Open Source BSD Deep Learning Frameworks
Sort By:
Deep Learning Frameworks for BSD
Browse free open source Deep Learning Frameworks and projects for BSD below. Use the toggles on the left to filter open source Deep Learning Frameworks by OS, license, language, programming language, and project status.
-
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
99.99% Uptime for MySQL and PostgreSQL DatabasesCloud SQL Enterprise Plus delivers near-zero downtime with 35 days of point-in-time recovery. Supports MySQL, PostgreSQL, and SQL Server.
-
1
OpenCV
Open Source Computer Vision Library
The Open Source Computer Vision Library has >2500 algorithms, extensive documentation and sample code for real-time computer vision. It works on Windows, Linux, Mac OS X, Android, iOS in your browser through JavaScript. Languages: C++, Python, Julia, Javascript Homepage: https://opencv.org Q&A forum: https://forum.opencv.org/ Documentation: https://docs.opencv.org Source code: https://github.com/opencv Please pay special attention to our tutorials! https://docs.opencv.org/master Books about the OpenCV are described here: https://opencv.org/books.html -
2
Megatron
Ongoing research training transformer models at scale
Megatron is a large, powerful transformer developed by the Applied Deep Learning Research team at NVIDIA. This repository is for ongoing research on training large transformer language models at scale. We developed efficient, model-parallel (tensor, sequence, and pipeline), and multi-node pre-training of transformer based models such as GPT, BERT, and T5 using mixed precision. Megatron is also used in NeMo Megatron, a framework to help enterprises overcome the challenges of building and training sophisticated natural language processing models with billions and trillions of parameters. Copyright (c) 2022, NVIDIA CORPORATION. All rights reserved. -
3
AudioCraft
Audiocraft is a library for audio processing and generation
AudioCraft is a PyTorch library for text-to-audio and text-to-music generation, packaging research models and tooling for training and inference. It includes MusicGen for music generation conditioned on text (and optionally melody) and AudioGen for text-conditioned sound effects and environmental audio. Both models operate over discrete audio tokens produced by a neural codec (EnCodec), which acts like a tokenizer for waveforms and enables efficient sequence modeling. The repo provides inference scripts, checkpoints, and simple Python APIs so you can generate clips from prompts or incorporate the models into applications. It also contains training code and recipes, so researchers can fine-tune on custom data or explore new objectives without building infrastructure from scratch. Example notebooks, CLI tools, and audio utilities help with prompt design, conditioning on reference audio, and post-processing to produce ready-to-share outputs. -
4
GPT-NeoX
Implementation of model parallel autoregressive transformers on GPUs
This repository records EleutherAI's library for training large-scale language models on GPUs. Our current framework is based on NVIDIA's Megatron Language Model and has been augmented with techniques from DeepSpeed as well as some novel optimizations. We aim to make this repo a centralized and accessible place to gather techniques for training large-scale autoregressive language models, and accelerate research into large-scale training. For those looking for a TPU-centric codebase, we recommend Mesh Transformer JAX. If you are not looking to train models with billions of parameters from scratch, this is likely the wrong library to use. For generic inference needs, we recommend you use the Hugging Face transformers library instead which supports GPT-NeoX models. -
Cut Data Warehouse Costs by 54%BigQuery delivers 54% lower TCO with exabyte scale and flexible pricing. Free migration tools handle the SQL translation automatically.
