ICP_Deep Learning 4 - PallaviArikatla/Python GitHub Wiki

INTRODUCTION: Working on image classification with CNN followed by training and evaluating.

IMPLEMENTATION:

Question 1: Follow the instruction below and then report how the performance changed.(apply all at once)

• Import all the necessary libraries.
• Read and split the data to train and split.
• Before making changes, create the model.

• Compile the model.
• Model gets created.

• Fit the model and evaluate the model.
• Calculate the accuracy and print it.

• Save the model and read the model.

Question 2: predict the first 4 image of the test data. Then, print the actual label for those 4 images (label means the probability associated with them) to check if the model predicted correctly or not.

• Find predict class using model,predict_classes using the test image.
• Find the actual value and get the actual and predicted value.

Question 3: Visualize Loss and Accuracy using the history object.

• Take the values of accuracy from the above and plot the graphs against them.
• Plot graphs for both loss and accuracy.

Bonus Question:

• Consider the saved model from question 1.
• Find predict class using model,predict_classes using the test image.
• Find the actual value and get the actual and predicted value.