Search Results for "convolution"
Sort By:
Showing 62 open source projects for "convolution"
View related business solutions-
Veeam Data Platform v13.1 - Get Your Free TrialTry Veeam Data Platform today. Experience the unified platform that's secure by design, portable by default, and proven to recover clean, fast, and anywhere.
-
Custom VMs From 1 to 96 vCPUs With 99.95% UptimeLive migration and automatic failover keep workloads online through maintenance. One free e2-micro VM every month.
-
1
ImageFiltering.jl
Julia implementations of multidimensional array convolution
Julia implementations of multidimensional array convolution and nonlinear stencil operations. ImageFiltering implements blurring, sharpening, gradient computation, and other linear filtering operations, as well nonlinear filters like min/max. -
2
DSP.jl
Filter design, periodograms, window functions
DSP.jl provides a number of common digital signal processing routines in Julia. -
3
Watermark-Removal
Machine learning image inpainting task that removes watermarks
...The system analyzes an image containing a watermark and attempts to reconstruct the underlying visual content so that the watermark is removed while preserving the original appearance of the image. The project uses neural network models inspired by research in contextual attention and gated convolution, which are methods commonly applied to image restoration tasks. Through these techniques, the model learns to identify regions of the image affected by the watermark and generate realistic replacements for the missing visual information. The repository contains code for preprocessing images, training the model, and running inference on images to automatically remove watermark artifacts. -
4
Compute Library
The Compute Library is a set of computer vision and machine learning
The Compute Library is a set of computer vision and machine learning functions optimized for both Arm CPUs and GPUs using SIMD technologies. The library provides superior performance to other open-source alternatives and immediate support for new Arm® technologies e.g. SVE2. -
$300 Free Credits to Build on Google CloudPut your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
-
5
bild
Image processing algorithms in pure Go
...It uses packages from the standard library whenever possible to reduce dependency use and development abstractions. All operations return image types from the standard library. Package convolution provides the functionality to create and apply a kernel to an image. Package effect provides the functionality to manipulate images to achieve various looks. Package histogram provides basic histogram types and functions to analyze RGBA images. Package paint provides functions to edit a group of pixels on an image. Package parallel provides helper functions for the dispatching of parallel jobs. -
6
ThinkDSP
Digital Signal Processing in Python, by Allen B. Downey
Think DSP is an educational Python project that teaches digital signal processing through executable examples rather than starting with heavy mathematical formalism. It accompanies Allen B. Downey’s book and organizes most lessons as Jupyter notebooks. Readers work directly with waves, spectra, harmonics, filtering, convolution, and other signal-processing concepts. Early exercises show how to decompose sounds, modify frequency components, and synthesize new audio. The repository includes chapter notebooks, solution notebooks, sample sound files, book sources, and reusable Python code. Lessons can run online through Google Colab or Binder, or locally with Conda or Poetry. ... -
7
Pytorch-toolbelt
PyTorch extensions for fast R&D prototyping and Kaggle farming
A pytorch-toolbelt is a Python library with a set of bells and whistles for PyTorch for fast R&D prototyping and Kaggle farming. Easy model building using flexible encoder-decoder architecture. Modules: CoordConv, SCSE, Hypercolumn, Depthwise separable convolution and more. GPU-friendly test-time augmentation TTA for segmentation and classification. GPU-friendly inference on huge (5000x5000) images. Every-day common routines (fix/restore random seed, filesystem utils, metrics). Losses: BinaryFocalLoss, Focal, ReducedFocal, Lovasz, Jaccard and Dice losses, Wing Loss and more. Extras for Catalyst library (Visualization of batch predictions, additional metrics). ... -
8
MIVisionX
Set of comprehensive computer vision & machine intelligence libraries
MIVisionX toolkit is a set of comprehensive computer vision and machine intelligence libraries, utilities, and applications bundled into a single toolkit. AMD MIVisionX delivers highly optimized open-source implementation of the Khronos OpenVX™ and OpenVX™ Extensions along with Convolution Neural Net Model Compiler & Optimizer supporting ONNX, and Khronos NNEF™ exchange formats. The toolkit allows for rapid prototyping and deployment of optimized computer vision and machine learning inference workloads on a wide range of computer hardware, including small embedded x86 CPUs, APUs, discrete GPUs, and heterogeneous servers. ... -
9
FXRoute
FXRoute is a Linux audio routing and DSP platform for stereo and subwo
FXRoute is an open-source Linux audio platform for playback, routing, measurement and DSP. It supports stereo, 2.1 and 2.2 systems, room/subwoofer optimization, PEQ and convolution, internet radio, local music libraries and streaming services including Spotify, Qobuz and TIDAL. -
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.