-
5
JEPA
PyTorch code and models for V-JEPA self-supervised learning from video
JEPA (Joint-Embedding Predictive Architecture) captures the idea of predicting missing high-level representations rather than reconstructing pixels, aiming for robust, scalable self-supervised learning. A context encoder ingests visible regions and predicts target embeddings for masked regions produced by a separate target encoder, avoiding low-level reconstruction losses that can overfit to texture. This makes learning focus on semantics and structure, yielding features that transfer well with simple linear probes and minimal fine-tuning. The repository provides training recipes, data pipelines, and evaluation utilities for image JEPA variants and often includes ablations that illuminate which masking and architectural choices matter. Because the objective is non-autoregressive and operates in embedding space, JEPA tends to be compute-efficient and stable at scale. The approach has become a strong alternative to contrastive or pixel-reconstruction methods for representation learning. -
6
Robust Tube MPC
Example implementation for robust model predictive control using tube
robust-tube-mpc is a MATLAB implementation of robust tube-based Model Predictive Control (MPC). The framework provides tools to design and simulate controllers that maintain stability and constraint satisfaction in the presence of bounded disturbances. Tube-based MPC achieves robustness by combining a nominal trajectory planner with an error feedback controller that keeps the actual system state within a "tube" around the nominal trajectory. This repository includes example scripts and implementations demonstrating how to apply the method to control problems. It is particularly useful for researchers, students, and engineers exploring robust control strategies in uncertain environments. By offering a structured implementation, robust-tube-mpc makes it easier to study and extend advanced MPC techniques for real-world applications. -
7
DeepSpeed
Deep learning optimization library: makes distributed training easy
DeepSpeed is an easy-to-use deep learning optimization software suite that enables unprecedented scale and speed for Deep Learning Training and Inference. With DeepSpeed you can: 1. Train/Inference dense or sparse models with billions or trillions of parameters 2. Achieve excellent system throughput and efficiently scale to thousands of GPUs 3. Train/Inference on resource constrained GPU systems 4. Achieve unprecedented low latency and high throughput for inference 5. Achieve extreme compression for an unparalleled inference latency and model size reduction with low costs DeepSpeed offers a confluence of system innovations, that has made large scale DL training effective, and efficient, greatly improved ease of use, and redefined the DL training landscape in terms of scale that is possible. These innovations such as ZeRO, 3D-Parallelism, DeepSpeed-MoE, ZeRO-Infinity, etc. fall under the training pillar. -
8
Deeplearning.ai
Study notes, summaries, and auxiliary materials for deep learning
Deeplearning.ai collects study notes, summaries, and auxiliary materials aligned with the popular deep learning course series many learners take early in their AI journey. It distills core ideas such as optimization, regularization, convolutional networks, sequence models, and practical training tricks. The explanations aim to bridge theory and practice, often connecting mathematical intuition to code-level implications. By organizing the content as “books” or structured notes, it gives students a consistent reference to revisit as models and tooling evolve. Many learners use it to supplement course videos, reinforcing concepts before implementing assignments or projects. As a consolidated guide, it reduces context-switching and helps build a durable mental model of deep learning fundamentals. -
9
Exposure Correction
Learning multi-scale deep model correcting over- and under- exposed
Exposure_Correction is a research project that provides the implementation for the paper Learning Multi-Scale Photo Exposure Correction (CVPR 2021). The repository focuses on correcting poorly exposed photographs, handling both underexposure and overexposure using a deep learning approach. The method employs a multi-scale framework that learns to enhance images by adjusting exposure levels across different spatial resolutions. This allows the model to preserve fine details while correcting global lighting inconsistencies. The repository includes pre-trained models, datasets, and training/testing code to enable reproducibility and experimentation. By leveraging this framework, researchers and developers can apply exposure correction to a wide range of natural images, improving visual quality without manual editing. The project serves both as a research reference and a practical tool for computational photography and image enhancement. -
$300 Free Credits to Build on Google CloudPut your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
-
10
Make-A-Video - Pytorch (wip)
