Amazing Machine Learning Open Source of the Year (v.2019)

Amazing Machine Learning Open Source of the Year (v.

2019)MybridgeBlockedUnblockFollowFollowingFeb 1For the past year, we’ve compared nearly 22,000 Machine Learning open source tools and projects to pick Top 49 (0.

22% chance).

The tools and projects are broken down by 6 categoriesComputer Vision (1~5)Reinforcement Learning (6~13)NLP (14~20)GAN (21~26)Neural Network (27~35)Toolkit (36~49)This is an extremely competitive list and it carefully picks the best open source Machine Learning projects published between Jan and Dec 2018.

Mybridge AI evaluates the quality by considering popularity, engagement and recency.

To give you an idea about the quality, the average number of Github ⭐️ is 3,566.

Machine Learning Articles of the Year v.

2019: HereMachine Learning Open Source v.

2018 (21K Claps on Medium): HereOpen source projects can be useful for programmers.

Give a plenty of time to play around with Machine Learning open source projects you may have missed for the past year.

<Recommended Learning>A) Beginner: Machine Learning, Data Science and Deep Learning with Python.

TensorFlow & Neural Networks [84,632 recommends, 4.

5/5 stars]B) Advanced: Deep Reinforcement Learning in Python.

[20,396 recommends, 4.

6/5 stars]For text version with Table of Contents: Go to Github(Click the numbers or images below)<Computer Vision>No 1Detectron: FAIRs research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.

[18913 stars on Github].

No 2Openpose: Real-time multi-person keypoint detection library for body, face, and hands estimation [11052 stars on Github].

No 3DensePose: A real-time approach for mapping all human pixels of 2D RGB images to a 3D surface-based model of the body [4165 stars on Github].

No 4Maskrcnn-benchmark: Fast, modular reference implementation of Semantic Segmentation and Object Detection algorithms in PyTorch.

[3888 stars on Github].

No 5SNIPER is an efficient multi-scale object detection algorithm [1963 stars on Github].

<Reinforcement Learning>No 6Psychlab: Experimental paradigms implemented using the Psychlab platform (3D platform for agent-based AI) [5595 stars on Github].

No 7ELF: An Extensive, Lightweight, and Flexible platform for game research.

We have used it to build our Go playing bot, ELF OpenGo, which achieved a 14–0 record versus four global top-30 players [2406 stars on Github].

No 8TRFL: A library of useful building blocks for writing reinforcement learning (RL) agents in TensorFlow [2312 stars on Github].

No 9Horizon: The first open source reinforcement learning platform for large-scale products and services [1703 stars on Github].

No 10Chess-alpha-zero: Chess reinforcement learning by AlphaGo Zero methods.

[1307 stars on Github].

No 11Dm_control: The DeepMind Control Suite and Control Package [1231 stars on Github].

No 12MAMEToolkit: Arcade Game Reinforcement Learning Python Library [437 stars on Github].

No 13Reaver: Reaver: Modular Deep Reinforcement Learning Framework.

Focused on StarCraft II.

Supports Gym, Atari, and MuJoCo.

Matches reference results.

[355 stars on Github].

<NLP>No 14Bert: TensorFlow code and pre-trained models for BERT [11703 stars on Github].

No 15Pytext: A natural language modeling framework based on PyTorch [4466 stars on Github].

No 16Bert-as-service: A NLP model developed by Google for pre-training language representations.

It leverages an enormous amount of plain text data publicly available on the web and is trained in an unsupervised manner.

[2055 stars on Github].

No 17UnsupervisedMT: Phrase-Based & Neural Unsupervised Machine Translation — Facebook Research [1068 stars on Github].

No 18DecaNLP: The Natural Language Decathlon: A Multitask Challenge for NLP — Salesforce [1648 stars on Github].

No 19Nlp-architect: NLP Architect by Intel AI Lab: Python library for exploring the state-of-the-art deep learning topologies and techniques for NLP [1751 stars on Github].

No 20Gluon-nlp: NLP made easy [1263 stars on Github].

<GAN>No 21DeOldify: A Deep Learning based project for colorizing and restoring old images [5060 stars on Github].

No 22Progressive_growing_of_gans: Progressive Growing of GANs for Improved Quality, Stability, and Variation [4046 stars on Github].

No 23MUNIT: Multimodal Unsupervised Image-to-Image Translation [1339 stars on Github].

No 24Transparent_latent_gan: Use supervised learning to illuminate the latent space of GAN for controlled generation and edit [1337 stars on Github].

No 25Gandissect: Pytorch-based tools for visualizing and understanding the neurons of a GAN.

[1065 stars on Github].

No 26GANimation: Anatomically-aware Facial Animation from a Single Image [869 stars on Github].

<Neural Network>No 27Fastai: It simplifies training fast and accurate neural nets using modern best practices [11597 stars on Github].

No 28DeepCreamPy: Decensoring Hentai with Deep Neural Networks [7046 stars on Github].

No 29Augmentor v0.

2: Image augmentation library in Python for machine learning.

[2805 stars on Github].

No 30Graph_nets: Build Graph Nets in Tensorflow [2723 stars on Github].

No 31Textgenrnn: Python module to easily generate text using a pretrained character-based recurrent neural network.

[1900 stars on Github].

No 32Person-blocker: Automatically “block” people in images (like Black Mirror) using a pretrained neural network.

[1806 stars on Github].

No 33Deepvariant: DeepVariant is an analysis pipeline that uses a deep neural network to call genetic variants from next-generation DNA sequencing data.

[1502 stars on Github].

No 34Video-nonlocal-net: Non-local Neural Networks for Video Classification [1049 stars on Github].

No 35Ann-visualizer: A python library for visualizing Artificial Neural Networks (ANN) [922 stars on Github].

<Toolkit>No 36Tfjs: A WebGL accelerated, browser based JavaScript library for training and deploying ML models.

[10268 stars on Github].

No 37Dopamine: A research framework for fast prototyping of reinforcement learning algorithms — Google [7142 stars on Github].

No 38Lime: Explaining the predictions of any machine learning classifier [5173 stars on Github].

No 39Autokeras: An open source software library for automated machine learning (AutoML) [4520 stars on Github].

No 40Shap: Explain the output of any machine learning model using expectations and Shapley values.

[3496 stars on Github].

No 41MMdnn: A set of tools to help users inter-operate among different deep learning frameworks.



model conversion and visualization.

Convert models between Caffe, Keras, MXNet, Tensorflow [3021 stars on Github].

No 42Mlflow: Open source platform for the machine learning lifecycle [3013 stars on Github].

No 43Mace: A deep learning inference framework optimized for mobile heterogeneous computing platforms.

[2979 stars on Github].

No 44PySyft: A Python library for secure, private Deep Learning.

PySyft decouples private data from model training, using Multi-Party Computation (MPC) within PyTorch [2595 stars on Github].

No 45Adanet: Fast and flexible AutoML with learning guarantees.

[2293 stars on Github].

No 46Tencent-ml-images: Largest multi-label image database; ResNet-101 model; 80.

73% top-1 acc on ImageNet [2094 stars on Github].

No 47Donkeycar: Open source hardware and software platform to build a small scale self driving car.

[1207 stars on Github].

No 48PocketFlow: An Automatic Model Compression (AutoMC) framework for developing smaller and faster AI applications.

[1677 stars on Github].

No 49DALI: A library containing both highly optimized building blocks and an execution engine for data pre-processing in deep learning applications [1013 stars on Github].

That’s it for Machine Learning Tutorials of the Year.

If you like this curation, read more articles ranked by Mybridge at out blogRecommend & share.

.. More details

Leave a Reply