Search Results for "learning" - Page 2
Sort By:
Showing 46 open source projects for "learning"
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.
-
Full-stack observability with actually useful AI | 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
Consistent Depth
We estimate dense, flicker-free, geometrically consistent depth
Consistent Depth is a research project developed by Facebook Research that presents an algorithm for reconstructing dense and geometrically consistent depth information for all pixels in a monocular video. The system builds upon traditional structure-from-motion (SfM) techniques to provide geometric constraints while integrating a convolutional neural network trained for single-image depth estimation. During inference, the model fine-tunes itself to align with the geometric constraints of a... -
2
Super-résolution via CNN
Super resolution using a CNN, based on the work of the DGtal team
...This program will generate "model_epoch_ .pth" files corresponding to the model at epoch n, in a folder saved_model_u t_bs bs_tbs tbs_lr lr, where corresponds to the scale factor, bsthe size of the training batch, tbsthe size of the test batch and lrto the learning rate. Low res images should be located in a "dataset/input" folder, and high res targets in a "dataset/target" folder, where each different quality image has the same name in both folders. -
3
DeepFaceLab
The leading software for creating deepfakes
...DeepFaceLab is an open-source deepfake system that enables users to swap the faces on images and on video. It offers an imperative and easy-to-use pipeline that even those without a comprehensive understanding of the deep learning framework or model implementation can use; and yet also provides a flexible and loose coupling structure for those who want to strengthen their own pipeline with other features without having to write complicated boilerplate code. DeepFaceLab can achieve results with high fidelity that are indiscernible by mainstream forgery detection approaches. ... -
4
FastoCloud PRO
IPTV/NVR/CCTV/Video cloud https://fastocloud.com
IPTV/Video cloud Features: Cross-platform (Linux, MacOSX, FreeBSD, Raspbian/Armbian) GPU/CPU Encode/Decode/Post Processing Stream statistics CCTV Adaptive hls streams Load balancing Temporary urls HLS push EPG scanning Subtitles to text conversions AD insertion Logo overlay Video effects Relays Timeshifts Catchups Playlists Restream/Transcode from online streaming services like Youtube, Twitch Mozaic Many Outputs Physical Inputs Streaming Protocols File Formats Presets Vods/Series server-side support Pay per view channels Channels on demand HTTP Live Streaming (HLS) server-side support Public API, client server communication via JSON RPC Protocol gzip compression Deep learning video analysis Supported deep learning frameworks: Tensorflow NCSDK Caffe ML Hardware: -
$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.
-
5
Udeler
Udemy Course Downloader (GUI)
Udeler is an open source, cross-platform desktop application for downloading Udemy Courses. It makes viewing and learning from Udemy Courses a lot easier by downloading the courses to your desktop, allowing you to view them conveniently offline and at your own pace. Udeler downloads Udemy Courses straight to your Downloads folder, keeping the original structure of course content intact. It works a lot like most other download managers, but Udeler automates this process when downloading Udemy Courses. ... -
6
linjam
A cross platform NINJAM client with linear chain-streaming mode
...It is the much needed modern replacement for the aging platform-specific clients with many new enhancements. The highest goal of the LinJam project is to flatten the pro-audio learning-curve; easing the intimidation that most non-technical musicians experience when they are first introduced to NINJAM. Some of the ways proposed to accomplish this include: offering a minimal interface with some reasonable default settings, some normalizing/conditioning features such as auto-gain and limiter, and the option to elect a "sound man". ... -
7
PyTorch Natural Language Processing
Basic Utilities for PyTorch Natural Language Processing (NLP)
PyTorch-NLP is a library for Natural Language Processing (NLP) in Python. It’s built with the very latest research in mind, and was designed from day one to support rapid prototyping. PyTorch-NLP comes with pre-trained embeddings, samplers, dataset loaders, metrics, neural network modules and text encoders. It’s open-source software, released under the BSD3 license. With your batch in hand, you can use PyTorch to develop and train your model using gradient descent. For example, check out... -
8
YouTube-8M
Starter code for working with the YouTube-8M dataset
...The code demonstrates how to process frame-level features, train logistic and deep learning models, evaluate them using metrics like global Average Precision (gAP) and mean Average Precision (mAP), and export trained models for MediaPipe inference. -
9
OpenFace
A state-of-the-art facial behavior analysis toolkit
OpenFace is an advanced facial behavior analysis toolkit intended for computer vision and machine learning researchers, those in the affective computing community, and those who are simply interested in creating interactive applications based on facial behavior analysis. The OpenFace toolkit is capable of performing several complex facial analysis tasks, including facial landmark detection, eye-gaze estimation, head pose estimation and facial action unit recognition. -
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.