-
10
CalCurve
Load headphone calibration files
CalCurve loads local headphone calibration files and applies them as convolution correction. It accepts FIR WAV files directly, or TXT/CSV correction curves which are converted internally to FIR. -
11
BoofCV
BoofCV is an open source Java library for real-time computer vision.
...Written from scratch for ease of use and high performance, it provides both basic and advanced features needed for creating a computer vision system. Functionality include optimized low level image processing routines (e.g. convolution, interpolation, gradient) to high level functionality such as image stabilization. Released under an Apache 2.0 license for both academic and commercial use. -
12
pyisocalc
Isotopic pattern calculator in python 3.x
An isotopic pattern calculator written in Python 3. Given a chemical formula, it calculates the full isotopic distribution and simulates a mass spectrum. Dependencies: Python 3.6+, numpy, matplotlib, tkinter. The old python 2.x code has been updated and given a GUI. It's also a lot faster now. -
13
Make-A-Video - Pytorch (wip)
Implementation of Make-A-Video, new SOTA text to video generator
...The gist of the paper comes down to, take a SOTA text-to-image model (here they use DALL-E2, but the same learning points would easily apply to Imagen), make a few minor modifications for attention across time and other ways to skimp on the compute cost, do frame interpolation correctly, get a great video model out. Passing in images (if one were to pretrain on images first), both temporal convolution and attention will be automatically skipped. In other words, you can use this straightforwardly in your 2d Unet and then port it over to a 3d Unet once that phase of the training is done. -
14
Creatools Piano XS
Sample based piano virtual instrument
Is the third generation of a free and opensource virtual piano project built on HISE open source framework. It is built and developed with an aim to make a contribution towards free music education and creative freedom and it is therefore licensed under GPLv3 license. for more info: https://musictop69.wixsite.com/creatools -
15
Freeverb3_vst
Freeverb3 DSP VST effect plugins
The Freeverb3VST is a package of VST DSP effect plugins utilizing the Freeverb3 signal processing library. Many types of audio processing effects including high quality reverbs and impulse response convolution processors are available. -
16
spaGO
Self-contained Machine Learning and Natural Language Processing lib
A Machine Learning library written in pure Go designed to support relevant neural architectures in Natural Language Processing. Spago is self-contained, in that it uses its own lightweight computational graph both for training and inference, easy to understand from start to finish. The core module of Spago relies only on testify for unit testing. In other words, it has "zero dependencies", and we are committed to keeping it that way as much as possible. Spago uses a multi-module workspace to... -
17
libdspl-2.0
libdspl-2.0 is opensource cross-platform digital signal processing alg
libdspl-2.0 — opensource cross-platform digital signal processing algorithm library, written in C language. Distributed under LGPL v3 license. This allows to use this library in all applications with dynamic linking. -
18
texturize
Generate photo-realistic textures based on source images
...It's useful in the context of computer graphics if you want to make variations on a theme or expand the size of an existing texture. This software is powered by deep learning technology, using a combination of convolution networks and example-based optimization to synthesize images. We're building texturize as the highest-quality open source library available! The examples are available as notebooks, and you can run them directly in-browser thanks to Jupyter and Google Colab. -
19
T81 558
Applications of Deep Neural Networks