Implementation of Make-A-Video, new SOTA text to video generator
Implementation of Make-A-Video, new SOTA text to video generator from Meta AI, in Pytorch. They combine pseudo-3d convolutions (axial convolutions) and temporal attention and show much better temporal fusion. The pseudo-3d convolutions isn't a new concept. It has been explored before in other contexts, say for protein contact prediction as "dimensional hybrid residual networks". The gist of the paper comes down to, take a SOTA text-to-image model (here they use DALL-E2, but the same learning points would easily apply to Imagen), make a few minor modifications for attention across time and other ways to skimp on the compute cost, do frame interpolation correctly, get a great video model out. Passing in images (if one were to pretrain on images first), both temporal convolution and attention will be automatically skipped. In other words, you can use this straightforwardly in your 2d Unet and then port it over to a 3d Unet once that phase of the training is done. -
11
MatlabFunc
Matlab codes for feature learning
MatlabFunc is a collection of MATLAB functions developed by the ZJULearning group to support various tasks in computer vision, machine learning, and numerical computation. The repository brings together a wide range of utility scripts, algorithms, and implementations that serve as building blocks for research and development. These functions cover areas such as matrix operations, optimization, data processing, and visualization, making them broadly applicable across different research domains. The project is intended to provide reusable and adaptable MATLAB code that can save time for researchers and students working on experimental or applied projects. By consolidating these tools in one place, MatlabFunc serves as a practical reference and toolkit for both academic and engineering purposes. Contributions and improvements from the community are encouraged, allowing the repository to grow into a richer resource over time. -
12
Open Model Zoo
Pre-trained Deep Learning models and demos
Open Model Zoo is a large repository of high-quality pre-trained deep learning models and demonstration applications designed to work with the OpenVINO™ toolkit, offering a comprehensive starting point for a wide range of AI and computer vision workloads. It includes hundreds of models covering object detection, classification, segmentation, pose estimation, speech recognition, text-to-speech, and more, many of which are already converted into formats optimized for inference on CPUs, GPUs, VPUs, and other accelerators supported by OpenVINO. In addition to model files, Open Model Zoo provides demo applications that show realistic usage patterns and help developers quickly prototype and understand inference pipelines in C++, Python, or via the OpenCV Graph API. Tools in the repository also help automate model downloads and other tasks, making it easier to incorporate these models into production systems or custom solutions. -
13
vJEPA-2
PyTorch code and models for VJEPA2 self-supervised learning from video
VJEPA2 is a next-generation self-supervised learning framework for video that extends the “predict in representation space” idea from i-JEPA to the temporal domain. Instead of reconstructing pixels, it predicts the missing high-level embeddings of masked space-time regions using a context encoder and a slowly updated target encoder. This objective encourages the model to learn semantics, motion, and long-range structure without the shortcuts that pixel-level losses can invite. The architecture is designed to scale: spatiotemporal ViT backbones, flexible masking schedules, and efficient sampling let it train on long clips while remaining stable. Trained representations transfer well to downstream tasks such as action recognition, temporal localization, and video retrieval, often with simple linear probes or light fine-tuning. The repository typically includes end-to-end recipes—data pipelines, augmentation policies, training scripts, and evaluation harnesses. -
14
Cross Attention Control
Unofficial implementation of "Prompt-to-Prompt Image Editing
Cross Attention Control is an unofficial Stable Diffusion implementation of Prompt-to-Prompt image editing with cross-attention control. It modifies diffusion-model attention maps during inference so prompt changes can produce more controlled edits. The method is designed to avoid manual masks while requiring no additional training or fine-tuning. The notebooks include examples for editing images generated from the same seed. The project also adds image inversion using a modified inverse DDIM process to recover a latent representation from an existing image. Additional techniques help preserve compatibility with other schedulers and improve inversion at higher classifier-free guidance values. -
15
DLRM
An implementation of a deep learning recommendation model (DLRM)
