Search Results for "deep" - Page 11
Sort By:
Showing 293 open source projects for "deep"
View related business solutions-
$300 Free Credits for Your Google Cloud ProjectsLaunch your next project with $300 in free Google Cloud credits—no strings attached. Test, build, and deploy without risk. Use your credits across the entire Google Cloud platform to find what works best for your needs. After your credits are used, continue with always-free tier services. Only pay when you're ready to scale. Sign up in minutes and start exploring.
-
Stop Storing Third-Party Tokens in Your DatabaseRolling your own OAuth token storage can be a security liability. Token Vault securely stores access and refresh tokens from federated providers and handles exchange and renewal automatically. Connected accounts, refresh exchange, and privileged worker flows included.
-
1
Accord.NET Framework
Scientific computing, machine learning and computer vision for .NET
The Accord.NET Framework provides machine learning, mathematics, statistics, computer vision, computer audition, and several scientific computing related methods and techniques to .NET. The project is compatible with the .NET Framework. NET Standard, .NET Core, and Mono. -
2
Orkney
Orkney Testframework
...Test steps are used like bricks to create test cases while test groups collect test cases and other test groups to create a test suite. Test cases are written in a simple text language thus allowing composition of cases from test steps without deep programming knowledge. Reports are created in text and in XML format, the latter are converted to a human readable form when using a standard web browser. -
3
TensorFlow World
Simple and ready-to-use tutorials for TensorFlow
...The explanations are present in the wiki associated with this repository. There are different motivations for this open source project. TensorFlow (as we write this document) is one of / the best deep learning frameworks available. The question that should be asked is why has this repository been created when there are so many other tutorials about TensorFlow available on the web? Deep Learning is in very high interest these days - there's a crucial need for rapid and optimized implementations of the algorithms and architectures. ... -
4
fast-neural-style
Feedforward style transfer
...It also provides insights into the underlying techniques used in neural style transfer, making it both a practical tool and a learning resource. By combining performance and quality, it enables creative applications in image processing and design. Overall, fast-neural-style showcases how deep learning can be used for real-time artistic transformations. -
Build Agents and Models on One PlatformGemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
-
5
Caffe
A fast open framework for deep learning
Caffe is an open source deep learning framework that’s focused on expression, speed and modularity. It’s got an expressive architecture that encourages application and innovation, and extensible code that’s great for active development. Caffe also offers great speed, capable of processing over 60M images per day with a single NVIDIA K40 GPU. It’s arguably one of the fastest convnet implementations around. -
6
Swift AI
The Swift machine learning library
Swift AI is a high-performance deep learning library written entirely in Swift. We currently offer support for all Apple platforms, with Linux support coming soon. Swift AI includes a collection of common tools used for artificial intelligence and scientific applications. A flexible, fully-connected neural network with support for deep learning. Optimized specifically for Apple hardware, using advanced parallel processing techniques. -
7
Grenade
Deep Learning in Haskell
Grenade is a composable, dependently typed, practical, and fast recurrent neural network library for concise and precise specifications of complex networks in Haskell. Because the types are so rich, there's no specific term level code required to construct this network; although it is of course possible and easy to construct and deconstruct the networks and layers explicitly oneself. Networks in Grenade can be thought of as a heterogeneous list of layers, where their type includes not only... -
8
Face Verification Experiment
Original Caffe Version for LightCNN-9. Highly recommend to use PyTorch
face_verification_experiment is a research repository focused on experiments in face verification using deep learning. It provides implementations and scripts for testing different neural network architectures and training strategies on face recognition and verification tasks. The project is designed to help researchers and practitioners evaluate the performance of models on standard datasets and explore techniques for improving accuracy. -
9
odtReportSQL
Defines a complete reports/documents system for WAMP applications
...Based on templates created using OpenOffice (.odt files): templates can be of any size (A4, A3...) and multipage. On templates:: - Simple substitution based on couples #field#/value - Blocks and nested blocks duplication (any deep) or deletion - Pictures substitution The HTML User Inteface is build by System and can be easy added at existing php applications. This system is DB driven, using 2 tables to define all templates To add a new document is only required to update DB. Sources in github https://github.com/msillano/odtReportSQL Install: download all files in www/my_app/ see install.txt file -
Stop Cyber Threats with VM-Series Next-Gen Firewall on AzureGain integrated visibility across all traffic in a single pass. Deploy Palo Alto Networks VM-Series to determine application identity and content while automating security policy updates via rich APIs.
