Skip to content
Open-source Deep Learning library in C# with CUDA and BLAS support
C# Cuda
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
Prod
Tests
.gitignore
LICENSE
README.md
SharpNet.sln

README.md

SharpNet is an Open-source Deep Learning library written in C# 7.0.

It supports:

  • Residual Networks v1, v2 and WideResNet
  • DenseNet
  • Dropout / BatchNorm / Conv / Pooling / Dense / Concatenate / Shortcut layers
  • Elu / Relu / Sigmoid / Softmax activations
  • SGD & Adam optimizers
  • Image Data Augmentation (with Cutout/CutMix/Mixup)
  • Ensemble Learning

It can be run both on GPU (using NVIDIA cuDNN) and on the CPU (using MKL Blas).

It is targeted to make a good use of the GPU (even if it is not currently as fast as MxNet) :

  • on ResNet18 v1, it is between 1.5x (batch size = 128) and 3x time (batch size = 32) faster then TensorFlow

It requires:

Next Targets:

  • Add ResNet v2 support => DONE
  • Add Dense Network support => DONE
  • Cutout => DONE
  • Add CutMix => DONE
  • Add Mixup => DONE
  • Add multi GPU support
  • Add RNN / LSTM support
  • Improve memory efficiency for gradients => DONE
  • Add Wide ResNet / Wide DenseNet support => DONE
  • Improve Image Data Augmentation (with rotation) => DONE
You can’t perform that action at this time.