HallocA fast and highly scalable GPU dynamic memory allocator
Stars: ✭ 89 (-96.88%)
HasteHaste: a fast, simple, and open RNN library
Stars: ✭ 214 (-92.49%)
GinkgoNumerical linear algebra software package
Stars: ✭ 149 (-94.77%)
Libtorch Yolov5A LibTorch inference implementation of the yolov5
Stars: ✭ 127 (-95.54%)
MinhashcudaWeighted MinHash implementation on CUDA (multi-gpu).
Stars: ✭ 88 (-96.91%)
Compute.scalaScientific computing with N-dimensional arrays
Stars: ✭ 191 (-93.3%)
PytorchPyTorch tutorials A to Z
Stars: ✭ 87 (-96.95%)
Cuda CnnCNN accelerated by cuda. Test on mnist and finilly get 99.76%
Stars: ✭ 148 (-94.81%)
Batch ShipyardSimplify HPC and Batch workloads on Azure
Stars: ✭ 240 (-91.58%)
GatelessgatesharpGateless Gate Sharp is an user-friendly yet extremely powerful open-source multi-algorithm miner for Windows operating systems.
Stars: ✭ 86 (-96.98%)
SketchgraphsA dataset of 15 million CAD sketches with geometric constraint graphs.
Stars: ✭ 148 (-94.81%)
Python Opencv Cudacustom opencv_contrib module which exposes opencv cuda optical flow methods with python bindings
Stars: ✭ 86 (-96.98%)
EtlBlazing-fast Expression Templates Library (ETL) with GPU support, in C++
Stars: ✭ 190 (-93.33%)
Training MaterialA collection of code examples as well as presentations for training purposes
Stars: ✭ 85 (-97.02%)
NsfminerNo Fee Ethash miner for AMD and Nvidia
Stars: ✭ 141 (-95.05%)
Kaldikaldi-asr/kaldi is the official location of the Kaldi project.
Stars: ✭ 11,151 (+291.26%)
Caffe ModelCaffe models (including classification, detection and segmentation) and deploy files for famouse networks
Stars: ✭ 1,258 (-55.86%)
FsynthWeb-based and pixels-based collaborative synthesizer
Stars: ✭ 146 (-94.88%)
OneflowOneFlow is a performance-centered and open-source deep learning framework.
Stars: ✭ 2,868 (+0.63%)
Senet CaffeA Caffe Re-Implementation of SENet
Stars: ✭ 169 (-94.07%)
ShadergumUnity3D GPU Sculpt & Morph
Stars: ✭ 125 (-95.61%)
Onnx ChainerAdd-on package for ONNX format support in Chainer
Stars: ✭ 83 (-97.09%)
GonvmlNVIDIA Management Library (NVML) bindings for Go
Stars: ✭ 82 (-97.12%)
Pytorch Heda reimplementation of Holistically-Nested Edge Detection in PyTorch
Stars: ✭ 228 (-92%)
Pytorch EmdlossPyTorch 1.0 implementation of the approximate Earth Mover's Distance
Stars: ✭ 82 (-97.12%)
Low Rank Bilinear PoolingFine-grained classification via second order statistics in a compact end-to-end trainable model
Stars: ✭ 145 (-94.91%)
Kmeans pytorchpytorch implementation of basic kmeans algorithm(lloyd method with forgy initialization) with gpu support
Stars: ✭ 81 (-97.16%)
Pixel📷 A composable image editor using Core Image and Metal.
Stars: ✭ 2,495 (-12.46%)
Modulated Deform Convdeformable convolution 2D 3D DeformableConvolution DeformConv Modulated Pytorch CUDA
Stars: ✭ 81 (-97.16%)
2016 super resolutionICCV2015 Image Super-Resolution Using Deep Convolutional Networks
Stars: ✭ 78 (-97.26%)
Nd4jFast, Scientific and Numerical Computing for the JVM (NDArrays)
Stars: ✭ 1,742 (-38.88%)
SeqfaceSeqFace : Making full use of sequence information for face recognition
Stars: ✭ 125 (-95.61%)
Hyperlearn50% faster, 50% less RAM Machine Learning. Numba rewritten Sklearn. SVD, NNMF, PCA, LinearReg, RidgeReg, Randomized, Truncated SVD/PCA, CSR Matrices all 50+% faster
Stars: ✭ 1,204 (-57.75%)
NplusminerNPlusMiner + GUI | NVIDIA/AMD/CPU miner | AI | Autoupdate | MultiRig remote management
Stars: ✭ 75 (-97.37%)
ColorizationAutomatic colorization using deep neural networks. "Colorful Image Colorization." In ECCV, 2016.
Stars: ✭ 2,791 (-2.07%)
Touch Bar IstatsShow CPU/GPU/MEM temperature on Touch Bar with BetterTouchTool!
Stars: ✭ 141 (-95.05%)
Cuda ConvnetMy fork of Alex Krizhevsky's cuda-convnet from 2013 where I added dropout, among other features.
Stars: ✭ 238 (-91.65%)
FcisFully Convolutional Instance-aware Semantic Segmentation
Stars: ✭ 1,563 (-45.16%)
Pedestrian alignmentTCSVT2018 Pedestrian Alignment Network for Large-scale Person Re-identification
Stars: ✭ 223 (-92.18%)
Cuda programmingCode from the "CUDA Crash Course" YouTube series by CoffeeBeforeArch
Stars: ✭ 169 (-94.07%)
DeeprecommenderDeep learning for recommender systems
Stars: ✭ 1,593 (-44.11%)
Lambdacube EdslPrevious version of LambdaCube 3D as Embedded Domain Specific Language in Haskell. Check the latest system:
Stars: ✭ 186 (-93.47%)
WgpuSafe and portable GPU abstraction in Rust, implementing WebGPU API.
Stars: ✭ 3,305 (+15.96%)
Caffe2pytorch TsnTransform the caffe model to pytorch model for Temporal Segment Network
Stars: ✭ 69 (-97.58%)
Resnet On Cifar10Reimplementation ResNet on cifar10 with caffe
Stars: ✭ 123 (-95.68%)
DragonDragon: A Computation Graph Virtual Machine Based Deep Learning Framework.
Stars: ✭ 168 (-94.11%)
Finitediff.jlFast non-allocating calculations of gradients, Jacobians, and Hessians with sparsity support
Stars: ✭ 123 (-95.68%)
Deformable KernelsDeforming kernels to adapt towards object deformation. In ICLR 2020.
Stars: ✭ 166 (-94.18%)
Warp RnntCUDA-Warp RNN-Transducer
Stars: ✭ 122 (-95.72%)