Image JsImage processing and manipulation in JavaScript
SkimcaffeCaffe for Sparse Convolutional Neural Network
ConvolveSimple demonstration of separable convolutions
LaserThe 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
EtlBlazing-fast Expression Templates Library (ETL) with GPU support, in C++
RocketROCKET: Exceptionally fast and accurate time series classification using random convolutional kernels
Pyecopython implementation of efficient convolution operators for tracking
Psconv[ECCV 2020] PSConv: Squeezing Feature Pyramid into One Compact Poly-Scale Convolutional Layer
JamesdspmanagerAudio DSP effects build on Android system framework layer. This is a repository contains a pack of high quality DSP algorithms specialized for audio processing.
PytsetlinmachineImplements 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
PyspeechrevThis python code performs an efficient speech reverberation starting from a dataset of close-talking speech signals and a collection of acoustic impulse responses.
ScidartMultiplatform scientific computing for Dart
CoordconvPytorch implementation of "An intriguing failing of convolutional neural networks and the CoordConv solution" - https://arxiv.org/abs/1807.03247
Fft Conv PytorchImplementation of 1D, 2D, and 3D FFT convolutions in PyTorch. Much faster than direct convolutions for large kernel sizes.
Anomaly detectionThis 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.
CapsgnnA PyTorch implementation of "Capsule Graph Neural Network" (ICLR 2019).
YannThis toolbox is support material for the book on CNN (http://www.convolution.network).
MnnMNN is a blazing fast, lightweight deep learning framework, battle-tested by business-critical use cases in Alibaba
VkfftVulkan Fast Fourier Transform library
Tusimple DucUnderstanding Convolution for Semantic Segmentation
SurgeA Swift library that uses the Accelerate framework to provide high-performance functions for matrix math, digital signal processing, and image manipulation.
LibxsmmLibrary for specialized dense and sparse matrix operations, and deep learning primitives.
Dsp TheoryTheory of digital signal processing (DSP): signals, filtration (IIR, FIR, CIC, MAF), transforms (FFT, DFT, Hilbert, Z-transform) etc.
NumpycnnBuilding Convolutional Neural Networks From Scratch using NumPy
Sota PyA discrete-time Python-based solver for the Stochastic On-Time Arrival routing problem
ImagingImaging is a simple image processing package for Go
MassivEfficient Haskell Arrays featuring Parallel computation
ShufflenetShuffleNet in PyTorch. Based on https://arxiv.org/abs/1707.01083
NonuniformBlurAuthors' 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 (theoratica…
shellnetShellNet: Efficient Point Cloud Convolutional Neural Networks using Concentric Shells Statistics
riconvRotation Invariant Convolutions for 3D Point Clouds Deep Learning
dsp-theoryTheory of digital signal processing (DSP): signals, filtration (IIR, FIR, CIC, MAF), transforms (FFT, DFT, Hilbert, Z-transform) etc.
deep-scite🚣 A simple recommendation engine (by way of convolutions and embeddings) written in TensorFlow
minirocketMINIROCKET: A Very Fast (Almost) Deterministic Transform for Time Series Classification
WebSightAiding the visually impaired through real time augmented reality, AI object detection, WebGL shaders effects such as edge detection, and colour adjustments.
dspDSP and filtering library
susaHigh Performance Computing (HPC) and Signal Processing Framework
IrradianceMapAuthors' 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.