Jump to content
  • Deep Learning with Spotfire Statistica®


    Statistica 13.2 was release with Microsoft Cognitive Toolkit.

    An example workspace named Example_MNIST Digit Recognition was also released with Statistica and it is attached to the bottom of this page.  This workspace analyzes handwriting with a public dataset. 

    The execution time of this example will depend on the hardware. For example, running this on a 16-core (non-GPU) linux VM took 62.95 real-time minutes to do the train and test and 999.01 minutes of user time and 4 minutes of system time. The user time indicated that all 16 cores were all very busy (999/63 = 15.85). Of course this means little as CNTK is designed for parallelism and massive GPU support is the point.

    example_mnist_digit_recognition_.thumb.png.995861b4708d2061dfa6ea6de81b3511.png

    Attachments

    You can download attachments from resources.

    example_mnist_digit_recognition.zip


    User Feedback

    Recommended Comments

    There are no comments to display.


×
×
  • Create New...