Open Source Linux Machine Learning Software - Page 4
Sort By:
Machine Learning Software for Linux
View 58 business solutions-
Forever Free Full-Stack Observability | Grafana CloudBuilt on open standards like Prometheus and OpenTelemetry, Grafana Cloud includes Kubernetes Monitoring, Application Observability, Incident Response, plus the AI-powered Grafana Assistant. Get started with our generous free tier today.
-
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.
-
1
MLflow
Open source platform for the machine learning lifecycle
MLflow is a platform to streamline machine learning development, including tracking experiments, packaging code into reproducible runs, and sharing and deploying models. MLflow offers a set of lightweight APIs that can be used with any existing machine learning application or library (TensorFlow, PyTorch, XGBoost, etc), wherever you currently run ML code (e.g. in notebooks, standalone applications or the cloud). -
2
MNN
MNN is a blazing fast, lightweight deep learning framework
MNN is a highly efficient and lightweight deep learning framework. It supports inference and training of deep learning models, and has industry leading performance for inference and training on-device. At present, MNN has been integrated in more than 20 apps of Alibaba Inc, such as Taobao, Tmall, Youku, Dingtalk, Xianyu and etc., covering more than 70 usage scenarios such as live broadcast, short video capture, search recommendation, product searching by image, interactive marketing, equity distribution, security risk control. In addition, MNN is also used on embedded devices, such as IoT. MNN Workbench could be downloaded from MNN's homepage, which provides pretrained models, visualized training tools, and one-click deployment of models to devices. Android platform, core so size is about 400KB, OpenCL so is about 400KB, Vulkan so is about 400KB. Supports hybrid computing on multiple devices. Currently supports CPU and GPU. -
3
PandaOCR
Multifunctional OCR Image and Text Recognition
At present, the newly refactored PandaOCR.Pro professional version has been released. It is faster and more stable, with richer interfaces and easier operation. It is recommended for you to use it! The normal version will continue to be maintained, and all interfaces will be retained but no new functions will be added. The reason why the version number of the professional version starts from 5.x is that the normal version will be updated in the future, so a period of version number is reserved. You can continue to use the regular version for free as before, without worrying about deactivating the regular version after the launch of the professional version. If you have higher needs, you can try the professional version. You can also use the Baidu API interface without activation. Support shortcut keys and screen corner trigger screenshot recognition function, convenient and fast. -
4
ROOT
Analyzing, storing and visualizing big data, scientifically
ROOT is a unified software package for the storage, processing, and analysis of scientific data: from its acquisition to the final visualization in the form of highly customizable, publication-ready plots. It is reliable, performant and well supported, easy to use and obtain, and strives to maximize the quantity and impact of scientific results obtained per unit cost, both of human effort and computing resources. ROOT provides a very efficient storage system for data models, that demonstrated to scale at the Large Hadron Collider experiments: Exabytes of scientific data are written in columnar ROOT format. ROOT comes with histogramming capabilities in an arbitrary number of dimensions, curve fitting, statistical modeling, and minimization, to allow the easy setup of a data analysis system that can query and process the data interactively or in batch mode, as well as a general parallel processing framework, RDataFrame, that can considerably speed up an analysis. -
Earn up to 16% annual interest with Nexo.Generate interest, borrow against your crypto, and trade a range of cryptocurrencies — all in one platform. Geographic restrictions, eligibility, and terms apply.
