End to End ML Project - Fashion MNIST - Description

Objective

The objective of the project is -

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.

The objective of the project is - to use Fashion-MNIST data set to identify (predict) different fashion products from the given images using Machine Learning.

We will be following the below steps to solve this problem:

1. Importing the libraries

2. Using some pre-defined utility functions

3. Loading the data

4. Cleaning the data

5. Dividing the dataset into training and test dataset using train_test_split in the ratio 85:15

6. Training several models and analyzing their performance to select a model

7. Use dimensionality reduction to improve the ‘training’,
   ‘fine-tuning’ and ‘prediction’ time.

8. Fine-tuning the model by finding the best hyper-parameters and features

9. Evaluating selected model using test dataset

Acknowledgements

Cloudxlab is using this “Fashion MNIST” problem for its machine learning learners for learning and practicing. Fashion-MNIST dataset is a collection of articles images provided by Zalando . We thank Zalando Research for hosting the dataset.