Search Results for "inference" - Page 4
Sort By:
Showing 139 open source projects for "inference"
View related business solutions-
Gemini 3 and 200+ AI Models on One PlatformBuild generative AI apps with Vertex AI. Switch between models without switching platforms.
-
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.
-
1
KotlinDL
High-level Deep Learning Framework written in Kotlin
...Under the hood, it uses TensorFlow Java API and ONNX Runtime API for Java. KotlinDL offers simple APIs for training deep learning models from scratch, importing existing Keras and ONNX models for inference, and leveraging transfer learning for tailoring existing pre-trained models to your tasks. This project aims to make Deep Learning easier for JVM and Android developers and simplify deploying deep learning models in production environments. -
2
Kitten
A statically typed concatenative systems programming language
Kitten is an experimental, concatenative programming language that blends Forth/Joy-style stack programming with modern static typing and effect tracking. Programs are composed by chaining small words that transform a typed stack, and the compiler uses type inference to ensure compositions are valid. The language explores disciplined handling of side effects, aiming to separate pure transformations from operations that perform I/O or mutate state. Its design encourages small, reusable building blocks that compose cleanly, while still permitting low-level control where performance matters. The implementation targets efficient compiled code and investigates how advanced type systems can improve reliability in a stack-based language. ... -
3
Alphafold
Open source code for AlphaFold
This package provides an implementation of the inference pipeline of AlphaFold v2.0. This is a completely new model that was entered in CASP14 and published in Nature. For simplicity, we refer to this model as AlphaFold throughout the rest of this document. Any publication that discloses findings arising from using this source code or the model parameters should cite the AlphaFold paper. -
4
Style2Paints
Sketch + style = paints
style2paints is an AI-assisted colorization system aimed primarily at line art and manga, turning monochrome drawings into colored illustrations with minimal manual effort. It combines automatic color inference with user guidance, letting artists nudge the model using sparse color hints, masks, or style references. The pipeline focuses on preserving line quality while spreading coherent colors and shading across regions that are often ambiguous to purely automatic methods. Iterative refinement is a core workflow: you can add or adjust hints, rerun inference, and progressively converge on a desired palette and lighting. ... -
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.
-
5
Neural Network Visualization
Project for processing neural networks and rendering to gain insights
nn_vis is a minimalist visualization tool for neural networks written in Python using OpenGL and Pygame. It provides an interactive, graphical representation of how data flows through neural network layers, offering a unique educational experience for those new to deep learning or looking to explain it visually. By animating input, weights, activations, and outputs, the tool demystifies neural network operations and helps users intuitively grasp complex concepts. Its lightweight codebase is... -
6
Twinify
Privacy-preserving generation of a synthetic twin to a data set
...Depending on the nature of your data, twinify implements either the NAPSU-MQ approach described by Räisä et al. or finds an approximate parameter posterior for any probabilistic model you formulated using differentially private variational inference (DPVI). For the latter, twinify also offers automatic modeling for easy building of models fitting the data. If you have existing experience with NumPyro you can also implement your own model directly. Often data that would be very useful for the scientific community is subject to privacy regulations and concerns and cannot be shared. ... -
7
Real-ESRGAN
Real-ESRGAN aims at developing Practical Algorithms
...It extends the original Enhanced Super-Resolution Generative Adversarial Network (ESRGAN) approach by training on synthetic degradations to make results more robust on real-world images, effectively enhancing resolution, reducing noise/artifacts, and reconstructing fine detail in low-quality imagery. The repository includes inference and training scripts, a model zoo with different pretrained models (including general and anime-oriented variants), and support for batch and arbitrary scaling, making it adaptable for diverse enhancement tasks. It emphasizes usability with utilities that handle alpha channels, gray/16-bit images, and tiled inference for large inputs, and can be run via Python scripts or portable executables. -
8
Amazon SageMaker Operators Kubernetes
Amazon SageMaker operator for Kubernetes
Amazon SageMaker is a fully managed machine learning service. With SageMaker, data scientists and developers can quickly and easily build and train machine learning models, and then directly deploy them into a production-ready hosted environment. It provides an integrated Jupyter authoring notebook instance for easy access to your data sources for exploration and analysis, so you don't have to manage servers. It also provides common machine learning algorithms that are optimized to run... -
9
SageMaker MXNet Inference Toolkit
Toolkit for allowing inference and serving with MXNet in SageMaker
SageMaker MXNet Inference Toolkit is an open-source library for serving MXNet models on Amazon SageMaker. This library provides default pre-processing, predict and postprocessing for certain MXNet model types and utilizes the SageMaker Inference Toolkit for starting up the model server, which is responsible for handling inference requests. AWS Deep Learning Containers (DLCs) are a set of Docker images for training and serving models in TensorFlow, TensorFlow 2, PyTorch, and MXNet. ... -
AI-generated apps that pass security reviewRetool lets you generate dashboards, admin panels, and workflows directly on your data. Type something like “Build me a revenue dashboard on my Stripe data” and get a working app with security, permissions, and compliance built in from day one. Whether on our cloud or self-hosted, create the internal software your team needs without compromising enterprise standards or control.