DLRM (Deep Learning Recommendation Model) is Meta’s open-source reference implementation for large-scale recommendation systems built to handle extremely high-dimensional sparse features and embedding tables. The architecture combines dense (MLP) and sparse (embedding) branches, then interacts features via dot product or feature interactions before passing through further dense layers to predict click-through, ranking scores, or conversion probabilities. The implementation is optimized for performance at scale, supporting multi-GPU and multi-node execution, quantization, embedding partitioning, and pipelined I/O to feed huge embeddings efficiently. It includes data loaders for standard benchmarks (like Criteo), training scripts, evaluation tools, and capabilities like mixed precision, gradient compression, and memory fusion to maximize throughput. -
16
Deep Learning Is Nothing
Deep learning concepts in an approachable style
Deep-Learning-Is-Nothing presents deep learning concepts in an approachable, from-scratch style that demystifies the stack behind modern models. It typically begins with linear algebra, calculus, and optimization refreshers before moving to perceptrons, multilayer networks, and gradient-based training. Implementations favor small, readable examples—often NumPy first—to show how forward and backward passes work without depending solely on high-level frameworks. Once the fundamentals are clear, the material extends to CNNs, RNNs, and attention mechanisms, explaining why each architecture suits particular tasks. Practical sections cover data pipelines, regularization, and evaluation, emphasizing reproducibility and debugging techniques. The goal is to replace buzzwords with intuition so learners can reason about architectures and training dynamics with confidence. -
17
Deep Learning Models
A collection of various deep learning architectures, models, and tips
This repository collects clear, well-documented implementations of deep learning models and training utilities written by Sebastian Raschka. The code favors readability and pedagogy: components are organized so you can trace data flow through layers, losses, optimizers, and evaluation. Examples span fundamental architectures—MLPs, CNNs, RNN/Transformers—and practical tasks like image classification or text modeling. Reproducible training scripts and configuration files make it straightforward to rerun experiments or adapt them to your own datasets. The repo often pairs implementations with notes on design choices and trade-offs, turning it into both a toolbox and a learning resource. It’s suitable for students, researchers prototyping ideas, and practitioners who want clean baselines before adding complexity. -
18
Deep Learning Papers Reading Roadmap
Deep Learning papers reading roadmap for anyone who are eager to learn
Deep Learning Papers Reading Roadmap is a widely known curated reading plan for deep learning that helps newcomers and practitioners navigate the vast literature in a structured and intentional way. It is built around several guiding principles: moving from outline to detail, from older foundational papers to state-of-the-art work, and from generic to more specialized areas while keeping a focus on impactful contributions. The roadmap organizes papers into categories such as fundamentals, convolutional networks, sequence models, unsupervised learning, generative models, optimization, and application areas like computer vision or NLP. For each section, it suggests an order that lets readers gradually build intuition and then dive deeper into more advanced or recent topics. It is particularly useful for students and engineers who want to systematically improve their understanding rather than randomly picking papers. -
19
Deep Learning cheatsheets
VIP cheatsheets for Stanford's CS 230 Deep Learning
Deep Learning cheatsheets forStanford's CS 230 is an educational repository that compiles comprehensive cheat sheets, summaries, and study resources covering the core concepts taught in Stanford’s CS230 Deep Learning course. The project organizes complex machine learning topics into visually structured reference materials that simplify studying neural networks, convolutional architectures, recurrent networks, optimization strategies, and training methodologies. It was created to help students and practitioners quickly review important formulas, workflows, and implementation concepts without navigating large textbooks or lecture archives. The repository combines concise theoretical explanations with practical training advice, making it valuable for both interview preparation and hands-on model development. Its materials are widely used within the machine learning community because of their accessibility, clarity, and high information density. -
20
Deep Reinforcement Learning TensorFlow
TensorFlow implementation of Deep Reinforcement Learning papers
