• en-qai-sm
English multi-task CNN trained on OntoNotes. Assigns context-specific token vectors, POS tags, dependency parse and named entities.

• faircorels
FairCORELS, a modified version of CORELS to build fair and interpretable models. Welcome to FairCorels, a Python library for learning fair and interpretable models using the Certifiably Optimal RulE ListS (CORELS) algorithm!

• flexi-hash-embedding
PyTorch Extension Library of Optimized Scatter Operations. This PyTorch Module hashes and sums variably-sized dictionaries of features into a single fixed-size embedding. Feature keys are hashed, which is ideal for streaming contexts and online-learning such that we don’t have to memorize a mapping between feature keys and indices. Multiple variable-length features are grouped by example and then summed. Feature embeddings are scaled by their values, enabling linear features rather than just one-hot features.

• JLpy-utils-package
Custom methodes for various data science, computer vision, and machine learning operations in python

• kde-gpu
We implemented nadaraya waston kernel density and kernel conditional probability estimator using cuda through cupy. It is much faster than cpu version but it requires GPU with high memory.

• matchzoo-py
Facilitating the design, comparison and sharingof deep text matching models.

• naive-feature-selection
Naive Feature Selection. This package solves the Naive Feature Selection problem described in [the paper](https://…/1905.09884 ).

• pencilbox
A pencilbox for your Jupyter notebooks.

• pyAudioProcessing
Audio processing-feature extraction and building machine learning models from audio data.

• scrolldown
Keep long running notebook in jupyter scrolled to the bottom

• styletransfer
Transfer the style of one image to another using PyTorch

• tf-object-detection
A Thin Wrapper around Tensorflow Object Detection API for Easy Installation and Use. This is a thin wrapper around [Tensorflow Object Detection API](https://…/object_detection ) for easy installation and use. The original [installation procedure](https://…/installation.md ) contains multiple manual steps that make dependency management difficult. This repository creates a pip package that automate the installation so that you can install the API with a single pip install.

• titanfe
titan Data Flow Engine for Python

• trendet
trendet – is a Python package for trend detection on stock time series data

• twodlearn
Easy development of machine learning models