Search Results for "model"
Sort By:
Showing 37 open source projects for "model"
View related business solutions-
Define and Deliver Comprehensive Cybersecurity Services. Security threats continue to grow, and your clients are most likely at risk. Small- to medium-sized businesses (SMBs) are targeted by 64% of all cyberattacks, and 62% of them admit lacking in-house expertise to deal with security issues. Now technology solution providers (TSPs) are a prime target. Enter ConnectWise Cybersecurity Management (formerly ConnectWise Fortify) — the advanced cybersecurity solution you need to deliver the managed detection and response protection your clients require. Whether you’re talking to prospects or clients, we provide you with the right insights and data to support your cybersecurity conversation. From client-facing reports to technical guidance, we reduce the noise by guiding you through what’s really needed to demonstrate the value of enhanced strategy.
-
Whether natural disaster, cyberattack, or plain-old human error, data can disappear in the blink of an eye. ConnectWise BCDR (formerly Recover) delivers reliable and secure backup and disaster recovery backed by powerful automation and a 24/7 NOC to get your clients back to work in minutes, not days.
-
1
Video-subtitle-extractor
A GUI tool for extracting hard-coded subtitle (hardsub) from videos
... and Ali to complete text recognition locally. Support GPU acceleration, after GPU acceleration, you can get higher accuracy and faster extraction speed. (CLI version) No need for users to manually set the subtitle area, the project automatically detects the subtitle area through the text detection model. Filter the text in the non-subtitle area and remove the watermark (station logo) text. -
2
Real-ESRGAN GUI
Cross-platform GUI for image upscaler Real-ESRGAN
... arm64single-architecture applications by themselves. Real-ESRGAN can only enlarge the input image with a fixed 2-4x magnification (related to the selected model). This functionality is achieved by downsampling using a conventional scaling algorithm after multiple calls to Real-ESRGAN. Split each frame of the GIF and record the duration, zoom in one by one and then merge. Drag an image file or directory to any position in the window, and its path can be automatically set as the input. -
3
MeshLab
The open source mesh processing system
MeshLab is an open-source, portable, and extensible system for the processing and editing of unstructured large 3D triangular meshes. It is aimed to help the processing of the typical not-so-small unstructured models arising in 3D scanning, providing a set of tools for editing, cleaning, healing, inspecting, rendering and converting this kind of meshes. MeshLab is mostly based on the open source C++ mesh processing library VCGlib developed at the Visual Computing Lab of ISTI - CNR. VCG can... -
4
MediaPipe
Cross-platform, customizable ML solutions for live and streaming media
MediaPipe offers open-source cross-platform, customizable ML solutions for live and streaming media. Provides segmentation masks for prominent humans in the scene. MediaPipe Face Mesh is a face geometry solution that estimates 468 3D face landmarks in real-time even on mobile devices. It employs machine learning (ML) to infer the 3D surface geometry, requiring only a single camera input without the need for a dedicated depth sensor. Utilizing lightweight model architectures together with GPU... -
Chat with your business data with Looker. More than just a modern business intelligence platform, you can turn to Looker for self-service or governed BI, build your own custom applications with trusted metrics, or even bring Looker modeling to your existing BI environment.
-
5
SuperImage
Sharpen your low-resolution pictures with the power of AI upscaling
... and Real-ESRGAN. The input image is processed in tiles on the device GPU, using a pre-trained Real-ESRGAN model. The tiles are then merged into the final high-resolution image. This application requires Vulkan or OpenCL support and Android 7 or above. -
6
AI Models
A repository of trained models
All models (at least currently) are supported by chaiNNer, an upscaling GUI that allows for both very simple and very complex tasks to be completed in a nice manner where you "chain" nodes together. Highly recommended for images. If you're looking to upscale videos using the models then use enhancr simply due to the fact that it supports TensorRT, which will allow you to upscale videos at incredible speeds! The GUI is one of the best looking applications out there and is personally my go to... -
7
Segmentation Models
Segmentation models with pretrained backbones. PyTorch
... results (higher metric score and faster convergence). It is not necessary in case you train the whole model, not only the decoder. Pytorch Image Models (a.k.a. timm) has a lot of pretrained models and interface which allows using these models as encoders in smp, however, not all models are supported. Input channels parameter allows you to create models, which process tensors with an arbitrary number of channels. -
8
G2SConverter
Convert models from GoldSource engine to Source engine with AI
.... After the Upscaling procedure, the texture is deblured using the Scale-recurrent Network for Deep Image Deblurring. An example of a processed texture is shown in the following image (parameters used: scaling-factor = 4 and deblur iterations = 4) besides upscaling and debluring the utility also generates normal maps for each texture. This is implemented using the DeepBump by HugoTiny model. Examples of normal maps are shown in the following images. -
9
A multimedia authoring and processing framework and a video playout server for television broadcasting.
-
From nurturing a single PCB seedling to cultivating intricate systems, for over 30 years our industry-leading, patented automated electronic design analysis & optimization software suite has empowered the growth of robust, reliable, and efficient product designs, trusted by clients worldwide.
-
10
VSGAN
VapourSynth Single Image Super-Resolution Generative Adversarial
Single Image Super-Resolution Generative Adversarial Network (GAN) which uses the VapourSynth processing framework to handle input and output image data. Transform, Filter, or Enhance your input video, or the VSGAN result with VapourSynth, a Script-based NLE. You can chain models or re-run the model twice-over (or more). Have low VRAM? Don’t worry! The Network will be applied in quadrants of the image to reduce up-front VRAM usage. You can use any RGB video input, including float32 (e.g., RGBS... -
11
Easy Upscale
A simple image upscaler application using EDSR, ESPCN, FSRCNN, etc.