-
10
WxRecoderVideo
Based on VCamera, Imitating WeChat to record short videos
...The project typically combines Java and native components to handle performance-critical tasks such as encoding and file writing. It showcases how to manage audio and video synchronization during recording, ensuring consistent playback results. The architecture is structured as a learning resource, helping developers explore camera APIs, media codecs, and FFmpeg-style processing concepts. It also includes playback modules to review recorded content directly within the app. Overall, it serves as a practical example of implementing end-to-end video recording functionality on Android. -
11
PyQt5 Apps
Some useful apps based on PyQt5
PyQt5-Apps is a collection of desktop applications built using the PyQt5 framework, showcasing various graphical user interface implementations and utilities. The repository serves as a learning resource for developers interested in building cross-platform desktop applications with Python. It includes multiple small tools and demos that illustrate concepts such as window management, event handling, and UI design. The applications demonstrate how to integrate multimedia, file handling, and system interaction features within PyQt environments. ... -
12
KinoGlitch
Video glitch effects for Unity
...It emphasizes real-time performance and simple parameterization so you can animate intensity over time. The effects can be layered and tuned to match the mood of gameplay or cinematics. The repository’s clarity makes it a useful reference for developers learning to implement post-processing passes and stylized image effects in Unity. -
13
Scene is a computer vision framework that performs background subtraction and object tracking, using two traditional algorithms and three more recent algorithms based on neural networks and fuzzy classification rules. For each detected object, Scene sends TUIO messages to one or several client applications. The present release features GPU accelerated versions of all the background subtraction methods and morphological post processing of the object blobs with dilation and erosion filters,...
-
14
easyjasub
Tool to add furigana and in-line translation to Japanese subtitles
easyjasub (http://easyjasub.sf.net) is a tool to assist in understanding Japanese subtitles those who have a little knowledge of Japanese language, for language learning. It allows you to get subtitles with furigana and in-line translation, in several formats suitable for both video rendering and self-study Timing for the Japanese subtitles is used, the secondary subtitles may be repeated into multiple lines. The synchronization of input text subtitles is very important to properly associate them. ... -
15
mmpx
Mmpx easy convert video and trace FLV to AVI (MPEG-4) library h.263
Mmpx easy convert, on standard version 1.0, FLV (flash video) to AVI (MPEG-4/DIVX video). And player video/audio with your owner library h.263. In LINUX version , experimental program C++, to learning protocol h.263 with option trace step bit by bit. -
16
Black Hole Cortex
Sphere surface layers of visual cortex approach maximum info density
Near the surface (even horizon) of a black hole, there is maximum information density in units of squared plancks (and some translation to qubits). Similarly, our imagination is the set of all possible things we can draw onto our most dense layer of visual cortex in electricity patterns. Bigger layers have more neurons to handle those possibilities. A Black Hole Cortex is a kind of visual cortex that has density of neuron layers similar to density at various radius from a black hole. What we... -
17
Gorp
Easy Video Editor - graphical interface to non-linear video editor
Gorp is an easy-to-use non-linear video editor primarily driven using a graphical interface. It is intended as an entry level tool for video editing, but will provide enough flexibility for more advanced users. Currently it can read and write MPG1 and MPG2 files, and transform them on the way. The number of transforms available is limited, but will grow. View the video flow at any part of the flow diagram, step forward, backward etc to make sure that it is correct. Write your own... -
18
Player2edu
Flash-based player for e-learning content
Flash-based player for e-learning content. Created in AS3 and fully configurable in xml. -
19
The Python Computer Vision Framework is an opened project deisgned for all those interested in computer vision. It aims at making computer vision more easy and structured and matlab-free. It may also be used for other artistic and scientific areas.
-
20
This project aims to develop a tool to create DVD, hence the name; PyQtADA: Python and Qt another DVD Author. In linux there are very few tools to perform this functionality with high performance and a low learning curve for users.
-
21
A group of specific modules that allow to create and manage a simple distance learning system including audio/video and slide synchronization (in live streamed session too), slideshows, content management, teacher/student chat.
