To classify the drawn figure to be a fashion product and predict the product.
Fashion MNIST Training dataset consists of 60,000 images and each image has 784 features (i.e. 28×28 pixels). Each pixel is a value from 0 to 255, describing the pixel intensity. 0 for white and 255 for black.
Training Data
training and fitting the model
demo model
Model Architecture
Model training graph
LEARNING GRAPH 1
LEARNING GRAPH 2
Conclusion
With our final CNN model, we could achieve a training accuracy of 94% and test accuracy of 93% confirming that model is fine with no overfitting.
If you remember, with Machine Learning model (XGBoost) I had achieved a test accuracy of 84.72 %, and with Deep Learning model (CNN) here I could achieve a test accuracy of 93 %. Thus, we got around 8% improvement in accuracy by using Deep Learning.
Though, in this case, we got a good improvement in accuracy score (8%), still there may be a chance to improve performance further, by say, increasing the number of convolutional layers (and neurons/filters) or trying out different combinations of different layers.
