🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Models and examples built with TensorFlow

scikit-learn: machine learning in Python

TensorFlow code and pre-trained models for BERT

A toolkit for developing and comparing reinforcement learning algorithms.

Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow

The interactive graphing library for Python ✨

Datasets, Transforms and Models specific to Computer Vision

Library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.

Image augmentation for machine learning experiments.

A flexible tool for creating, organizing, and sharing visualizations of live, rich data. Supports Torch and Numpy.

A Python Library for Outlier and Anomaly Detection, Integrating Classical and Deep Learning Techniques

A PyTorch implementation of the Transformer model in "Attention is All You Need".

AutoML library for deep learning

Pretrained ConvNets for pytorch: NASNet, ResNeXt, ResNet, InceptionV4, InceptionResnetV2, Xception, DPN, etc.

Anomaly detection related books, papers, videos, and toolboxes

A Python implementation of global optimization with gaussian processes.

tensorboard for pytorch (and chainer, mxnet, numpy, ...)

Distributed Asynchronous Hyperparameter Optimization in Python

Keras code and weights files for popular deep learning models.

A Python Package to Tackle the Curse of Imbalanced Datasets in Machine Learning

Image augmentation library in Python for machine learning.

A library of extension and helper modules for Python's data analysis and machine learning libraries.

Automated CI toolchain to produce precompiled opencv-python, opencv-python-headless, opencv-contrib-python and opencv-contrib-python-headless packages.

High-level library to help with training and evaluating neural networks in PyTorch flexibly and transparently.

Visual analysis and diagnostic tools to facilitate machine learning model selection.

Manipulation and analysis of geometric objects

Sequential model-based optimization with a `scipy.optimize` interface

PyTorch implementation of "Efficient Neural Architecture Search via Parameters Sharing"

The friendly PIL fork