Awesome GitHub RepositoriesTensorFlow

TensorFlow.js is a JavaScript machine learning library used for training and deploying models in web browsers and server-side environments. It functions as a browser-based model trainer, a WebAssembly inference engine, and a WebGPU accelerated tensor library for low-level linear algebra. The project also includes a model converter to transform Python-based models into optimized formats for JavaScript execution. The library distinguishes itself through a pluggable backend architecture that allows mathematical operations to be executed via CPU, WebGL, or WebGPU. It supports the conversion of Py

This project is a collection of pre-trained machine learning models and conversion pipelines designed for running inference directly in the browser using TensorFlow.js. It provides a library of ready-to-use models for computer vision, audio classification, and natural language processing tasks. The suite includes specialized tools for transforming Python-based Keras models into JSON formats compatible with web environments. It enables the deployment of these models by fetching architectures and weight shards via HTTP for client-side execution. The project covers a broad range of capabilities

WasmEdge is an extensible WebAssembly runtime that executes WebAssembly bytecode in a secure sandbox for cloud, edge, and embedded applications. It functions as a multi-language compiler, compiling applications written in Rust, JavaScript, Go, and Python into WebAssembly bytecode for sandboxed execution, and as a server-side JavaScript runtime that runs JavaScript programs with ES6 modules, NPM packages, and Node.js-compatible APIs. The runtime also serves as an AI inference runtime, executing AI models from JavaScript using WASI-NN plug-ins for inference tasks on personal devices and edge har

OpenVINO is an AI inference engine and model serving platform designed to execute optimized deep learning models across CPUs, GPUs, and NPUs through a unified API. It includes a model optimization toolkit for converting, quantizing, and compressing models from various frameworks, alongside a specialized generative AI runtime for large language models. The project distinguishes itself through a plugin-based hardware acceleration layer that maps neural network operations to vendor-specific drivers. It features advanced execution mechanisms such as continuous batching, speculative decoding, and

tflearn is a deep learning framework and high-level API wrapper for TensorFlow. It provides a toolkit for designing neural network architectures and a system for executing training loops and optimizing model weights across CPUs and GPUs. The project simplifies the process of building and training models through a modular interface and a high-level API for prototyping. It includes specialized utilities for deep learning visualization, allowing for the generation of graphical diagrams to analyze network structures, weights, gradients, and activations. The framework covers a broad range of capa

tensorrtx is a computer vision inference engine and model implementation library designed for graphics processor acceleration. It provides a framework for optimizing deep learning models through a GPU inference optimizer, a deep learning model converter for transforming weights from frameworks like TensorFlow and PyTorch, and a custom plugin library to implement operations not natively supported by the TensorRT API. The project distinguishes itself through a comprehensive collection of pre-defined network implementations, ranging from various YOLO versions and DETR transformers for object det

yolotf is an object detection framework that provides tools for converting Darknet model configurations and weights into TensorFlow graphs. It includes a TensorFlow model trainer for training new detection models or fine-tuning existing weights using custom datasets. The project features a mobile model exporter that serializes graph definitions and metadata into protobuf files for deployment on mobile devices. The framework supports object detection inference on images and video to identify objects and export bounding box coordinates. It manages model state through weight-mapping translation

Darkflow is an object detection framework and computer vision pipeline that provides a programmatic interface for performing real-time image analysis and object identification. It functions as a tool for loading weights, fine-tuning models, and executing inference on both static images and video feeds. The project serves as a converter that translates Darknet configurations and weights into TensorFlow graphs to enable retraining and deployment. It includes a model exporter that saves trained graphs into portable protobuf files for use on mobile and native devices. The system covers capabilit

MMdnn is a deep learning model converter and migrator designed to translate neural network architectures and weights between different frameworks such as TensorFlow, PyTorch, and Keras. It utilizes a standardized intermediate representation to decouple network structures and weights from specific framework implementations, enabling the transformation of pre-trained models across different environments. The project distinguishes itself by generating native Python reconstruction code from its intermediate representations, allowing models to be rebuilt and fine-tuned in target environments. It a

This project is a comprehensive instructional resource and course for building neural networks using PyTorch. It covers the fundamental building blocks of deep learning, including tensor manipulation, automatic differentiation, and the construction of modular neural network components. The repository serves as a technical guide for several specialized domains. It provides implementation details for computer vision tasks such as image classification, object detection, and semantic segmentation, as well as natural language processing workflows involving transformers, recurrent networks, and gen

