Project ,

Breast Cancer Detection

In this project we will develop a model to classify the images of breast cancer and predict whether the given image belongs to class 0 or class 1 (Class 0 → No Invasive Ductal Carcinoma, Class 1 → Yes Invasive Ductal Carcinoma). 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 Vgg16 model with a transfer learning approach. 

What will you Learn in the Project?

  1. Loading the image data with ImageDataGenerator class
  2. Developing 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 Vgg16?


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

Tools Used

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

Tasks to be Performed

We will be performing the following tasks as part of this project:

Task-1: Import the dataset and divide it into a train/test/validation split.

Task-2: Develop a fully connected vanilla(base) CNN model

Task-3: Compile the model and do training with Early Stopping 

Task-4: Validate the base model on the test set

Task-5: Perform data augmentation on train set  

Task-6: Train and evaluate the updated model with augmented data

Task-7: Download the vgg16 model and freeze it’s all the weights

Task-8: Create a new model with vgg16

Task-9: Fit and evaluate updated vgg model

Task-10: Save the best model into Keras H5 format

+3 enrolled
Not Enrolled
or 99₹ 999
91% off

Skills you will develop

Develop CNN models in Keras

Plot loss and accuracy using Matplotlib

Transfer learning in Keras

Model training and validation in Keras

Saving the trained model in Keras