<- back to the overview

This model will recognize handwritten digits in an image from the MNIST data set. It is based on a Convolutional Neural Network (CNN) implemented in Keras and trained on the publicly available MNIST (https://en.wikipedia.org/wiki/MNIST_database) data set.

The data set contains a large number of handwritten digits. The network learned to recognize the digits and classify which number is visible in the image.

The model will return the classified number and also the certainty of the model (from 0.00-1.00)

These handwritten digits are available for testing:

you can save one of these and use them as input for this handwriting recognition model.

The following tutorial will help you to make your own handwriting recognition deployment in UbiOps: ubiops.com/docs/ubiops_tutorials/ready-deployments/image-recognition/image-recognition/ 


This model is intended for demonstration and testing purposes only. UbiOps is not liable for any damages arising from the use or inability to use any of the models and applications listed on the UbiOps Community Model pages. Even though UbiOps and our partners carefully created and optimized these models, it is always advised to benchmark and check the respective functionality before applying it in any production setting.

Created: 20-11-2021

Last modified: 16-12-2021

Publisher: UbiOps

This model will recognize handwritten digits in an image from the MNIST data set.

Import this model in your UbiOps project

Do you want to run this model yourself? Follow the steps below:

  1. Log in to your UbiOps account,
  2. Go to Imports & Exports
  3. Click “Create Import” and select the Import from link tab
  4. Copy & Paste the URL below and click “Next”