates.

• deeSOM
Deep ensemble-elastic self-organized map (deesom): a SOM based classifier to deal with large and highly imbalanced data.

• experiment-ltt
Experimentation toolbox