Fashion_MNIST

Classifying the fashion models using deep learning

Problem statement:

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. Our aim is to classify the images

Description :

The dataset contains the images of articles in the form of pixel values and its labels in target variable.

class labels ---> 0:t-shirt/top, 1:trouser, 2:pullover, 3:dress, 4:coat, 5:sandal, 6:shirt, 7:sneaker, 8:bag, 9:ankle boot

We have to classify the images on test data after training the model using the train data. For implementing this i am using deep learning methodology.

Tasks perfromed :

1. Reading the dataset & EDA analysis on the dataset

2. building the sequential model on train data using deep neural network

3. evaluation of model on test data based on accuracy metrics

4. checking the predicted labels which are matching with the original test images using plots

Dependencies:

Python 3+, jupyter notebbook, Pandas, Numpy, Tensorflow, Keras, Matplotlib

Purpose:

The purpose of this project is to gain insights, capability building & help others in

a) Pratical implementation of deep learning using Tensorflow and keras in Fashion-MNIST dataset

b) classifying the different fashion models using deep network

c) Knowing the intricacies about deep neural network