-
5
Transformer Engine
A library for accelerating Transformer models on NVIDIA GPUs
Transformer Engine (TE) is a library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper GPUs, to provide better performance with lower memory utilization in both training and inference. TE provides a collection of highly optimized building blocks for popular Transformer architectures and an automatic mixed precision-like API that can be used seamlessly with your framework-specific code. TE also includes a framework-agnostic C++ API that can be integrated with other deep-learning libraries to enable FP8 support for Transformers. As the number of parameters in Transformer models continues to grow, training and inference for architectures such as BERT, GPT, and T5 become very memory and compute-intensive. Most deep learning frameworks train with FP32 by default. This is not essential, however, to achieve full accuracy for many deep learning models. -
6
Turing.jl
Bayesian inference with probabilistic programming
Bayesian inference with probabilistic programming. -
7
YOLOX
YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5
YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. YOLOX is an anchor-free version of YOLO, with a simpler design but better performance! It aims to bridge the gap between research and industrial communities. Prepare your own dataset with images and labels first. For labeling images, you can use tools like Labelme or CVAT. One more thing worth noting is that you should also implement pull_item and load_anno method for the Mosiac and MixUp augmentations. Except special cases, we always recommend using our COCO pre-trained weights for initializing the model. As YOLOX is an anchor-free detector with only several hyper-parameters, most of the time good results can be obtained with no changes to the models or training settings. -
8
autoresearch
AI agents autonomously run and improve ML experiments overnight
autoresearch is an experimental framework that enables AI agents to autonomously conduct machine learning research by iteratively modifying and training models. Created by Andrej Karpathy, the project allows an agent to edit the model training code, run short experiments, evaluate results, and repeat the process without human intervention. Each experiment runs for a fixed five-minute training window, enabling rapid iteration and consistent comparison across architectural or hyperparameter changes. The system centers on a simple workflow where the agent modifies a single training file while human researchers guide the process through a program.md instruction file. Designed to run on a single GPU, it keeps the research loop minimal and self-contained to make autonomous experimentation practical. Over time, the agent logs experiments, evaluates improvements, and gradually evolves the model through automated trial-and-error. -
9
dlib
Toolkit for making machine learning and data analysis applications
Dlib is a modern C++ toolkit containing machine learning algorithms and tools for creating complex software in C++ to solve real world problems. It is used in both industry and academia in a wide range of domains including robotics, embedded devices, mobile phones, and large high performance computing environments. Dlib's open source licensing allows you to use it in any application, free of charge. Good unit test coverage, the ratio of unit test lines of code to library lines of code is about 1 to 4. The library is tested regularly on MS Windows, Linux, and Mac OS X systems. No other packages are required to use the library, only APIs that are provided by an out of the box OS are needed. There is no installation or configure step needed before you can use the library. All operating system specific code is isolated inside the OS abstraction layers which are kept as small as possible. -
AI-powered service management for IT and enterprise teamsGive your IT, operations, and business teams the ability to deliver exceptional services—without the complexity. Maximize operational efficiency with refreshingly simple, AI-powered Freshservice.
-
10
ggml
Tensor library for machine learning
ggml is an open-source tensor library designed for efficient machine learning computation with a focus on running models locally and with minimal dependencies. Written primarily in C and C++, the library provides low-level tensor operations and automatic differentiation that allow developers to implement machine learning algorithms and neural networks efficiently. The project emphasizes portability and performance, enabling machine learning inference across a wide range of hardware environments including CPUs and specialized accelerators. It is widely used as a foundational component in projects that run large language models locally, including tools that perform inference for transformer-based models. The library also implements optimization algorithms and computation graph functionality so developers can build training and inference workflows directly on top of its tensor operations. -
11
AIMET
AIMET is a library that provides advanced quantization and compression
