Project ,

Skin Cancer

In this project, we’ll develop a model to classify the images of skin cancer and predict whether the given image belongs to class malignant or class benign. We’ll develop a base model and then learn how we can improve the accuracy or reduce the underfitting/overfitting of the model using different techniques such as data augmentation and transfer learning. We’ll start with the vanilla model and then move to the ResNet50 model, and at the end, we’ll learn how to make inferences on a single image. 
Course
Curriculum

What will you Learn in the Project?

  1. Loading the image data with ImageDataGenerator class
  2. Developing the CNN model and compiling and fitting it on the train set
  3. How to perform Data Augmentation?
  4. How to do transfer learning with pre-trained models such as ResNet50?

Prerequisite

  1. Woking knowledge of Keras library 
  2. Understanding of different convolution methods and operations i.e. Filter, kernels, padding, pooling 

Tools

  1. Google Colab for training the model
  2. Matplotlib library for visualizing the loss & accuracy of the model 
  3. Keras[tensorflow]

Tasks

We will be performing the following tasks in this project:

Task-1: Import libraries and load the data with ImageDataGenerator class

Task-2: Build a vanilla[base] CNN Model

Task-3: Compile and fit the base model

Task-4: Plot the results of loss and accuracy of the base model

Task-5: Perform different data augmentation techniques on the train set 

Task-6: Build a new model on augmented data and perform model evaluation

Task-7: Transfer Learning with ResNet50

Task-8: Build new ResNet Model and fit it on the dataset

Task-9: Inferencing on the test image with best performing model

+4 enrolled
Not Enrolled
or 99₹ 999
91% off

Skills you will develop

Developing CNN models in Keras

Plotting loss and accuracy using matplotlib

Data Augmentation techniques

Transfer learning in Keras

Model training and validation in keras

Making predictions on a single test image