cuda-convnet2

3.0
(2)

cuda-convnet2 is a fast C++/CUDA implementation of convolutional (or more generally, feed-forward) neural networks that can model arbitrary layer connectivity and network depth, any directed acyclic graph of layers will do it required fermi-generation GPU (GTX 4xx, GTX 5xx, or Tesla equivalent).

Work for cuda-convnet2?

Learning about cuda-convnet2?

We can help you find the solution that fits you best.

Find the Right Product

cuda-convnet2 Reviews

Chat with a G2 Advisor
Write a Review
Filter Reviews
Filter Reviews
  • Ratings
  • Company Size
  • Industry
Ratings
Company Size
Industry
Showing 2 cuda-convnet2 reviews
LinkedIn Connections
cuda-convnet2 review by G2 Crowd User
G2 Crowd User
Validated Reviewer
Review Source
content

"One of the original deep learning frameworks, unlikely to be useful for modern projects"

What do you like best?

It is a slight evolution of the code Alex Krizhevsky used to win the Imagenet challenge back in 2012, so it is useful in a historical sense and worth looking at out of curiosity. It has since inspired many many libraries for training ConvNets on the GPU.

What do you dislike?

It hasn't been updated for at least four years, and as such does not include modern layers, or features such as automatic differentiation.

Recommendations to others considering the product

It is the OG of deep learning, but Caffe quickly became the library of choice, before itself being replaced by Tensorflow and Pytorch.

What business problems are you solving with the product? What benefits have you realized?

I ran cuda-convnet back in the day to train convolutional neural networks for image recognition. The main advantage was the ability to run super fast on the GPU.

Sign in to G2 Crowd to see what your connections have to say about cuda-convnet2
cuda-convnet2 review by G2 Crowd User in Higher Education
G2 Crowd User in Higher Education
Validated Reviewer
Review Source
content

"Amazing classification in less time."

What do you like best?

Parallel processing. It is very fast and relatively easy to understand

What do you dislike?

Nvidia gpu required. We cant use it with any other gpu

What business problems are you solving with the product? What benefits have you realized?

I am solving an image classification problem. While solving on CPU where it takes forever to run, cuda runs it in minuted

What Artificial Neural Network solution do you use?

Thanks for letting us know!

There are not enough reviews of cuda-convnet2 for G2 Crowd to provide buying insight. Below are some alternatives with more reviews:

1
Mocha Logo
Mocha
4.0
(13)
Mocha is a Deep Learning framework for Julia, inspired by the C++ framework Caffe that is efficient implementations of general stochastic gradient solvers and common layers, it could be used to train deep / shallow (convolutional) neural networks, with (optional) unsupervised pre-training via (stacked) auto-encoders.
2
Keras Logo
Keras
4.7
(13)
Keras is a neural networks library, written in Python and capable of running on top of either TensorFlow or Theano.
3
AWS Deep Learning AMIs Logo
AWS Deep Learning AMIs
4.2
(11)
The AWS Deep Learning AMIs is designed to equip data scientists, machine learning practitioners, and research scientists with the infrastructure and tools to accelerate work in deep learning, in the cloud, at any scale.
4
TFLearn Logo
TFLearn
4.0
(5)
TFlearn is a modular and transparent deep learning library built on top of Tensorflow that provide a higher-level API to TensorFlow in order to facilitate and speed-up experimentations, while remaining fully transparent and compatible with it.
5
julia-ann Logo
julia-ann
3.3
(3)
julia-ann is the implementation of backpropagation artificial neural networks in Julia that allow users to build multilayer networks and accept DataFrames as inputs. fit! and predict currently require Float64 matrices and vectors.
6
ConvNetJS Logo
ConvNetJS
3.8
(3)
ConvNetJS is a Javascript library for training Deep Learning models (Neural Networks) entirely in a browser.
7
brain Logo
brain
4.3
(3)
brain is a JavaScript neural network library to recognize color contrast.
8
Brainstrom Logo
Brainstrom
4.3
(3)
Brainstorm makes working with neural networks fast, flexible and fun that allows to work on multiple platforms with multiple computing backends.
9
Deep Learning GPU Training System (DIGITS) Logo
Deep Learning GPU Training System (DIGITS)
4.2
(3)
NVIDIA Deep Learning GPU Training System (DIGITS) deep learning for data science and research to quickly design deep neural network (DNN) for image classification and object detection tasks using real-time network behavior visualization.
10
BrainCore Logo
BrainCore
4.5
(2)
BrainCore is a neural network framework written in Swift that uses Metal which makes it fast.
Show more
Kate from G2 Crowd

Learning about cuda-convnet2?

I can help.
* We monitor all cuda-convnet2 reviews to prevent fraudulent reviews and keep review quality high. We do not post reviews by company employees or direct competitors. Validated reviews require the user to submit a screenshot of the product containing their user ID, in order to verify a user is an actual user of the product.