Search Results for "training"
Sort By:
Showing 26 open source projects for "training"
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.
-
$300 in Free Credit Towards Top Cloud ServicesStart your project in minutes. After credits run out, 20+ products include free monthly usage. Only pay when you're ready to scale.
-
1
SCAIL
Towards Studio-Grade Character Animation via In-Context Learning of 3D
...Given its listing alongside other ZAI projects like speech recognition and text-to-speech systems, SCAIL likely emphasizes scalable, composable AI learning frameworks that support researchers and practitioners in experimenting with learning algorithms, datasets, and model components. The repository structure suggests a focus on flexibility and extensibility, with potential integration into other ZAI tooling for training or analysis. -
2
xeokit SDK
Open source JavaScript SDK for viewing high-detail 3D BIM
xeokit is an open-source 3D graphics SDK from xeolabs for BIM and AEC. Built to view huge models in the browser. Used by industry leaders. Visualize complex, federated AEC models at full precision, in all major browsers, including mobile. A complete JavaScript graphics toolkit for building BIM and AEC viewing applications. Open source components to build your own product, your way. Keep everything on your own servers. Get your models on the Web using a toolkit of production-proven components... -
3
Habitat-Sim
A flexible, high-performance 3D simulator for Embodied AI research
Habitat-Sim is a high-performance 3D simulator for embodied AI research, designed to run photorealistic indoor environments at thousands of frames per second. It offers GPU-accelerated rendering and a flexible sensor suite—RGB, depth, semantic segmentation, and more—so agents can perceive and act in realistic scenes. The engine is written in C++ with Python bindings and integrates physics, navigation meshes, and shortest-path planners to support tasks like point-goal navigation,... -
4
VGGSfM
VGGSfM: Visual Geometry Grounded Deep Structure From Motion
VGGSfM is an advanced structure-from-motion (SfM) framework jointly developed by Meta AI Research (GenAI) and the University of Oxford’s Visual Geometry Group (VGG). It reconstructs 3D geometry, dense depth, and camera poses directly from unordered or sequential images and videos. The system combines learned feature matching and geometric optimization to generate high-quality camera calibrations, sparse/dense point clouds, and depth maps in standard COLMAP format. Version 2.0 adds support... -
Go From AI Idea to AI App FastAccess Gemini 3 and 200+ models. Build chatbots, agents, or custom models with built-in monitoring and scaling.
-
5
AnimateDiff
Plug-n-play module turning text-to-image models into animation
AnimateDiff is an open-source project designed to enhance text-to-image diffusion models by adding animation capabilities. It allows users to turn static images generated by popular text-to-image models into animated sequences without requiring additional model training. This plug-and-play tool is compatible with a wide range of community models and facilitates the generation of animation directly from pre-existing text-to-image models. It supports various configurations to create animations with different visual styles, providing flexibility and ease of use for developers and artists interested in exploring dynamic, AI-generated animations. -
6
MMDeploy
OpenMMLab Model Deployment Framework
...All kinds of modules in the SDK can be extended, such as Transform for image processing, Net for Neural Network inference, Module for postprocessing and so on. Install and build your target backend. ONNX Runtime is a cross-platform inference and training accelerator compatible with many popular ML/DNN frameworks. Please read getting_started for the basic usage of MMDeploy. -
7
DALL-E 2 - Pytorch
Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis
...Specifically, this repository will only build out the diffusion prior network, as it is the best performing variant (but which incidentally involves a causal transformer as the denoising network) To train DALLE-2 is a 3 step process, with the training of CLIP being the most important. To train CLIP, you can either use x-clip package, or join the LAION discord, where a lot of replication efforts are already underway. Then, you will need to train the decoder, which learns to generate images based on the image embedding coming from the trained CLIP. -
8
Grabber of Pictures
Quick search and download pictures from Google Images
...Cross platform application (Windows, Linux and MacOS) User friendly and multilingual interface Search for an unlimited number of pictures Search for a custom number of pictures Custom selecting images for download Batch image search by several keywords and phrases separated by commas Downloading pictures in several streams Save/reset your image search configuration Drag and drop image from preview to any destination (folder, video editor, etc.) The use of grabber Grabber of Pictures allows to download Google images for collecting data for training neural networks, a selection of images for media projects, Youtube videos, etc -
9
DeepMind Lab
A customizable 3D platform for agent-based AI research
...To enable compiler optimizations, pass the flag --compilation_mode=opt, or -c opt for short, to each bazel build, bazel test and bazel run command. The flag is omitted from the examples here for brevity, but it should be used for real training and evaluation where performance matters. DeepMind Lab ships with an example random agent in python/random_agent.py which can be used as a starting point for implementing a learning agent. -
Go from Code to Production URL in SecondsSkip the Kubernetes configs. Cloud Run handles HTTPS, scaling, and infrastructure automatically. Two million requests free per month.
