convolution

MNN is a blazing fast, lightweight deep learning framework, battle-tested by business-critical use cases in Alibaba. Full multimodal LLM Android App:[MNN-LLM-Android](./apps/Android/MnnLlmChat/README.md)

Imaging is a simple image processing package for Go

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

校招、秋招、春招、实习好项目！带你从零实现一个高性能的深度学习推理库，支持大模型 llama2 、Unet、Yolov5、Resnet等模型的推理。Implement a high-performance deep learning inference library step by step

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

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

An implementation of the system-wide JamesDSP audio processing engine for non-rooted Android devices

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

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

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

Image processing and manipulation in JavaScript

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.

Understanding Convolution for Semantic Segmentation

Building Convolutional Neural Networks From Scratch using NumPy

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

Tensorflow implementation of Gated Conditional Pixel Convolutional Neural Network

Deep Learning in C#

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

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

Efficient Haskell Arrays featuring Parallel computation