This project is about developing a Deep Learning Model based on Fashion-MNIST dataset using Convolutional Neural Networks to classify images according to their type.
Fashion-MNIST is a dataset of Zalando's article images consisting of a training set of 60,000 examples and a test set of 10,000 examples. Each example is a 28x28 grayscale image, associated with a label from 10 classes. https://www.tensorflow.org/datasets/catalog/fashion_mnist
The Python Code is set in Jupyter Nitebook IDE. The code is all about importing libraries,loading datasets, preprocessing the data,visualising samples, building the CNN model,compiling and then fitting it,and then predicting the test data labels and further validating and evaluating the model and finally saving it. The model architecture can be seen as in model_plot.png.
The model has Testing Accuracy of 92.61% , F1_Score of 92.61% and Precision_Score of 92.71%.