Search Results for "model-builder" - Page 2
Sort By:
Showing 54 open source projects for "model-builder"
View related business solutions-
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.
-
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
DeepSpeech
Open source embedded speech-to-text engine
DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers. DeepSpeech is an open-source Speech-To-Text engine, using a model trained by machine learning techniques based on Baidu's Deep Speech research paper. Project DeepSpeech uses Google's TensorFlow to make the implementation easier. A pre-trained English model is available for use and can be downloaded following the instructions in the usage docs. If you want to use the pre-trained English model for performing speech-to-text, you can download it (along with other important inference material) from the DeepSpeech releases page. -
2
Keras TCN
Keras Temporal Convolutional Network
...Performs better than LSTM/GRU on a vast range of tasks (Seq. MNIST, Adding Problem, Copy Memory, Word-level PTB...). Parallelism (convolutional layers), flexible receptive field size (possible to specify how far the model can see), stable gradients (backpropagation through time, vanishing gradients). The usual way is to import the TCN layer and use it inside a Keras model. The receptive field is defined as the maximum number of steps back in time from current sample at time T, that a filter from (block, layer, stack, TCN) can hit (effective history) + 1. ... -
3
BBQLinux
An Arch based Linux distribution for Android developers
BBQLinux is a user-friendly Linux distribution made for Android developers. It has everything on board to build AOSP or AOSP-based Distributions like CyanogenMod. BBQLinux is based on Arch Linux and is using a Rolling Release Development Model which means it’s getting continually updated and upgraded. It will never be necessary to re-install a later release of BBQLinux. BBQLinux is fully compatible with Arch Linux and is using the same package repos. -
4
Pretty Damn Quick (PDQ) analytically solves queueing network models of computer and manufacturing systems, data networks, etc., written in conventional programming languages. Generic or customized reports of predicted performance measures are output.
-
$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.
-
5
Age and Gender Estimation
Keras implementation of a CNN network for age and gender estimation
...Because the face images in the UTKFace dataset is tightly cropped (there is no margin around the face region), faces should also be cropped in demo.py if weights trained by the UTKFace dataset is used. Please set the margin argument to 0 for tight cropping. You can evaluate a trained model on the APPA-REAL (validation) dataset. We pose the age regression problem as a deep classification problem followed by a softmax expected value refinement and show improvements over direct regression training of CNNs. Our proposed method, Deep EXpectation (DEX) of apparent age, first detects the face in the test image and then extracts the CNN predictions from an ensemble of 20 networks on the cropped face. -
6
DeepCluster
Deep Clustering for Unsupervised Learning of Visual Features
DeepCluster is a classic self-supervised clustering-based representation learning algorithm that iteratively groups image features and uses the cluster assignments as pseudo-labels to train the network. In each round, features produced by the network are clustered (e.g. k-means), and the cluster IDs become supervision targets in the next epoch, encouraging the model to refine its representation to better separate semantic groups. This alternating “cluster & train” scheme helps the model gradually discover meaningful structure without labels. DeepCluster was one of the early successes in unsupervised visual feature learning, demonstrating that clustering-based reformulation can rival supervised baselines for many downstream tasks. ... -
7
ENAS in PyTorch
PyTorch implementation of "Efficient Neural Architecture Search
...It is primarily intended as a research and educational codebase, helping practitioners understand how ENAS works in practice and how to reproduce results on benchmark datasets. The project includes training scripts, model definitions, and search procedures that show the full workflow from architecture sampling to evaluation. Because ENAS relies on shared weights among candidate models, the implementation emphasizes efficiency and experiment reproducibility. -
8
Albedo
A recommender system for discovering GitHub repos
Albedo is an open-source recommender system aimed at helping developers discover GitHub repositories by learning from activity signals. It treats repositories and developers as a graph of interactions and applies large-scale matrix factorization to model affinities, with Apache Spark providing the distributed data processing. The project focuses on implicit feedback—stars, watches, and other engagement metrics—so it can build useful recommendations without explicit ratings. A reproducible setup and Makefile-driven workflow streamline tasks like spinning up services, loading datasets, training models, and generating candidate lists. ... -
9
TACO is a toolkit for building distributed control systems or any other distributed system. It is based on a C/C++ core. It is based on the client-server model. It supports writing clients and server on Unix+Windows. Clients and servers can be written in
-
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.
