convolution

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

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

Imaging is a simple image processing package for Go

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

Vulkan/CUDA/HIP/OpenCL/Level Zero/Metal Fast Fourier Transform library

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

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

带你从零实现一个高性能的深度学习推理库

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

Understanding Convolution for Semantic Segmentation

Building Convolutional Neural Networks From Scratch using NumPy

Image processing and manipulation in JavaScript

Tensorflow implementation of Gated Conditional Pixel Convolutional Neural Network

Deep Learning in C#

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

Efficient Haskell Arrays featuring Parallel computation

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

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

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

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.