-
10
PrettyTensor
Pretty Tensor: Fluent Networks in TensorFlow
Pretty Tensor is a high-level API built on top of TensorFlow that simplifies the process of creating and managing deep learning models. It wraps TensorFlow tensors in a chainable object syntax, allowing developers to build multi-layer neural networks with concise and readable code. Pretty Tensor preserves full compatibility with TensorFlow’s core functionality while providing syntactic sugar for defining complex architectures such as convolutional and recurrent networks. -
11
React Fiber Architecture
A description of React's new core algorithm, React Fiber
The React Fiber Architecture project is a detailed technical document that explains the internal design and behavior of React Fiber, the core algorithm that powers modern React rendering. Rather than being a traditional code library, it serves as an educational deep dive into how React manages updates, scheduling, and reconciliation under the hood. The document explores how Fiber replaces the older stack-based reconciliation algorithm with a more flexible system that breaks rendering work into incremental units. This enables advanced features such as interruptible rendering, prioritization of updates, and smoother user interfaces during complex operations. ... -
12
json4sapnw
Another JSON extension for SAP ABAP
...It comes in the customer exchange namespace /CEX/ and has to be installed as an SAP transport request. The addon supports object oriented JSON methods to process deep structured JSON data. Building JSON data from SAP data objects and parsing JSON data back to SAP data objects are supported. See the WIKI for some examples. Thanks to the SAP community and especially to Rüdiger Plantiko for the basic work (http://ruediger-plantiko.blogspot.de/2010/12/ein-json-parser-in-abap.html). Enjoy! ... -
13
deemon
Deemon Scripting Language
...With a fully packed standard library including support for file-io, threads, atomics, pipes, math, file-system, sockets, randomization, hashing, serialization, a wide selection of emulated c/c++ headers and more, deemon provides a suitable environment for any application. Syntax is easy to read and understand and is mostly based on the common languages such as c/c++, java and python, though for those fascinated by it, reaches very deep and allows for pleasingly beautiful code to be written. If you wish to learn deemon, download any package and take a look at 'lib/tut' Note: If you've already used v100, you'll be happy to see how much deemon has grown in the five months that have passed. Keep up to date with deemon at: https://github.com/GrieferAtWork/deemon -
14
CRFasRNN
Semantic image segmentation method described in the ICCV 2015 paper
CRF-RNN is a deep neural architecture that integrates fully connected Conditional Random Fields (CRFs) with Convolutional Neural Networks (CNNs) by reformulating mean-field CRF inference as a Recurrent Neural Network. This fusion enables end-to-end training via backpropagation for semantic image segmentation tasks, eliminating the need for separate, offline post-processing steps. -
15
Rendr
Render your Backbone.js apps on the client and the server
Rendr is a small library that allows you to run your Backbone.js apps seamlessly on both the client and the server. Allow your web server to serve fully-formed HTML pages to any deep link of your app, while preserving the snappy feel of a traditional Backbone.js client-side MVC app. We believe there has to be a better way to build rich web apps today. In the last few years, we've seen more of the application moved to the client-side, with JavaScript representations of views, templates, and models. This enables us to build interactive, native-style single-page apps, but splitting your app into two distinct codebases (often using different languages for client and server) also creates challenges for performance, maintainability, and SEO. ... -
16
iOS Tech Frontier
Tanslates high-quality iOS technology, open source libraries
iOS Tech Frontier is a curated, deep-dive repository of advanced technical knowledge around the iOS operating system and ecosystem, designed primarily for intermediate to advanced developers who want to understand beyond SDK basics and build highly performant, robust applications. Instead of simple how-to recipes, the project collects detailed explanations, system internals analyses, and real-world insights into core subsystems like memory management (ARC), threading and Grand Central Dispatch, Objective-C/Swift runtime behavior, UIKit rendering pipelines, and effective use of concurrency. ... -
17
Awesome Recurrent Neural Networks
A curated list of resources dedicated to RNN
