ELEKTRONN: A highly configurable toolkit for training 3d/2d CNNs and general Neural Networks Project Website: http://elektronn.org/ Github Link: https://github.com/ELEKTRONN/ELEKTRONN Description ELEKTRONN is a deep learning toolkit that makes powerful neural networks accessible to scientists outside of the machine learning community. … Continue reading

# Tag Archives: CUDA

ConvNet: Convolutional Neural Networks for Matlab Project Website: None Github Link: https://github.com/sdemyanov/ConvNet Description Convolutional Neural Networks for Matlab, including Invariang Backpropagation algorithm (IBP). Has versions for GPU and CPU, written on CUDA, C++ and Matlab. All versions work identically. The … Continue reading

CUV: Matrix library for CUDA in C++ and Python Project Website: http://www.ais.uni-bonn.de/ Github Link: https://github.com/deeplearningais/CUV Description CUV is a C++ template and Python library which makes it easy to use NVIDIA(tm) CUDA. Features Supported Platforms: • This library was only … Continue reading

Gnumpy Project Website: None Github Link: http://www.cs.toronto.edu/~tijmen/gnumpy.html Description Do you want to have both the compute power of GPU’s and the programming convenience of Python numpy? Gnumpy + Cudamat will bring you that. Gnumpy is a simple Python module that … Continue reading

CUDAMat: Python module for performing basic dense linear algebra computations on the GPU using CUDA Project Website: None Github Link: https://github.com/cudamat/cudamat Description The aim of the cudamat project is to make it easy to perform basic matrix calculations on CUDA-enabled … Continue reading

CXXNET is a fast, concise, distributed deep learning framework Project Website: CXXNet now move forward to MXNet Github Link: https://github.com/dmlc/cxxnet Description CXXNET is a fast, concise, distributed deep learning framework. Contributors: https://github.com/antinucleon/cxxnet/graphs/contributors Documentation Learning to use cxxnet by examples Note … Continue reading

mshadow: Matrix Shadow Project Website: None Github Link: https://github.com/dmlc/mshadow Description MShadow is a lightweight CPU/GPU Matrix/Tensor Template Library in C++/CUDA. The goal of mshadow is to support efficient, device invariant and simple tensor library for machine learning project that aims … Continue reading