-
10
AutoBench
This program is a benchmark site data extraction util program
This program is a program that extracts the latest CPU, GPU, Drive and RAM performance scores and rankings from benchmark sites. The Output Data is saved as a csv, xlsx and xls file. CPU information is written by model name and score. GPU information is written by model name and score. Drive information is written by model name and score. RAM information is written by model name and score. -
11
BlackPack
Graphical RPM package builder
BlackPack is a utility to aid in creating installable RedHat packages (.rpm). The goal behind the project is to make developing for RedHat based Linux distributions more appealing, with an easy to use interface for packaging applications, artwork, media, themes, etc. -
12
BlockSparse
Efficient GPU kernels for block-sparse matrix multiplication
The blocksparse repository provides efficient GPU kernels (TensorFlow custom ops) for block-sparse matrix multiplication and convolution operations. The idea is to exploit block-level sparsity — i.e. treat matrices or weight tensors as composed of blocks, many of which may be zero or unused — to save compute and memory when sparsity patterns are structured. This is particularly useful in models like Sparse Transformers, where attention matrices or intermediate layers may adopt block-sparse... -
13
EasyRepo
Offline DVDs software repository builder for Ubuntu and derivatives
Easy Repo is a GUI tool for create APT repository on DVD disks for your Debian/Ubuntu system. It can be usefull to use Ubuntu Software Center without an internet connectivity. Program is written in python/GTK+ and considered to be portable to win/mac as well. -
14
RhinoLINUX Main Edition
Desktop Linux - custom built on Debian/Ubuntu/Mint upstream codebases
...RhinoLINUX can run multiple Windows versions side by side at the same time or install Windows apps, including MS Office ! Custom system tools such as Multisystem boot builder apps, Live USB creators, Backup tools etc. as well as our Remastering tools left in -
15
SDEdumper
Copy multiples feature classes in ArcSDE to a local file geodatabase
Why use it? You can create your own Python script using model builder, but you have to modify the script everytime you want to dump different tables. Using this script you only need to have a CSV with all the table names, that’s it. Purpose: It can be used as an archival and historical database It will make you ArcSDE database portable and shareable -
16
GlassBeadGame
Organizing the Knowledge of Humanity
...This project aims to make the expanse of human knowledge beautifully presentable and the exabytes of data navigable by an average user via the power of a Unified Data Model and 3d visualization layer for the Web. It will invert the top 3 layers of the OSI network model to make a 3-dimensional presentation layer with a peer-to-peer session layer for the Internet. For the curious, there is a simple demo that provides a small sense of the possibilities. Requires: VPython available here or see http://vpython.org. -
17
This Project aims to create a Linux Distribution focused on the IBM zOS system, it includes a set of Mainframe tools, based all in Linux Kernel modules, C and Python. -MainFrame Access Methods -ISPF menus -REXX scripting -RACF security -JCL Batch Job
-
18
DataFinder is a data management client developed in Python that primarily targets the management of scientific technical data. The system is able to handle large amounts of data and can be easily integrated in existing working environments.
-
19
Open TBroker aims to provide an open source implementation of a Tunnel Broker according to the model specified by RFC3053.
-
20
A metering and charge-back mechanism based on real time pricing (RTP) for the cloud services. This project caters to the need of a dynamic pay-per-use model in the cloud environment.
-
21
Java based multi-agent platform built on an organizational model (agent, group, role). MadKit provides general agent facilities (lifecycle management, message passing, distribution, ...), and allows high heterogeneity in agents.
-
22
Orange JeOS
Orange JeOS ("juice") is a small and secure Linux distribution
Orange JeOS ("juice") is a small and secure Linux distribution, based on CentOS and designed for use by hardware, software and virtual appliance builders. OJ-Builder Tools are used to build an Orange JeOS ISO entirely from public CentOS repository. Orange JeOS leverages the CentOS Linux distribution and allows building fully functioning software (and hardware and virtual) appliances in as little as 200 MB. -
23
AKIRA aims to create a C++ development framework to build cognitive architectures and complex artificial intelligent agents.Features:KQML,Fuzzy Logic,Neural Net,Fuzzy Cognitive Maps and DIPRA (a distributed BDI - Belief Desire Intention goals model)
-
24
The CCM Tools are CASE tools used for generating CORBA components, test components, and test programs based on source IDL files. Various target languages can be generated. Scripting language wrappers can also be generated to enable rapid prototyping.
-
25