...Deep learning allows a neural network to learn hierarchies of information in a way that is like the function of the human brain. This course will introduce the student to classic neural network structures, Convolution Neural Networks (CNN), Long Short-Term Memory (LSTM), Gated Recurrent Neural Networks (GRU), General Adversarial Networks (GAN) and reinforcement learning. Application of these architectures to computer vision, time series, security, natural language processing (NLP), and data generation will be covered. High-Performance Computing (HPC) aspects will demonstrate how deep learning can be leveraged both on graphical processing units (GPUs), as well as grids. -
20
DiffEqOperators.jl
Linear operators for discretizations of differential equations
...For the operators, both centered and upwind operators are provided, for domains of any dimension, arbitrarily spaced grids, and for any order of accuracy. The cases of 1, 2, and 3 dimensions with an evenly spaced grid are optimized with a convolution routine from NNlib.jl. Care is taken to give efficiency by avoiding unnecessary allocations, using purpose-built stencil compilers, allowing GPUs and parallelism, etc. Any operator can be concretized as an Array, a BandedMatrix or a sparse matrix. -
21
DeepLabv3 Plus
Encoder-Decoder with Atrous Separable Convolution
DeepLabv3 Plus is a PyTorch implementation of DeepLabv3+ for semantic segmentation. It implements the encoder-decoder architecture with atrous separable convolution and provides a practical workflow for training, prediction, and mIoU evaluation. The repository supports VOC-style segmentation datasets and includes utilities for annotation generation, JSON dataset conversion, model summary inspection, prediction, and metric calculation. It provides pretrained weight workflows for MobileNetV2 and Xception backbones and notes that the correct backbone should be selected during training and prediction. ... -
22
ASRT Speech Recognition
A Deep-Learning-Based Chinese Speech Recognition System
ASRT is an end-to-end deep-learning Chinese ASR system built with TensorFlow/Keras, using convolution + CTC and a Max-Entropy HMM language model. It provides a REST/gRPC server backend and client SDKs in multiple languages (Python, Java, Go, Windows). Notably lightweight, it performs well without needing GPU acceleration and runs across platforms, targeting developers and researchers building Chinese voice interfaces. -
23
MeshCNN in PyTorch
Convolutional Neural Network for 3D meshes in PyTorch
MeshCNN is a deep learning framework designed specifically for processing 3D triangular mesh data using convolutional neural networks. Unlike traditional CNNs that operate on images or voxel grids, MeshCNN performs convolution operations directly on the edges of mesh structures. This design allows the model to capture geometric relationships between mesh elements while preserving the underlying topology of 3D shapes. The framework introduces specialized layers such as edge-based convolution, mesh pooling, and mesh unpooling operations that enable hierarchical feature learning on mesh surfaces. ... -
24
AlphaPlot
Interactive scientific graphing and data analysis software.
...The spreadsheets as well as graphs and note windows are gathered in a project and can be organized using folders. The built-in analysis operations include column/row statistics, (de)convolution, FFT and FFT-based filters. Scripting Console support in-place evaluation of mathematical expressions and scrtipting interface to ECMAScript like dynamic scripting language(java script). The GUI of the application uses the Qt toolkit. Periodic test builds are available here http://alphaplot.sourceforge.net/test-build.html -
25
Minkowski Engine
Auto-diff neural network library for high-dimensional sparse tensors
The Minkowski Engine is an auto-differentiation library for sparse tensors. It supports all standard neural network layers such as convolution, pooling, unspooling, and broadcasting operations for sparse tensors. The Minkowski Engine supports various functions that can be built on a sparse tensor. We list a few popular network architectures and applications here. To run the examples, please install the package and run the command in the package root directory. Compressing a neural network to speed up inference and minimize memory footprint has been studied widely. ...
