Partial Order PruningPartial Order Pruning: for Best Speed/Accuracy Trade-off in Neural Architecture Search
Stars: ✭ 135 (-18.67%)
MatexMachine Learning Toolkit for Extreme Scale (MaTEx)
Stars: ✭ 104 (-37.35%)
GinkgoNumerical linear algebra software package
Stars: ✭ 149 (-10.24%)
PfunitParallel Fortran Unit Testing Framework
Stars: ✭ 104 (-37.35%)
DashDASH, the C++ Template Library for Distributed Data Structures with Support for Hierarchical Locality for HPC and Data-Driven Science
Stars: ✭ 134 (-19.28%)
RainbowminerGPU/CPU Mining script with intelligent profit-switching between miningpools, algorithms, miners, using all possible combinations of devices (NVIDIA, AMD, CPU). Features: actively maintained, uses the top actual miner programs (Bminer, Ccminer, Claymore, Dstm, EnemyZ, Sgminer, T-rex and more) easy setup wizard, webinterface, auto update.
Stars: ✭ 158 (-4.82%)
Ytk Mp4jYtk-mp4j is a fast, user-friendly, cross-platform, multi-process, multi-thread collective message passing java library which includes gather, scatter, allgather, reduce-scatter, broadcast, reduce, allreduce communications for distributed machine learning.
Stars: ✭ 102 (-38.55%)
Waifu2x ExtensionImage, GIF and Video enlarger/upscaler achieved with waifu2x and Anime4K. [NO LONGER UPDATED]
Stars: ✭ 149 (-10.24%)
Pytorch gbw lmPyTorch Language Model for 1-Billion Word (LM1B / GBW) Dataset
Stars: ✭ 101 (-39.16%)
Gpu monitorMonitor your GPUs whether they are on a single computer or in a cluster
Stars: ✭ 133 (-19.88%)
Neural Style DockerA dockerized version of neural style transfer algorithms
Stars: ✭ 100 (-39.76%)
Cuda CnnCNN accelerated by cuda. Test on mnist and finilly get 99.76%
Stars: ✭ 148 (-10.84%)
NnvmNo description or website provided.
Stars: ✭ 1,639 (+887.35%)
DppDetail-Preserving Pooling in Deep Networks (CVPR 2018)
Stars: ✭ 99 (-40.36%)
EmuThe write-once-run-anywhere GPGPU library for Rust
Stars: ✭ 1,350 (+713.25%)
Cx db8a contextual, biasable, word-or-sentence-or-paragraph extractive summarizer powered by the latest in text embeddings (Bert, Universal Sentence Encoder, Flair)
Stars: ✭ 164 (-1.2%)
NyuziprocessorGPGPU microprocessor architecture
Stars: ✭ 1,351 (+713.86%)
SketchgraphsA dataset of 15 million CAD sketches with geometric constraint graphs.
Stars: ✭ 148 (-10.84%)
SigpyPython package for signal processing, with emphasis on iterative methods
Stars: ✭ 132 (-20.48%)
Extending JaxExtending JAX with custom C++ and CUDA code
Stars: ✭ 98 (-40.96%)
SupraSUPRA: Software Defined Ultrasound Processing for Real-Time Applications - An Open Source 2D and 3D Pipeline from Beamforming to B-Mode
Stars: ✭ 96 (-42.17%)
Region ConvNot All Pixels Are Equal: Difficulty-Aware Semantic Segmentation via Deep Layer Cascade
Stars: ✭ 95 (-42.77%)
Floyd CliCommand line tool for FloydHub - the fastest way to build, train, and deploy deep learning models
Stars: ✭ 147 (-11.45%)
Fbtt EmbeddingThis is a Tensor Train based compression library to compress sparse embedding tables used in large-scale machine learning models such as recommendation and natural language processing. We showed this library can reduce the total model size by up to 100x in Facebook’s open sourced DLRM model while achieving same model quality. Our implementation is faster than the state-of-the-art implementations. Existing the state-of-the-art library also decompresses the whole embedding tables on the fly therefore they do not provide memory reduction during runtime of the training. Our library decompresses only the requested rows therefore can provide 10,000 times memory footprint reduction per embedding table. The library also includes a software cache to store a portion of the entries in the table in decompressed format for faster lookup and process.
Stars: ✭ 92 (-44.58%)
NvfancontrolNVidia dynamic fan control for Linux and Windows
Stars: ✭ 93 (-43.98%)
Ergo Pe Av🧠 🦠 An artificial neural network and API to detect Windows malware, based on Ergo and LIEF.
Stars: ✭ 130 (-21.69%)
Fastaudio🔊 Audio and fastai v2
Stars: ✭ 93 (-43.98%)
ProphecisProphecis is a one-stop cloud native machine learning platform.
Stars: ✭ 156 (-6.02%)
NsfminerNo Fee Ethash miner for AMD and Nvidia
Stars: ✭ 141 (-15.06%)
LibmaliThe Mali GPU library used in Rockchip Platform
Stars: ✭ 128 (-22.89%)
AgencyExecution primitives for C++
Stars: ✭ 127 (-23.49%)
ElasticfusionReal-time dense visual SLAM system
Stars: ✭ 1,298 (+681.93%)
MatconvnetMatConvNet: CNNs for MATLAB
Stars: ✭ 1,299 (+682.53%)
Ipyexperimentsjupyter/ipython experiment containers for GPU and general RAM re-use
Stars: ✭ 128 (-22.89%)
AuroraMinimal Deep Learning library is written in Python/Cython/C++ and Numpy/CUDA/cuDNN.
Stars: ✭ 90 (-45.78%)
CuxfilterGPU accelerated cross filtering with cuDF.
Stars: ✭ 128 (-22.89%)
HallocA fast and highly scalable GPU dynamic memory allocator
Stars: ✭ 89 (-46.39%)
Sparkle🎇 A modern particle engine running on GPU, using c++14 and OpenGL 4.4.
Stars: ✭ 162 (-2.41%)
F LmLanguage Modeling
Stars: ✭ 156 (-6.02%)
FsynthWeb-based and pixels-based collaborative synthesizer
Stars: ✭ 146 (-12.05%)
Libtorch Yolov5A LibTorch inference implementation of the yolov5
Stars: ✭ 127 (-23.49%)
MinhashcudaWeighted MinHash implementation on CUDA (multi-gpu).
Stars: ✭ 88 (-46.99%)
Citro2dLibrary for drawing 2D graphics using the Nintendo 3DS's PICA200 GPU
Stars: ✭ 88 (-46.99%)
ParamonteParaMonte: Plain Powerful Parallel Monte Carlo and MCMC Library for Python, MATLAB, Fortran, C++, C.
Stars: ✭ 88 (-46.99%)
PytorchPyTorch tutorials A to Z
Stars: ✭ 87 (-47.59%)
Kaldikaldi-asr/kaldi is the official location of the Kaldi project.
Stars: ✭ 11,151 (+6617.47%)
ShaderviewA library for simple shader programming
Stars: ✭ 87 (-47.59%)
Texture CompressorCLI tool for texture compression using ASTC, ETC, PVRTC and S3TC in a KTX container.
Stars: ✭ 156 (-6.02%)
GpurirPython library for Room Impulse Response (RIR) simulation with GPU acceleration
Stars: ✭ 145 (-12.65%)