Deep Reinforcement Learning TensorFlow is a comprehensive TensorFlow codebase that implements several foundational deep reinforcement learning algorithms for educational and experimental use. The repository focuses on clarity and modularity so users can study how different RL approaches are built and compare their behavior across environments. It includes implementations of well-known algorithms such as Deep Q-Networks (DQN), policy gradients, and related variants, demonstrating how neural networks can be trained through interaction with simulated environments. The project is commonly used by learners who want to move beyond theory and understand the practical mechanics of training RL agents. Visualization utilities and training scripts help users monitor learning progress and debug experiments. -
21
Deep-Learning-Interview-Book
Interview guide for machine learning, mathematics, and deep learning
Deep-Learning-Interview-Book collects structured notes, Q&A, and concept summaries tailored to deep-learning interviews, turning scattered study into a coherent playbook. It spans the core math (linear algebra, probability, optimization) and the practitioner topics candidates actually face, like CNNs, RNNs/Transformers, attention, regularization, and training tricks. Explanations emphasize intuition first, then key formulas and common pitfalls, so you can reason through unseen questions rather than memorize trivia. Many entries connect theory to implementation details, including how choices in activation, initialization, or normalization affect convergence and stability. The content is organized for fast review before an interview loop but is also deep enough for systematic study over weeks. Because it’s text-first and modular, it works equally well as a quick refresher or a backbone for a full study plan. -
22
Deep-Learning-with-PyTorch-Tutorials
Deep Learning and PyTorch Introduction Video Tutorial with Source Code
Deep-Learning-with-PyTorch-Tutorials is a companion repository for an introductory deep learning course built around PyTorch. It provides source code, notebooks, and presentation materials for a practical video-based learning path. The lessons begin with PyTorch setup, tensors, indexing, mathematical operations, gradients, and basic optimization. They then move into neural networks, logistic regression, multilayer perceptrons, CNNs, ResNet, RNNs, LSTMs, autoencoders, VAEs, GANs, graph convolutional networks, and transfer learning. The repository is designed for learners who want to connect deep learning concepts with executable examples. Overall, it is a structured PyTorch practice resource for beginners and early deep learning practitioners. -
23
Deep-Learning-with-TensorFlow-book
Open source Deep Learning book, based on TensorFlow
Deep-Learning-with-TensorFlow-book is an open-source deep learning book based on TensorFlow 2.0. It combines theory with practical examples, making it suitable for beginners who want to learn deep learning through hands-on code. The repository includes the PDF book, companion source code, course slides, and notebook-style materials. It covers core machine learning and deep learning concepts through TensorFlow-based implementation. The project also supports educational use, with materials that can be adopted by students, self-learners, and instructors. Overall, it is a complete learning package for understanding modern deep learning workflows through TensorFlow 2.0 examples. -
24
Learn_Deep_Learning_in_6_Weeks
This is the Curriculum for "Learn Deep Learning in 6 Weeks"
Learn_Deep_Learning_in_6_Weeks compresses an introductory deep learning curriculum into six weeks of structured learning and practice. It begins with neural network fundamentals and moves through convolutional and recurrent architectures, optimization strategies, regularization, and transfer learning. The materials emphasize code-first understanding: building small models, training them on accessible datasets, and analyzing their behavior. Each week culminates in a tangible outcome—such as a working classifier or sequence model—so progress is visible and motivating. The plan also introduces practical considerations like GPU usage, checkpoints, and debugging training dynamics. It aims to give you enough breadth to recognize common patterns and enough depth to implement them on your own problems. -
25
LearningToCompare_FSL
Learning to Compare: Relation Network for Few-Shot Learning
LearningToCompare_FSL is a PyTorch implementation of the “Learning to Compare: Relation Network for Few-Shot Learning” paper, focusing on the few-shot learning experiments described in that work. The core idea implemented here is the relation network, which learns to compare pairs of feature embeddings and output relation scores that indicate whether two images belong to the same class, enabling classification from only a handful of labeled examples. The repository provides training and evaluation code for standard few-shot benchmarks such as miniImageNet and Omniglot, making it possible to reproduce the experimental results reported in the paper. It includes model definitions, data loading logic, episodic training loops, and scripts that implement the N-way K-shot evaluation protocol common in few-shot research. Researchers can use this codebase as a starting point to test new ideas, modify relation modules, or transfer the approach to new datasets.