This application was made to fulfill the assignment for the Data Structures course. The concept of the application is an application to upgrade/enhance image quality. The main theme is queues, we implement circular queues for pooling/storing a list of images to be upscaled. Gui creation is made manually using the tkinter library. For the upscale process itself, it uses the OpenCV library with a model obtained from open source. Checked using vermin. Minimum required versions: 3.6 Incompatible... -
12
Robust Video Matting (RVM)
Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX
We introduce a robust, real-time, high-resolution human video matting method that achieves new state-of-the-art performance. Our method is much lighter than previous approaches and can process 4K at 76 FPS and HD at 104 FPS on an Nvidia GTX 1080Ti GPU. Unlike most existing methods that perform video matting frame-by-frame as independent images, our method uses a recurrent architecture to exploit temporal information in videos and achieves significant improvements in temporal coherence and... -
13
AviSynth AiUpscale v1.2.0
AviSynth+ implementation of Super-Resolution Convolutional Neural
... for training super-resolution networks, including those tested here. Note however that as an exception to this, the Anime4K models were trained using the average area downsampling method. The AiUpscale models used for all datasets were the "Photo" models, except for the Manga109 dataset for which the "LineArt" models were used. In the same way, the Waifu2x cunet model was used for the Manga109 dataset, and the upconv_7 model for the rest. -
14
Render32
Command-line video compositing and audio mixing tools
Render is a program for creating composite BMP image sequences. These images are composited as specified in a text configuration file. Mixer is a program for mixing film soundtracks. It accepts input files in WAV format and outputs a mixed soundtrack in WAV format. Each input channel can contain one or more audio files that are edited and mixed using a cue sheet. The maximum number of channels is a compile-time parameter. -
15
Super-résolution via CNN
Super resolution using a CNN, based on the work of the DGtal team
Super-resolution using a CNN, based on the work of the DGtal team. First of all, an Nvidia graphics card (neither AMD nor Intel integrated) is highly recommended to parallelize the CNN. You will then need to install CUDA. No CUDA = dozens of times slower. 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... -
16
DeepFaceLab
The leading software for creating deepfakes
DeepFaceLab is currently the world's leading software for creating deepfakes, with over 95% of deepfake videos created with DeepFaceLab. 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... -
17
Talkie
Talking 3D character for your stream
Full source code and 3D model for a talking 3D character, tweak as you need. Useful for streaming/videos when you don't want to show your face. Uses your mic input to move the mouth* You can provide your own 3D model with a jaw bone. This is not intended for end users. No executable is provided. You will need to have a 3D head modeled, with armature attached and a labeled jaw bone (unless you just want to use the default green sphere). Also some idea on how to use GODOT would be an asset... -
18
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... -
19
The Integrating Vision Toolkit (IVT) is a powerful and fast C++ computer vision library with an easy-to-use object-oriented architecture. It offers its own multi-platform GUI toolkit. OpenCV is integrated optionally. Website: http://ivt.sourceforge.net
-
20
This is a MATLAB model of an end-to-end chain compliant to the DVB-T2 standard (ETSI EN 302 755 available from www.etsi.org). It was originally developed within the DVB consortium (www.dvb.org) by AICIA, BBC, Pace, Panasonic and SIDSA.
-
21
Remote control DLP projector NEC in VBS
Remote Control DLP projector from NEC projector VTxx VBS script
VBS-script for a remote control the projector through the converter RS-485/RS-232 over RS-485 network with voice actions (on-off, volume control, navigation and exit). Since its own software projector does not involve the use of an RS-485 interface and the ability to control the direction of reception and transmission, the necessary converters as converters with auto control, suitable, for example, ovenovskie model AC3-M-024 (without their own address). If necessary, the networking... -
22
onet
OctopusNet - SAT>IP Server with various possibilities
The High-End Networktuner - Octopus Net The Octopus Net is streaming LiveTV to IPTV-Ready devices in the local network. It makes so many devices to a FullHD (*1) receiver for satellite television and cable television. Thereby will send the FTA Channels (*2) in FullHD in the LAN or WLAN Network. Up to 4 streams - depending on model - may be used simultaneously on stationary and mobile devices. The to-use client software (*3) is for the operating systems iOS (iPhone, iPad), Android, Mac OS... -
23
UPNPLib-mobile
Java/Android library for port mapping on UPnP routers
This library allows to discover UPnP-compatible routers on the local network, get some basic router information, including model and version number, external and internal interfaces addresses, forwarded ports list. Library allows to add new and delete existing port mappings. UPNPLib-mobile is the port of the abandoned UPNPLib project developed by "sbbi". Unlike the original, UPNPLib-mobile intended to be used for Android software development. For more details about original UPNPLib... -
24
Pianissimo
A java 3D project for live rendering of a MIDI piano performance
This project was started as a Masters project back in 2006. I completed the project as part of my dissertation, and produced software to render Maya script (MEL) to animate a piano model I'd also created. From this I produced a number of videos, which I uploaded periodically to YouTube. Following numerous request I attempted to create a standalone application to playback MIDI performances without the need for a 3rd party 3d modelling/rendering application such as Maya. Given my original... -
25
Linux device driver for the EasyCAP Model DC60, with inputs CVBS, S-VIDEO, AUDIO(L), AUDIO(R), and for the EasyCAP002, with four CVBS inputs and microphone input. The USB ID is 05e1:0408 and the manufacturer is Syntek Semiconductor Co., Ltd.