-
10
FOML is an expressive logic rule language that supports object modeling, analysis, and inference. It naturally supports model-level activities, such as constraints (extending UML diagrams), dynamic compositional modeling, analysis and reasoning about models, model testing, design pattern modeling, specification of Domain Specific Modeling Languages, and meta-modeling. FOML can reason about: 1. The model meta-data (meta-model level reasoning, or syntax reasoning) 2.
-
11
Darknet
Convolutional Neural Networks
Darknet is an open source neural network framework written in C and CUDA, developed by Joseph Redmon. It is best known as the original implementation of the YOLO (You Only Look Once) real-time object detection system. Darknet is lightweight, fast, and easy to compile, making it suitable for research and production use. The repository provides pre-trained models, configuration files, and tools for training custom object detection models. With GPU acceleration via CUDA and OpenCV integration,... -
12
Real-ESRGAN ncnn Vulkan
NCNN implementation of Real-ESRGAN
Real-ESRGAN ncnn Vulkan is an optimized, cross-platform implementation of Real-ESRGAN using the ncnn neural network inference engine and Vulkan for hardware acceleration. Unlike the standard PyTorch-based Real-ESRGAN code, this variant is written in C/C++ and designed to run efficiently on many platforms (including Windows, Linux, and possibly Android) without requiring heavy frameworks like CUDA or Python. It provides command-line tools for upscaling images with selected models, allowing users to specify input/output paths, scaling factors, tile sizes, and model names from a compressed model set, which is particularly helpful for larger images or automated workflows. ... -
13
Nexus
Code-First, Type-Safe, GraphQL Schema Construction
...Automatically generates and infers types based on the schema. No need to manually add annotations, Nexus can automatically infer them in TypeScript using global declaration merging and conditional type inference. For association type fields, you can either import types you've created, or supply their names as strings, with free autocomplete. -
14
typera
Type-safe routes for Express and Koa
Typera helps you build backends in a type-safe manner by leveraging io-ts and some TypeScript type inference magic. It works with both Express and Koa. -
15
Statistical Rethinking 2022
Statistical Rethinking course winter 2022
This repository hosts the 2022 version of the Statistical Rethinking course. It contains course materials such as R scripts, notebooks, and worked examples aligned with McElreath’s textbook. The code emphasizes Bayesian data analysis using R, the rethinking package, and Stan models. It includes lecture code files, example datasets, and structured exercises that parallel the topics covered in the lectures (probability, regression, model comparison, Bayesian updating). The repo functions as a... -
16
MACE
Deep learning inference framework optimized for mobile platforms
Mobile AI Compute Engine (or MACE for short) is a deep learning inference framework optimized for mobile heterogeneous computing on Android, iOS, Linux and Windows devices. Runtime is optimized with NEON, OpenCL and Hexagon, and Winograd algorithm is introduced to speed up convolution operations. The initialization is also optimized to be faster. Chip-dependent power options like big.LITTLE scheduling, Adreno GPU hints are included as advanced APIs. -
17
Graph4NLP
Graph4nlp is the library for the easy use of Graph Neural Networks
Graph4NLP is an easy-to-use library for R&D at the intersection of Deep Learning on Graphs and Natural Language Processing (i.e., DLG4NLP). It provides both full implementations of state-of-the-art models for data scientists and also flexible interfaces to build customized models for researchers and developers with whole-pipeline support. Built upon highly-optimized runtime libraries including DGL , Graph4NLP has both high running efficiency and great extensibility. The architecture of... -
