Hub
Pricing About
WorkflowWorkflow

KNIME Deep Learning - Train MNIST classifier with Keras nodes

Deep learningKerasImage classification
scottf profile image
Draft Latest edits on 
Jul 5, 2017 1:02 PM
Drag & drop
Like
Download workflow
Workflow preview
This workflow trains a simple convolutional neural network (CNN) on the MNIST dataset via Keras. You can use either a code based approach to create the network in the DL Python Network Creator, or a series of Keras KNIME nodes.
Loading deploymentsLoading ad hoc jobs

Used extensions & nodes

Created with KNIME Analytics Platform version 4.0.1
  • Go to item
    KNIME CoreTrusted extension

    KNIME AG, Zurich, Switzerland

    Versions 3.6.0, 4.0.1

    knime
  • Go to item
    KNIME Deep Learning - Keras IntegrationTrusted extension

    KNIME AG, Zurich, Switzerland

    Versions 3.6.0, 4.0.0

    knime
  • Go to item
    KNIME Image ProcessingTrusted extension

    University of Konstanz / KNIME

    Versions 1.7.0, 1.8.0

    bioml-konstanz
  • Go to item
    KNIME JavaScript Views (Labs)Trusted extension

    KNIME AG, Zurich, Switzerland

    Version 4.0.1

    knime

Legal

By using or downloading the workflow, you agree to our terms and conditions.

KNIME
Open for Innovation

KNIME AG
Talacker 50
8001 Zurich, Switzerland
  • Software
  • Getting started
  • Documentation
  • Courses + Certification
  • Solutions
  • KNIME Hub
  • KNIME Forum
  • Blog
  • Events
  • Partner
  • Developers
  • KNIME Home
  • Careers
  • Contact us
Download KNIME Analytics Platform Read more about KNIME Business Hub
© 2025 KNIME AG. All rights reserved.
  • Trademarks
  • Imprint
  • Privacy
  • Terms & Conditions
  • Data Processing Agreement
  • Credits