-
10
Linux-Intelligent-Ocr-Solution
Easy-OCR solution and Tesseract trainer for GNU/Linux
...A Tesseract Trainer GUI is also shipped with this package. Forum : https://groups.google.com/forum/#!forum/lios Video Tutorial : https://www.youtube.com/playlist?list=PLn29o8rxtRe1zS1r2-yGm1DNMOZCgdU0i Tesseract Training Tutorial (beta) : https://www.youtube.com/watch?v=qLpCld4cdtk Source Code Github : https://github.com/Nalin-x-Linux/lios-3 Gitlab : https://gitlab.com/Nalin-x-Linux/lios-3 User guide is available in download page -
11
Image Super-Resolution (ISR)
Super-scale your images and run experiments with Residual Dense
...This project contains Keras implementations of different Residual Dense Networks for Single Image Super-Resolution (ISR) as well as scripts to train these networks using content and adversarial loss components. Docker scripts and Google Colab notebooks are available to carry training and prediction. Also, we provide scripts to facilitate training on the cloud with AWS and Nvidia-docker with only a few commands. When training your own model, start with only PSNR loss (50+ epochs, depending on the dataset) and only then introduce GANS and feature loss. This can be controlled by the loss weights argument. The weights used to produce these images are available directly when creating the model object. ... -
12
Exposure
Learning infinite-resolution image processing with GAN and RL
...ACM Transactions on Graphics (presented at SIGGRAPH 2018) Exposure is originally designed for RAW photos, which assumes 12+ bit color depth and linear "RGB" color space (or whatever we get after demosaicing). jpg and png images typically have only 8-bit color depth (except 16-bit pngs) and the lack of information (dynamic range/activation resolution) may lead to suboptimal results such as posterization. Moreover, jpg and most pngs assume an sRGB color space, which contains a roughly 1/2.2 Gamma correction, making the data distribution different from training images (which are linear). Exposure is just a prototype (proof-of-concept) of our latest research, and there are definitely a lot of engineering efforts required to make it suitable for a real product. -
13
House3D
A Realistic and Rich 3D Environment
...Each environment includes fully labeled 3D objects, allowing agents to perceive and interact with their surroundings through multiple sensory modalities including RGB images, depth maps, semantic segmentation masks, and top-down maps. The simulator is optimized for high-performance rendering, achieving thousands of frames per second to enable efficient large-scale training of RL agents. House3D has served as the foundation for several influential research projects such as RoomNav (for concept-based navigation) and Embodied Question Answering (EQA). -
14
Accord.NET Framework
Machine learning, computer vision, statistics and computing for .NET
...It can be used on Microsoft Windows, Xamarin, Unity3D, Windows Store applications, Linux or mobile. After merging with the AForge.NET project, the framework now offers a unified API for learning/training machine learning models that is both easy to use and extensible. -
15
Training Image Operators from Samples
Tools to train Image Operators automatically from a set of samples.
TRIOS - Training Image Operators from Samples is a set of tools to bring Image Processing closer to scientists in general. It is capable of estimating an operator between two images using only pairs of samples that contain an input image and the desired output. The operator is saved to a file and can be applied to any image. -
16
tracking.js
A modern approach for Computer Vision on the web
The tracking.js library brings different computer vision algorithms and techniques into the browser environment. By using modern HTML5 specifications, we enable you to do real-time color tracking, face detection and much more, all that with a lightweight core (~7 KB) and intuitive interface. To get started, download the project. This project includes all of the tracking.js examples, source code dependencies you'll need to get started. Unzip the project somewhere on your local drive. The... -
17
Gamera is a framework for the creation of structured document analysis applications by domain experts. It combines a programming library with GUI tools for the training and interactive development of recognition systems.
-
18
Screen Recorder Std
records video of on-screen activity.
...It can record and insert picture-in-picture video, so you can record your victories and post the clips online with embedded video of yourself while playing, or insert instructions and comments to create educational and training videos. Screen Recorder Std also offers Draw-on-Screen, customizable opacity, and file conversion capabilities. -
19
Pace & Place is an application for managing and visualizing GPS data and sports training data. It empowers the user to track training events and combine them with geographic data. Map, waypoint, track visualizations and geo-referencing of photos.
-
20
Foad is an open source software which receive an EKG Signal from scanner, WFDB database or heart sensors. Finding patient disease started by taking Fourier transform (FFT) from input signal and extract a single cycle. Based on some heuristic algorithm the most important feature like P , Q , R , S , T captured and feed to trained neural network. and so the final decision made by CNN library. As mentioned before this software also capable do some image processing on scanned paper to lower...
-
21
Hough Transformation(DELPHI/PASCAL CODE)
image processing source code - hough alogrithm
...In the actual project state you may see a line and circle detection - working only with simple images as the Hough accumulator post processing is not yet implemented. This project is looking for support and the currect version is just for training and teaching purpose ! remarks: * Now this projects provides a complete DELPHI project ready to compile and a *.exe for fast evaluation of the code performance * would like to see a port to LARZARUS Free Pascal - feel free to post your experiemence in the forum -
22
A java webstart application that attempts to create cubism style artwork through the layering of semi-transparent polygons via a training feedback loop. Produces increasingly realistic work though hill climbing.
-
23
GPU library for simple development of OpenGL-based GPGPU applications, offscreen rendering and shading techniques.
-
24
With this programm, you can create diagramms of player formations for soccer-games. It has been created to prepare and support training lessons. The german project-name "Fussballtrainer" means soccer coach and refers to the target-group.
-
25
FliteTutor is currently merely a concept for an interactive training enhancement to the free flight simulator FlightGear, the purpose will be to provide basic tutorials within FlightGear about its general usage and also specific topics. (check homepage)