18
SVoice (Speech Voice Separation)
We provide a PyTorch implementation of the paper Voice Separation
SVoice is a PyTorch-based implementation of Facebook Research’s study on speaker voice separation as described in the paper “Voice Separation with an Unknown Number of Multiple Speakers.” This project presents a deep learning framework capable of separating mixed audio sequences where several people speak simultaneously, without prior knowledge of how many speakers are present. The model employs gated neural networks with recurrent processing blocks that disentangle voices over multiple... -
19
PyTorchVideo
A deep learning library for video understanding research
...The library includes efficient implementations of state-of-the-art architectures such as SlowFast, X3D, and MViT, optimized for both research prototyping and production inference. It supports video I/O pipelines, data augmentation, distributed training, and mixed precision computation for large-scale experiments. PyTorchVideo also connects seamlessly with other Meta AI tools such as Detectron2 and PyTorch3D for multimodal video analysis. Designed to accelerate research and deployment, it serves as a unified framework for reproducible, high-performance video AI development. -
20
SageMaker TensorFlow Serving Container
A TensorFlow Serving solution for use in SageMaker
...You can also run your container locally in Docker to test different models and input inference requests by hand. -
21
TNN
Uniform deep learning inference framework for mobile
...As a basic acceleration framework for Tencent Cloud AI, TNN has provided acceleration support for the implementation of many businesses. Everyone is welcome to participate in the collaborative construction to promote the further improvement of the TNN inference framework. -
22
Minkowski Engine
Auto-diff neural network library for high-dimensional sparse tensors
...We list a few popular network architectures and applications here. To run the examples, please install the package and run the command in the package root directory. Compressing a neural network to speed up inference and minimize memory footprint has been studied widely. One of the popular techniques for model compression is pruning the weights in convnets, is also known as sparse convolutional networks. Such parameter-space sparsity used for model compression compresses networks that operate on dense tensors and all intermediate activations of these networks are also dense tensors. -
23
Caramel
Functional language for building type-safe applications
...Caramel leverages the OCaml compiler, to provide you with a pragmatic type system and industrial-strength type safety, and the Erlang VM, known for running low-latency, distributed, and fault-tolerant systems used in a wide range of industries. Excellent type inference, so you never need to annotate your code. Supports sources in OCaml (and soon Reason syntax too). Caramel aims to make building type-safe concurrent programs a productive and fun experience. Caramel should let anyone with existing OCaml or Reason experience be up and running without having to relearn the entire language. Caramel strives to integrate with the larger ecosystem of BEAM languages, like Erlang, Elixir, Gleam, Purerl, LFE, and Hamler. -
24
BudgetML
Deploy a ML inference service on a budget in 10 lines of code
Deploy a ML inference service on a budget in less than 10 lines of code. BudgetML is perfect for practitioners who would like to quickly deploy their models to an endpoint, but not waste a lot of time, money, and effort trying to figure out how to do this end-to-end. We built BudgetML because it's hard to find a simple way to get a model in production fast and cheaply. -
25
ThinkTs
Based on koa and typeorm,asynchronous non blocking reactive coding
Based on koa and Typeform, asynchronous nonblocking reactive coding, and a real MVC web framework, inspired by [ThinkPHP + Nestjs + FastAPI], it is also the fastest development speed and fastest performance.
