Part 1: Image Classification
CNN architecture: Two convolutional layers including batch normalization, relu and maxpool in each along with two fully connected layers with a relu after the first fc. Batch size = 100, learning rate = 0.0007 and number of epochs was 10.
Sample images from the dataloader along with their classes
Testing accuracy for each class
Validation accuracy for each class
Train(orange) and validation(blue) accuracy plots
Examples of correctly predicted classes (in green)
Examples of Incorrect predictions (in red)
I couldn't get my code to run for part 2 unfortunately. :(