Performance of Deep Learning Frameworks: Caffe, Deeplearning4j, TensorFlow, Theano, and Torch

Performance of Deep Learning Frameworks: Caffe, Deeplearning4j, TensorFlow, Theano, and Torch

This 15-page research paper compares the performance and accuracy of five deep learning frameworks: Caffe, Deeplearning4j, TensorFlow, Theano, and Torch. The comparative study makes use of fully connected neural networks for the MNIST classification.

With the number of training epochs set to 1, 5, and 10 (and the batch size of 128 images), the report provides comparison across the following parameters:

  • time for training a model
  • classification speed
  • accuracy of classification
  • the amount of code necessary

In addition, you will learn how changing the network “depth” and “width” affects the key evaluation metrics (the data is available for the Tanh and ReLU activation functions).

Please fill out the following form so that the tech study can be sent to you via e-mail.


Please, don't fill this field:


Customers Speak

  • "We highly recommend Altoros to rapidly build complex applications using cutting edge technologies. Again, great job!"

    Christopher Adorna, Sony Sony-logo-vector

© 2001 - 2016 Altoros