webdnn
Deep neural network accelerator
A framework that accelerates deep neural networks in web browsers using optimized models and GPU acceleration.
The Fastest DNN Running Framework on Web Browser
2k stars
60 watching
146 forks
Language: TypeScript
last commit: 3 months ago
Linked from 1 awesome list
acceleratedeep-neural-networksjavascriptoptimizationwebgpu
josephmisiti/awesome-machine-learningRelated projects:
| Repository | Description | Stars |
|---|---|---|
 ucb-bar/gemmini | A platform for exploring and evaluating deep learning hardware acceleration using a full-system simulation approach | 828 |
 doonny/pipecnn | A tool for accelerating convolutional neural networks on Field-Programmable Gate Arrays (FPGAs) using OpenCL-based hardware design | 1,264 |
 mofanv/darknetz | An application that runs several layers of a Deep Neural Network model in a secure environment for model privacy at the edge | 86 |
 unagiootoro/ruby-dnn | A Ruby-based deep learning library for building and training neural networks | 46 |
 yixuan/minidnn | A C++ library implementing deep neural networks with good performance and modularity | 399 |
 nngen/nngen | Generates hardware-specific accelerator designs for neural networks | 340 |
 element-research/dpnn | A package of reusable building blocks for deep neural networks in Lua | 194 |
 dianixn/signal_detection_ofdmpowerofdnn | A MATLAB implementation demonstrating the power of deep learning in signal detection and channel estimation for OFDM systems | 119 |
 mosdeo/lkydeepnn | A header-only C++ library for training and deploying deep neural networks on embedded systems | 49 |
 dmitryulyanov/fast-neural-doodle | A Lua-based implementation of neural doodle style transfer using intermediate representations and GPU acceleration. | 346 |
 antoniodeluca/dn2a | A toolkit for building and training dynamic neural networks | 463 |
 hyeongseokson1/cnn_deconvolution | An implementation of a CNN-based method for non-blind deconvolution using Wiener filtering as a pre-processing step. | 22 |
 sfmth/openspike | An accelerator designed to speed up spiking neural networks by integrating synaptic weights on a single chip. | 132 |
 xilinx/finn | Fast and scalable neural network inference framework for FPGAs. | 770 |
 jingweiz/pytorch-dnc | An implementation of Neural Turing Machine and Differentiable Neural Computer architectures using PyTorch and Visdom for deep learning tasks. | 278 |