https://github.com/anik120/pl-image_classification

A simple ChRIS plugin to classify images.
https://github.com/anik120/pl-image_classification

image-classification machine-learning opensource tensorflow

Last synced: 2 months ago
JSON representation

A simple ChRIS plugin to classify images.

• Host: GitHub
• URL: https://github.com/anik120/pl-image_classification
• Owner: anik120
• License: mit
• Created: 2018-03-27T17:37:39.000Z (over 8 years ago)
• Default Branch: master
• Last Pushed: 2018-03-28T14:55:23.000Z (over 8 years ago)
• Last Synced: 2025-06-04T23:19:11.084Z (about 1 year ago)
• Topics: image-classification, machine-learning, opensource, tensorflow
• Language: Python
• Homepage:
• Size: 9.77 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.rst
  • License: LICENSE

Awesome Lists containing this project

README

          
################################

pl-image_classification

################################

Abstract

********

This is a demo ChRIS plugin app.

The image plugin runs a neural network to perform a supervised machine learning 

task (Classification) on the MNSIT data set.

The MNIST data set is a database of images of handwriten digits, with 60,000 

training data points and 10,000 test data points.

You can learn more about the MNIST data set here: http://yann.lecun.com/exdb/mnist/

Run

***

* In your pwd, make two directories and name them 'in' and 'out'.

* Download the dataset from http://yann.lecun.com/exdb/mnist/ and move the 

downloaded files (.gz) files to the 'in' folder.

* Using ``docker run``

====================

Assign an "input" directory to ``/incoming`` and an output directory to ``/outgoing``

.. code-block:: bash

    docker run --rm -v $(pwd)/in:/incoming -v $(pwd)/out:/outgoing   \

            fnndsc/pl-image_classification image_classification.py            \

            /incoming /outgoing

This will ...

Make sure that the host ``$(pwd)/out`` directory is world writable!