Digit Recognizer Competition from Kaggle

This is a modification of the notebook posted by YASSINE GHOUZAM (https://www.kaggle.com/code/yassineghouzam/introduction-to-cnn-keras-0-997-top-6/notebook). Here I used a 5 layers Sequential Convolutional Neural Network for digits recognition trained on the provided dataset from Kaggle (https://www.kaggle.com/competitions/digit-recognizer/data). I built it with Keras from Tensorflow which is very intuitive.

First

I will prepare the data (handwritten digits images) then i will focus on the CNN modeling and evaluation.

I achieved 99.4% of accuracy with this CNN trained in 15 min on a M1 Macbook Air.

Name		Name	Last commit message	Last commit date
Latest commit History 9 Commits
.ipynb_checkpoints		.ipynb_checkpoints
.DS_Store		.DS_Store
.gitattributes		.gitattributes
MNIST-CNN-ENSEMBLE.csv		MNIST-CNN-ENSEMBLE.csv
README.md		README.md
cnn_mnist_datagen.csv		cnn_mnist_datagen.csv
digit recognizer_CNN.ipynb		digit recognizer_CNN.ipynb
digit recognizer_CNN_v2.ipynb		digit recognizer_CNN_v2.ipynb
test.csv		test.csv
train.csv		train.csv