PyTorch implementation of StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation. StarGAN can flexibly translate an input image to any desired target domain using only a single generator and a discriminator.

StarGAN - Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation

Haystack is an end-to-end framework that enables you to build powerful and production-ready pipelines for different search use cases. Whether you want to perform Question Answering or semantic document search, you can use the State-of-the-Art NLP models in Haystack to provide unique search experiences and allow your users to query in natural language. Haystack is built in a modular fashion so that you can combine the best technology from other open-source projects like Huggingface's Transformers, Elasticsearch, or Milvus.
 
Haystack can perform semantic search and retrieve documents according to meaning, not keywords. It can ask questions in natural language and find granular answers in your documents. It can automate processes by automatically applying a list of questions to new documents and using the extracted answers.

Haystack is an end-to-end framework that enables you to build powerful and production-ready pipelines for different search use cases. Whether you want to perform Question Answering or semantic document search, you can use the State-of-the-Art NLP models in Haystack to provide unique search experiences and allow your users to query in natural language. Haystack is built in a modular fashion so that you can combine the best technology from other open-source projects like Huggingface's Transformers, Elasticsearch, or Milvus.

Haystack - Build a natural language interface for your data

Coqui TTS is a library for advanced Text-to-Speech generation. It's built on the latest research, was designed to achieve the best trade-off among ease-of-training, speed and quality. Coqui TTS comes with pretrained models, tools for measuring dataset quality and already used in 20+ languages for products and research projects.
 
Features: 
<ul style="margin-bottom: 16px; padding-left: 2em;"><li style="">High-performance Deep Learning models for Text2Speech tasks.<ul style="padding-left: 2em;"><li>Text2Spec models (Tacotron, Tacotron2, Glow-TTS, SpeedySpeech).</li><li style="margin-top: 0.25em;">Speaker Encoder to compute speaker embeddings efficiently.</li><li style="margin-top: 0.25em;">Vocoder models (MelGAN, Multiband-MelGAN, GAN-TTS, ParallelWaveGAN, WaveGrad, WaveRNN)</li></ul></li><li style="margin-top: 0.25em;">Fast and efficient model training.</li><li style="margin-top: 0.25em;">Detailed training logs on the terminal and Tensorboard.</li><li style="margin-top: 0.25em;">Support for Multi-speaker TTS.</li><li style="margin-top: 0.25em;">Efficient, flexible, lightweight but feature complete&nbsp;Trainer API.</li><li style="margin-top: 0.25em;">Ability to convert PyTorch models to Tensorflow 2.0 and TFLite for inference.</li><li style="margin-top: 0.25em;">Released and read-to-use models.</li><li style="margin-top: 0.25em;">Tools to curate Text2Speech datasets underdataset_analysis.</li><li style="margin-top: 0.25em;">Utilities to use and test your models.</li><li style="margin-top: 0.25em;">Modular (but not too much) code base enabling easy implementation of new ideas.</li></ul>

Coqui TTS is a library for advanced Text-to-Speech generation. It's built on the latest research, was designed to achieve the best trade-off among ease-of-training, speed and quality.  Coqui TTS comes with pretrained models, tools for measuring dataset quality and already used in 20+ languages for products and research projects.



Coqui - Advanced Text-to-Speech Library

Stanza is a Python NLP Library for Many Human Languages. It contains support for running various accurate natural language processing tools on 60+ languages and for accessing the Java Stanford CoreNLP software from Python. A new collection of biomedical and clinical English model packages are now available, offering seamless experience for syntactic analysis and named entity recognition (NER) from biomedical literature text and clinical notes.

Stanza - A Python NLP Library for Many Human Languages

MindsDB enables you to use ML predictions in your database using SQL. MindsDB automates and abstracts machine learning models through virtual AI Tables. It can easily make predictions over very complex multivariate time-series data with high cardinality. 
 
Its features include:
<ul>
<li>Automatic data pre-processing, feature engineering and encoding</li>
<li>Classification, regression, time-series tasks</li>
<li>Bring models to production without &ldquo;traditional deployment&rdquo; as AI Tables</li>
<li>Get mModels&rsquo; accuracy scoring and confidence intervals for each prediction</li>
<li>Join ML models with existing data</li>
<li>Anomaly detection</li>
<li>Model explainability analysis</li>
<li>GPU support for models&rsquo; training</li>
<li>Open JSON-AI syntax to build models and bring your own ML blocks in a declarative way</li>
<li>REST API available as well</li>
</ul>

MindsDB enables you to use ML predictions in your database using SQL. MindsDB automates and abstracts machine learning models through virtual AI Tables. It can easily make predictions over very complex multivariate time-series data with high cardinality. 