Qualcomm Innovation Center (QuIC) is at the forefront of enabling low-power inference at the edge through its pioneering model-efficiency research. QuIC has a mission to help migrate the ecosystem toward fixed-point inference. With this goal, QuIC presents the AI Model Efficiency Toolkit (AIMET) - a library that provides advanced quantization and compression techniques for trained neural network models. AIMET enables neural networks to run more efficiently on fixed-point AI hardware accelerators. Quantized inference is significantly faster than floating point inference. For example, models that we’ve run on the Qualcomm® Hexagon™ DSP rather than on the Qualcomm® Kryo™ CPU have resulted in a 5x to 15x speedup. Plus, an 8-bit model also has a 4x smaller memory footprint relative to a 32-bit model. However, often when quantizing a machine learning model (e.g., from 32-bit floating point to an 8-bit fixed point value), the model accuracy is sacrificed. -
12
APKiD
Android Application Identifier for Packers, Protectors and Obfuscators
APKiD gives you information about how an APK was made. It identifies many compilers, packers, obfuscators, and other weird stuff. It's PEiD for Android. -
13
Apache MXNet (incubating)
A flexible and efficient library for deep learning
Apache MXNet is an open source deep learning framework designed for efficient and flexible research prototyping and production. It contains a dynamic dependency scheduler that automatically parallelizes both symbolic and imperative operations. On top of this is a graph optimization layer, overall making MXNet highly efficient yet still portable, lightweight and scalable. -
14
CVPR 2025
Collection of CVPR 2025 papers and open source projects
CVPR 2025 curates accepted CVPR 2025 papers and pairs them with their corresponding code implementations when available, giving researchers and practitioners a fast way to move from reading to reproducing. It organizes entries by topic areas such as detection, segmentation, generative models, 3D vision, multi-modal learning, and efficiency, so you can navigate the year’s output efficiently. Each paper entry typically includes a title, author list, and links to the paper PDF and official or third-party code repositories. The list frequently highlights benchmarks, leaderboards, or notable results so readers can assess impact at a glance. Because conference content evolves rapidly, the repository is updated as authors release code or refine readme instructions, keeping the collection timely. For teams planning literature reviews, study groups, or rapid prototyping sprints, it acts as a central index to the year’s most relevant methods with working implementations. -
15
CatBoost
High-performance library for gradient boosting on decision trees
CatBoost is a fast, high-performance open source library for gradient boosting on decision trees. It is a machine learning method with plenty of applications, including ranking, classification, regression and other machine learning tasks for Python, R, Java, C++. CatBoost offers superior performance over other GBDT libraries on many datasets, and has several superb features. It has best in class prediction speed, supports both numerical and categorical features, has a fast and scalable GPU version, and readily comes with visualization tools. CatBoost was developed by Yandex and is used in various areas including search, self-driving cars, personal assistance, weather prediction and more. -
16
GROBID
A machine learning software for extracting information
GROBID is a machine learning library for extracting, parsing, and re-structuring raw documents such as PDF into structured XML/TEI encoded documents with a particular focus on technical and scientific publications. First developments started in 2008 as a hobby. In 2011 the tool has been made available in open source. Work on GROBID has been steady as a side project since the beginning and is expected to continue as such. Header extraction and parsing from article in PDF format. The extraction here covers the usual bibliographical information (e.g. title, abstract, authors, affiliations, keywords, etc.). References extraction and parsing from articles in PDF format, around .87 F1-score against on an independent PubMed Central set of 1943 PDF containing 90,125 references, and around .89 on a similar bioRxiv set of 2000 PDF (using the Deep Learning citation model). All the usual publication metadata are covered (including DOI, PMID, etc.). -
17
Gradio
Create UIs for your machine learning model in Python in 3 minutes
Gradio is the fastest way to demo your machine learning model with a friendly web interface so that anyone can use it, anywhere! Gradio can be installed with pip. Creating a Gradio interface only requires adding a couple lines of code to your project. You can choose from a variety of interface types to interface your function. Gradio can be embedded in Python notebooks or presented as a webpage. A Gradio interface can automatically generate a public link you can share with colleagues that lets them interact with the model on your computer remotely from their own devices. Once you've created an interface, you can permanently host it on Hugging Face. Hugging Face Spaces will host the interface on its servers and provide you with a link you can share. One of the best ways to share your machine learning model, API, or data science workflow with others is to create an interactive demo that allows your users or colleagues to try out the demo in their browsers. -
18
Interpretable machine learning
Book about interpretable machine learning