A curated list of resources dedicated to recurrent neural networks (closely related to deep learning). Provides a wide range of works and resources such as a Recurrent Neural Network Tutorial, a Sequence-to-Sequence Model Tutorial, Tutorials by nlintz, Notebook examples by aymericdamien, Scikit Flow (skflow) - Simplified Scikit-learn like Interface for TensorFlow, Keras (Tensorflow / Theano)-based modular deep learning library similar to Torch, char-rnn-tensorflow by sherjilozair, char-rnn in tensorflow, and much more. ... -
18
MDA
Molecular Dynamics Analyzer (MDA)
MDA is a 3D single-particle tracking software that explicitly addresses fluorescence microscopy experiments deep in living specimens. It is capable of minimizing the systematic error that occurs with astigmatism-based 3D techniques owing to the aberrations induced by the refractive index mismatch. In contrast to existing techniques, the method determines the aberration directly from the acquired 2D image stream by exploiting the inherent particle movement and the redundancy introduced by the astigmatism. ... -
19
Human AI Net
a Human and Artificial Intelligence Network
...The main data format is, from xorlisp which is also in progress, immutable binary forest nodes, so if millions of people build that together nobody can damage or change anyone else's data since its all constant. You dont change variables. You create new data that points at existing constant data, as deep as you need it. I have mindmap lists, definitions, and 2 editable properties working that way with 2 kinds of event listeners that work locally. Its not a networked system yet, but the datastructs are ready to scale with it. -
20
Mori
ClojureScript's persistent data structures and supporting API
Mori brings ClojureScript's efficient persistent data structures and functional APIs into vanilla JavaScript, enabling immutability and functional programming patterns with performant collections in JS. The installed package contains a single optimized JavaScript file mori.js. Load mori in your Node.js programs as you would any other module. For vectors and maps we provide efficient thaw and freeze operations. All Mori maps and sets support all the non-mutating methods of the proposed ES6... -
21
Super CSV
A fast, programmer-friendly, free CSV library for Java
...This SourceForge page will remain, but with limited functionality (please go to GitHub to report issues and for project downloads). It is highly configurable, and supports reading and writing with POJOs, Maps and Lists. It also has support for deep-mapping and index-based mapping with POJOs, using the powerful Dozer extension. Its flexible 'Cell Processor' API automates data type conversions (parsing and formatting Dates, Integers, Booleans etc) and enforces constraints (mandatory columns, matching against regular expressions etc) - and it's easy to write your own if required. ... -
22
Immutable Sparse Wave Trees (WaveTree)
Realtime bigdata tool for bit strings up to 2^63 based on AVL forest
Realtime bigdata tool at the bit level based on immutable AVL forest which can be run in memory or, in future versions, as a merkle forest like a blockchain. Main object is a sparse bit string (Bits) that efficiently scales up to 2^63 bits normally compressed as forest has duplicated substrings. Bits objects support reading bit, byte, short, int, or long (Java primitives) at any bit index in 64 bit range. Example: instead of building a class to hold a header and then data, represent all of... -
23
ConvNetJS
Deep learning in Javascript to train convolutional neural networks
ConvNetJS is a Javascript library for training Deep Learning models (Neural Networks) entirely in your browser. Open a tab and you're training. No software requirements, no compilers, no installations, no GPUs, no sweat. ConvNetJS is an implementation of Neural networks, together with nice browser-based demos. It currently supports common Neural Network modules (fully connected layers, non-linearities), classification (SVM/Softmax) and Regression (L2) cost functions, ability to specify and train Convolutional Networks that process images, and experimental Reinforcement Learning modules, based on Deep Q Learning. ... -
24
CURRENNT
CUDA-enabled machine learning library for recurrent neural networks
CURRENNT is a machine learning library for Recurrent Neural Networks (RNNs) which uses NVIDIA graphics cards to accelerate the computations. The library implements uni- and bidirectional Long Short-Term Memory (LSTM) architectures and supports deep networks as well as very large data sets that do not fit into main memory. -
25
Novm
Experimental KVM-based VMM for containers, written in Go
...It showcases patterns like process-per-VM supervision, concise configuration, and direct mapping of devices needed for common development workloads. As a research vehicle, novm emphasizes hackability over feature completeness, making it useful for instrumentation experiments, educational deep dives, or bespoke CI sandboxes. Even though it’s not positioned as a drop-in for production hypervisors, it demonstrates how far a lean VM manager can go with modern kernel primitives.
