88 Open Source Convolution Software Projects

A Swift library that uses the Accelerate framework to provide high-performance functions for matrix math, digital signal processing, and image manipulation.

MNN is a blazing fast, lightweight deep learning framework, battle-tested by business-critical use cases in Alibaba

Imaging is a simple image processing package for Go

A PyTorch implementation of "Capsule Graph Neural Network" (ICLR 2019).

Understanding Convolution for Semantic Segmentation

Tensorflow implementation of Gated Conditional Pixel Convolutional Neural Network

Library for specialized dense and sparse matrix operations, and deep learning primitives.

Building Convolutional Neural Networks From Scratch using NumPy

A discrete-time Python-based solver for the Stochastic On-Time Arrival routing problem

Deep Learning in C#

Theory of digital signal processing (DSP): signals, filtration (IIR, FIR, CIC, MAF), transforms (FFT, DFT, Hilbert, Z-transform) etc.

Efficient Haskell Arrays featuring Parallel computation

ShuffleNet in PyTorch. Based on https://arxiv.org/abs/1707.01083

Caffe for Sparse Convolutional Neural Network

Image processing and manipulation in JavaScript

Simple demonstration of separable convolutions

The HPC toolbox: fused matrix multiplication, convolution, data-parallel strided tensor primitives, OpenMP facilities, SIMD, JIT Assembler, CPU detection, state-of-the-art vectorized BLAS for floats and integers

Blazing-fast Expression Templates Library (ETL) with GPU support, in C++

Efficient Sparse-Winograd Convolutional Neural Networks (ICLR 2018)

python implementation of efficient convolution operators for tracking

Fully Convolutional DenseNet (A.K.A 100 layer tiramisu) for semantic segmentation of images implemented in TensorFlow.

Audio DSP effects build on Android system framework layer. This is a repository contains a pack of high quality DSP algorithms specialized for audio processing.

Vulkan/CUDA/HIP/OpenCL Fast Fourier Transform library

[ECCV 2020] PSConv: Squeezing Feature Pyramid into One Compact Poly-Scale Convolutional Layer

ROCKET: Exceptionally fast and accurate time series classification using random convolutional kernels

Xilinx Deep Learning IP

A Cross-platform Library for Swift

This python code performs an efficient speech reverberation starting from a dataset of close-talking speech signals and a collection of acoustic impulse responses.

ShellNet: Efficient Point Cloud Convolutional Neural Networks using Concentric Shells Statistics

Implements the Tsetlin Machine, Convolutional Tsetlin Machine, Regression Tsetlin Machine, Weighted Tsetlin Machine, and Embedding Tsetlin Machine, with support for continuous features, multigranularity, and clause indexing

Pytorch implementation of "An intriguing failing of convolutional neural networks and the CoordConv solution" - https://arxiv.org/abs/1807.03247

Convolution and other super-patches (blur, sharpen)

Active Convolution

CNN applied to bearing signals for analysis

Commonly used image filters. :earth_americas: 包罗常见的图像滤波器。

This is a times series anomaly detection algorithm, implemented in Python, for catching multiple anomalies. It uses a moving average with an extreme student deviate (ESD) test to detect anomalous points.

This toolbox is support material for the book on CNN (http://www.convolution.network).

Tutorial on the Convolutional Tsetlin Machine

DSP and filtering library

使用numpy构建cnn复习深度学习知识

html5 canvas image process ( 3*3 kernel ) canvas卷积核测试 canvas图片后期

High Performance Computing (HPC) and Signal Processing Framework

Rotation Invariant Convolutions for 3D Point Clouds Deep Learning

Image Processing Toolbox in Verilog using Basys3 FPGA

Massively Parallel and Asynchronous Architecture for Logic-based AI

Use DCGAN to create trippy videos

An implementation of dilated convolutional layer based on Darknet Architecture

Floating point Forward/Inverse Fast Fourier Transform (FFT) IP-core for newest Xilinx FPGAs (Source lang. - VHDL).

Aiding the visually impaired through real time augmented reality, AI object detection, WebGL shaders effects such as edge detection, and colour adjustments.

Multi-threaded implementation of the Tsetlin Machine, Convolutional Tsetlin Machine, Regression Tsetlin Machine, and Weighted Tsetlin Machine, with support for continuous features and multigranularity.

:rowboat: A simple recommendation engine (by way of convolutions and embeddings) written in TensorFlow

A python module for seamless integration of analog filters designed in LTspice into Python3/Numpy signal processing projects.

An interactive player for CNN convolution

An example of C++ extension for PyTorch.

Reverb effect using hybrid impulse convolution

CNN text classification using keras

C# implementation of neural networks library. Contains basic types of layers (dense, convolution, pooling, flatten). Supports single CPU, Multi-CPU and GPU tensor operations (using ManagedCUDA). This project is no longer developed, since I ported it to C++ and greatly expanded (Neuro_).

TensorFlow implementation of CoordConv Layer introduced by UBER

Latte is a convolutional neural network (CNN) inference engine written in C++ and uses AVX to vectorize operations. The engine runs on Windows 10, Linux and macOS Sierra.

Octave Convolution Implementation in PyTorch

GEMM and Winograd based convolutions using CUTLASS

A C++ library that produces images based on different luminosity profiles

Multi-dimensional local filters (convolution, mathematical morphology, etc.) for Julia.

Graduate Level Course of Technical University of Munich

Band-limited Training and Inference for Convolutional Neural Networks

Functional N-dimensional convolution in Pytorch, recursively calling convNd until reaching conv3d.

A Java Library for Digital Signal Processing

An implementation of the original "ResNet" paper in Pytorch

PyTorch implementation of "Conformer: Convolution-augmented Transformer for Speech Recognition" (INTERSPEECH 2020)

Implementation of 1D, 2D, and 3D FFT convolutions in PyTorch. Much faster than direct convolutions for large kernel sizes.

PyTorch Implementation of CvT: Introducing Convolutions to Vision Transformers

Multiplatform scientific computing for Dart

MINIROCKET: A Very Fast (Almost) Deterministic Transform for Time Series Classification

This repo contains the code of "ConTNet: Why not use convolution and transformer at the same time?"

Authors' implementation of my SIGGRAPH Asia 2019 Technical Briefs (The Power of Box Filters: Real-time Approximation to Large Convolution Kernel by Box-filtered Image Pyramid) demo I (just for reference). A very fast approximation to large-kernel Gaussian blur with nonuniform blur radii, by making use of box-filtered mip maps V-cycle (theoratically related to Haar wavelet tranforms). The mathematical model can be found in the PDF file.

Authors' implementation of my SIGGRAPH Asia 2019 Technical Briefs (The Power of Box Filters: Real-time Approximation to Large Convolution Kernel by Box-filtered Image Pyramid) demo II. Real-time dynamic irradiance mapping.

Convolutional PyTorch debayering layer

Code generator for implicit gemm algorithm for amdgpu.

This project implements a convolution kernel based on vivado HLS on zcu104

A 2D convolution hardware implementation written in Verilog

Convolutive Matrix Factorization in Julia

Sobel–Feldman, Prewitt, Canny filter

Demonstrates how to divide a DL model into multiple IR model files (division) and introduce a simplest way to implement a custom layer works with OpenVINO IR models.

Canny Edge Detection, Eigen Faces Face Recognition Algorithm, Applying Sobel Filter, Hough Lines, Harris Corner Detection as a Feature, Image Manipulation