This book is about interpretable machine learning. Machine learning is being built into many products and processes of our daily lives, yet decisions made by machines don't automatically come with an explanation. An explanation increases the trust in the decision and in the machine learning model. As the programmer of an algorithm you want to know whether you can trust the learned model. Did it learn generalizable features? Or are there some odd artifacts in the training data which the algorithm picked up? This book will give an overview over techniques that can be used to make black boxes as transparent as possible and explain decisions. In the first chapter algorithms that produce simple, interpretable models are introduced together with instructions how to interpret the output. The later chapters focus on analyzing complex models and their decisions. In an ideal future, machines will be able to explain their decisions and make a transition into an algorithmic age more human. -
19
KAIR
Image Restoration Toolbox (PyTorch). Training and testing codes
Image restoration toolbox (PyTorch). Training and testing codes for DPIR, USRNet, DnCNN, FFDNet, SRMD, DPSR, BSR/GAN, SwinIR. -
20
Kodezi Chronos
Kodezi Chronos is a debugging-first language model
Kodezi Chronos is a research project focused on developing a specialized language model designed specifically for debugging software and understanding large code repositories. Unlike general-purpose language models that focus primarily on code generation, Chronos is built to diagnose and repair bugs by analyzing complex relationships across files within a codebase. The project introduces architectural techniques such as Adaptive Graph-Guided Retrieval, which allows the system to navigate large repositories and retrieve relevant debugging information from multiple sources. Another component, Persistent Debug Memory, allows the system to learn patterns from past debugging sessions and apply that knowledge to future problems. The repository mainly contains research documentation, evaluation benchmarks, and experimental frameworks rather than the full proprietary model implementation. -
21
LightGBM
Gradient boosting framework based on decision tree algorithms
LightGBM or Light Gradient Boosting Machine is a high-performance, open source gradient boosting framework based on decision tree algorithms. Compared to other boosting frameworks, LightGBM offers several advantages in terms of speed, efficiency and accuracy. Parallel experiments have shown that LightGBM can attain linear speed-up through multiple machines for training in specific settings, all while consuming less memory. LightGBM supports parallel and GPU learning, and can handle large-scale data. It’s become widely-used for ranking, classification and many other machine learning tasks. -
22
Ludwig
A codeless platform to train and test deep learning models
Ludwig is a toolbox built on top of TensorFlow that allows to train and test deep learning models without the need to write code. All you need to provide is a CSV file containing your data, a list of columns to use as inputs, and a list of columns to use as outputs, Ludwig will do the rest. Simple commands can be used to train models both locally and in a distributed way, and to use them to predict on new data. -
23
Metaflow
A framework for real-life data science
Metaflow is a human-friendly Python library that helps scientists and engineers build and manage real-life data science projects. Metaflow was originally developed at Netflix to boost productivity of data scientists who work on a wide variety of projects from classical statistics to state-of-the-art deep learning. -
24
Model Zoo
Please do not feed the models
FluxML Model Zoo is a collection of demonstration models built with the Flux machine learning library in Julia. The repository provides ready-to-run implementations across multiple domains, including computer vision, natural language processing, and reinforcement learning. Each model is organized into its own project folder with pinned package versions, ensuring reproducibility and stability. The examples serve both as educational tools for learning Flux and as practical starting points for building new models. GPU acceleration is supported for most models through CUDA integration, enabling efficient training on compatible hardware. With community contributions encouraged, the Model Zoo acts as a hub for sharing and exploring diverse machine learning applications in Julia. -
25
NVIDIA NeMo
Toolkit for conversational AI
NVIDIA NeMo, part of the NVIDIA AI platform, is a toolkit for building new state-of-the-art conversational AI models. NeMo has separate collections for Automatic Speech Recognition (ASR), Natural Language Processing (NLP), and Text-to-Speech (TTS) models. Each collection consists of prebuilt modules that include everything needed to train on your data. Every module can easily be customized, extended, and composed to create new conversational AI model architectures. Conversational AI architectures are typically large and require a lot of data and compute for training. NeMo uses PyTorch Lightning for easy and performant multi-GPU/multi-node mixed-precision training. Supported models: Jasper, QuartzNet, CitriNet, Conformer-CTC, Conformer-Transducer, Squeezeformer-CTC, Squeezeformer-Transducer, ContextNet, LSTM-Transducer (RNNT), LSTM-CTC. NGC collection of pre-trained speech processing models.