MindsDB - In-Database Machine Learning



AutoGluon automates machine learning tasks enabling you to easily achieve strong predictive performance in your applications. With just a few lines of code, you can train and deploy high-accuracy machine learning and deep learning models on image, text, and tabular data.
 
<ul>
<li>Quickly prototype deep learning and classical ML solutions for your raw data with a few lines of code.</li>
<li>Automatically utilize state-of-the-art techniques (where appropriate) without expert knowledge.</li>
<li>Leverage automatic hyperparameter tuning, model selection/ensembling, architecture search, and data processing.</li>
<li>Easily improve/tune your bespoke models and data pipelines, or customize <cite>AutoGluon</cite> for your use-case.</li>
</ul>

AutoGluon automates machine learning tasks enabling you to easily achieve strong predictive performance in your applications. With just a few lines of code, you can train and deploy high-accuracy machine learning and deep learning models on image, text, and tabular data.

AutoGluon - AutoML for Text, Image, and Tabular Data

Ray is an open-source unified compute framework that makes it easy to scale AI and Python workloads — from reinforcement learning to deep learning to tuning, and model serving. Ray is a unified way to scale Python and AI applications from a single node to a cluster.
 
Ray AI Runtime (AIR) is an open-source toolkit for building ML applications. It provides libraries for distributed data processing, model training, tuning, reinforcement learning, model serving, and more.
 
Ray Core provides a simple and flexible API for building and running your distributed applications. You can often parallelize single machine code with little to zero code changes.
 
With a Ray cluster you can deploy your workloads on AWS, GCP, Azure or on premise. You can also use Ray cluster managers to run Ray on your existing Kubernetes, YARN, or Slurm clusters.

Ray is an open-source unified compute framework that makes it easy to scale AI and Python workloads — from reinforcement learning to deep learning to tuning, and model serving. Ray is a unified way to scale Python and AI applications from a single node to a cluster.


Ray - A unified framework for scaling AI and Python applications

RedisAI is a Redis module for executing Deep Learning/Machine Learning models and managing their data. Its purpose is being a "workhorse" for model serving, by providing out-of-the-box support for popular DL/ML frameworks and unparalleled performance. RedisAI both maximizes computation throughput and reduces latency by adhering to the principle of data locality , as well as simplifies the deployment and serving of graphs by leveraging on Redis' production-proven infrastructure.

RedisAI - A Redis module for serving tensors and executing deep learning graphs

A comprehensive list of Deep Learning / Artificial Intelligence and Machine Learning tutorials - rapidly expanding into areas of AI/Deep Learning / Machine Vision / NLP and industry specific areas such as Climate / Energy, Automotives, Retail, Pharma, Medicine, Healthcare, Policy, Ethics and more. 

Machine-Learning / Deep-Learning / AI + Web3 -Tutorials

Pyro is a universal probabilistic programming language (PPL) written in Python and supported by PyTorch on the backend. Pyro enables flexible and expressive deep probabilistic modeling, unifying the best of modern deep learning and Bayesian modeling. 
 
Probability is the mathematics of reasoning under uncertainty, much as calculus is the mathematics for reasoning about rates of change. Models built in the language of probability can capture complex reasoning, know what they do not know, and uncover structure in data without supervision. Further, probability provides a way for human experts to provide knowledge to AI systems in the form of a priori beliefs.
 
Specifying probabilistic models directly can be cumbersome and implementing them can be very error-prone. Probabilistic programming languages (PPLs) solve these problems by marrying probability with the representational power of programming languages. A probabilistic program is a mix of ordinary deterministic computation and randomly sampled values; this stochastic computation represents a generative story about data.

Pyro is a universal probabilistic programming language (PPL) written in Python and supported by PyTorch on the backend. Pyro enables flexible and expressive deep probabilistic modeling, unifying the best of modern deep learning and Bayesian modeling.

Pyro - Deep universal probabilistic programming with Python and PyTorch

Rubrix is a production-ready Python framework for exploring, annotating, and managing data in NLP projects.
Most annotation tools treat data collection as a one-off activity at the beginning of each project. In real-world projects, data collection is a key activity of the iterative process of ML model development. Once a model goes into production, you want to monitor and analyze its predictions, and collect more data to improve your model over time. Rubrix is designed to close this gap, enabling you to iterate as much as you need.

RUBRIX -  Python framework to explore, label, and monitor data for NLP

Discover open source projects across all platforms

Projects