यह प्रोजेक्ट YOLOv4 ऑब्जेक्ट डिटेक्शन फ्रेमवर्क का PyTorch इम्प्लीमेंटेशन है। यह न्यूरल नेटवर्क को प्रशिक्षित और डिप्लॉय करने के लिए एक सिस्टम प्रदान करता है जो छवियों और वीडियो स्ट्रीम के भीतर कई वस्तुओं की पहचान और पता लगाता है। फ्रेमवर्क में प्रशिक्षित वेट्स को यूनिवर्सल फॉर्मेट और हार्डवेयर-विशिष्ट अनुकूलित इंजनों में बदलने के लिए टूल्स शामिल हैं, जो विशेष रूप से ONNX और TensorRT का समर्थन करते हैं। इसमें लेटेंसी कम करने और थ्रूपुट बढ़ाने के लिए एक TensorRT इन्फरेंस ऑप्टिमाइज़र, और NVIDIA DeepStream स्ट्रीमिंग एनालिटिक्स पाइपलाइन के साथ संगत एक मॉडल आर्किटेक्चर शामिल है। यह सिस्टम मोज़ेक डेटा ऑगमेंटेशन के साथ मॉडल प्रशिक्षण को कवर करता है और कई इन्फरेंस इंजनों में रीयल-टाइम ऑब्जेक्ट डिटेक्शन का समर्थन करता है। यह TensorFlow में मॉडल रूपांतरण के लिए उपयोगिताएँ प्रदान करता है और डिप्लॉयमेंट के लिए स्टेटिक और डायनेमिक बैच कॉन्फ़िगरेशन दोनों का समर्थन करता है।

यह प्रोजेक्ट एक स्व-पर्यवेक्षित कंट्रास्टिव लर्निंग फ्रेमवर्क है जिसे मानव-प्रदत्त लेबल का उपयोग किए बिना छवियों से विज़ुअल प्रतिनिधित्व सीखने के लिए डीप लर्निंग मॉडल को प्रशिक्षित करने के लिए डिज़ाइन किया गया है। यह प्रीट्रेन्ड विज़ुअल प्रतिनिधित्व मॉडल विकसित करने के लिए एक प्रणाली प्रदान करता है जिसे डाउनस्ट्रीम कंप्यूटर विज़न कार्यों के लिए अनुकूलित किया जा सकता है। इस फ्रेमवर्क में अर्ध-पर्यवेक्षित छवि वर्गीकरण के लिए टूल शामिल हैं, जो सटीकता में सुधार के लिए बड़े लेबल रहित डेटासेट को छोटे लेबल वाले सेट के साथ जोड़ते हैं। इसमें फ्रोजन अभ्यावेदन के शीर्ष पर एक सरल रैखिक क्लासिफायर को प्रशिक्षित करके सीखे गए छवि सुविधाओं की गुणवत्ता का आकलन करने के लिए एक रैखिक जांच मूल्यांकन टूल भी शामिल है। कोडबेस बड़े बैच आकारों को संभालने के लिए वितरित डीप लर्निंग प्रशिक्षण और हार्डवेयर त्वरण को कवर करता है, साथ ही कोसाइन-डिके लर्निंग रेट शेड्यूलिंग और वेट-डिके रेगुलराइजेशन जैसे ऑप्टिमाइज़ेशन प्रिमिटिव्स को भी कवर करता है। यह मॉडल प्रबंधन के लिए उपयोगिताएं भी प्रदान करता है, जिसमें विभिन्न डीप लर्निंग फ्रेमवर्क प्रारूपों के बीच प्रीट्रेन्ड चेकपॉइंट्स का रूपांतरण और मॉडल तैनाती के लिए टूल शामिल हैं। कार्यान्वयन Jupyter Notebooks के संग्रह के रूप में प्रदान किया गया है।

ruvector is a Rust-based vector store and graph database designed for local inference and nearest neighbor searches. It utilizes a vector graph database architecture and a graph neural network index to refine search rankings through structural attention. The system includes a hardware-accelerated quantum circuit simulator for executing state-vector simulations and complex search patterns, alongside a WebAssembly inference engine for running vector search and model execution directly in web browsers. The project employs a cognitive container format that bundles models, data, and a bootable mic

IREE is an MLIR-based compiler toolchain and runtime designed to translate machine learning models from various frameworks into optimized binaries for execution across diverse hardware targets. It provides a unified pipeline to ingest models from PyTorch, TensorFlow, JAX, and ONNX, lowering them into a common intermediate representation for deployment on CPUs, GPUs, and bare-metal embedded systems. The project distinguishes itself through a bytecode virtual machine and a hardware abstraction layer that decouple high-level model logic from specific hardware instruction sets. It supports sophis