TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems

14 Mar 2016tensorflow/tensorflow

TensorFlow is an interface for expressing machine learning algorithms, and an implementation for executing such algorithms.

DIMENSIONALITY REDUCTION

models

30 Apr 2020tensorflow/models

Models and examples built with TensorFlow

NEURAL ARCHITECTURE SEARCH OBJECT DETECTION

Scikit-learn: Machine Learning in Python

2 Jan 2012scikit-learn/scikit-learn

Scikit-learn is a Python module integrating a wide range of state-of-the-art machine learning algorithms for medium-scale supervised and unsupervised problems.

DIMENSIONALITY REDUCTION MODEL SELECTION

PyTorch: An Imperative Style, High-Performance Deep Learning Library

NeurIPS 2019 pytorch/pytorch

Deep learning frameworks have often focused on either usability or speed, but not both.

Automatic Differentiation in PyTorch

NIPS 2017 2017 pytorch/pytorch

In this article, we describe an automatic differentiation module of PyTorch — a library designed to enable rapid research on machine learning models.

DIMENSIONALITY REDUCTION

Adapting the Tesseract Open Source OCR Engine for Multilingual OCR

ACM 2009 tesseract-ocr/tesseract

We describe efforts to adapt the Tesseract open source OCR engine for multiple scripts and languages.

OPTICAL CHARACTER RECOGNITION TEST RESULTS

transformers

27 Apr 2020huggingface/transformers

🤗Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2. 0.

HUMOR DETECTION SENTENCE EMBEDDING

Caffe: Convolutional Architecture for Fast Feature Embedding

20 Jun 2014BVLC/caffe

The framework is a BSD-licensed C++ library with Python and MATLAB bindings for training and deploying general-purpose convolutional neural networks and other deep models efficiently on commodity architectures.

DIMENSIONALITY REDUCTION

Well-Read Students Learn Better: On the Importance of Pre-training Compact Models

ICLR 2020 google-research/bert

Recent developments in natural language representations have been accompanied by large and expensive models that leverage vast amounts of general-domain text through self-supervised pre-training.

LANGUAGE MODELLING MODEL COMPRESSION SENTIMENT ANALYSIS

detectron

ECCV 2018 facebookresearch/detectron

FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.

OBJECT DETECTION VIDEO CLASSIFICATION