In this 2-hour-long guided project, we will use an efficient net model and train it on a Brain MRI dataset. This dataset has more than 3000 Brain MRI scans which are categorized in four classes - Glioma Tumor, Meningioma Tumor, Pituitary Tumor and No Tumor. Our objective in this project is to create an image classification model that can predict Brain MRI scans that belong to one of the four classes with a reasonably high accuracy. Please note that this dataset, and the model that we train in the project, is for educational purposes only.
Class Deals by MOOC List - Click here and see Coursera's Active Discounts, Deals, and Promo Codes.
Project Prerequisite: Before you attempt this project, you should be familiar with programming in Python. You should also have a theoretical understanding of Convolutional Neural Networks, and optimization techniques. This is a hands on, practical project that focuses primarily on implementation, and not on the theory behind Convolutional Neural Networks.
We will be carrying out the entire project on the Google Colab environment so you will need a free Gmail account to complete this project.
This Guided Project was created by a Coursera community member.
In this Guided Project, you will:
- Learn to use Efficient Net to classify Brain MRI Scans in one of the four classes of Brain Tumor in Keras.
Learn step-by-step
- Introduction to the project.
- Clone dataset and Import Libraries
- Create directories to store Training and Test Data
- Data Visualization
- Create a function to crop images
- Save the cropped images to respective directories.
- Data Augmentation and Data Loading
- Model Creation
- Training and evaluating the model
- Prediction on Test Data
