Gear Up November Sale: 15% Off on All Courses | Use Coupon GO15 During Checkout | Offer Expires In

  Enroll Now

Training from Scratch vs Transfer Learning

1 / 8
 

About the Project

Objective

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(articles) from the given images using Machine Learning.

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

  1. Importing the libraries

  2. Loading the data

  3. Splitting the data

  4. Visualizing the Data

  5. Building the Model

  6. Fitting the Model

  7. Evaluating the Model Performance


Acknowledgements

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

What are we going to do?

We will train a neural network (say model A) on data related to 6 of the classes, and we will train another neural network (say model B) on the remaining 2 classes. Then, we would use the pre-trained weights of model A and tune the last layer so as to classify these 2 classes(this technique is called Transfer Learning), and compare the results of classification obtained using normal training and transfer learning. In this project, we would practically appreciate the use of Transfer Learning.


No hints are availble for this assesment

Answer is not availble for this assesment

Loading comments...