Skip to content
Classification of MNIST handwritten digits & custom handwritten digits.
Python
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
README.md
project6.py

README.md

PROBLEM

Train a convolutional neural network to recognize the MNIST handwritten digits.

TODO

  1. Succesful training and testing of classifier indicating training and test accuracies.
  2. Live demo presenting capture and detection of handwritten digits.
  3. Extra Credit: Live Demo presenting localization and identification of a handwritten digit that has been embedded in another image.

Results

Training:

Loss: 0.0620, Acccuracy: 98%

Testing:

Loss: 0.03162, Accuracy: 98.91%

You can’t perform that action at this time.