Skip to content

KaziTanvir/Handwritten-Digit-Recognition-Using-Neural-Networks

Repository files navigation

Handwritten Digit Recognition Using Neural Networks

Welcome to Basic Image Classification with TensorFlow.

This graph describes the problem that we are trying to solve visually. We want to create and train a model that takes an image of a hand written digit as input and predicts the class of that digit, that is, it predicts the digit or it predicts the class of the input image.

Hand Written Digits Classification

Results

Accuracy Score: 0.9707
Confusion Matrix:
[[ 971 0 1 1 1 1 2 0 2 1]
[ 0 1118 4 1 0 1 2 0 9 0]
[ 5 0 1008 2 2 1 2 5 5 2]
[ 0 0 8 989 0 2 0 3 4 4]
[ 2 1 6 2 937 1 4 2 2 25]
[ 5 1 0 16 1 850 6 1 8 4]
[ 7 2 1 1 4 2 936 0 5 0]
[ 1 6 17 9 1 0 0 970 4 20]
[ 3 0 6 7 1 5 3 2 946 1]
[ 4 2 1 7 4 0 1 2 6 982]]
Precision:0.9707
Recall: 0.9707

download

About

Handwritten Digit Recognition Using Neural Networks

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages