Convolutional Neural Network with PyTorch

In this assignment you will design and train a convolutional neural network (CNN) for image classification using PyTorch.

You will cover:

• Convolutional layers: Apply nn.Conv2d with various filter sizes, strides, and padding settings; understand how they detect local features.
• Pooling: Use max-pooling and average-pooling to reduce spatial dimensions and build translation invariance.
• Architecture design: Stack convolutional blocks followed by fully connected layers to form a complete classification pipeline.
• Training and evaluation: Train the network on an image dataset, monitor loss and accuracy, and evaluate on a held-out test set.
• Visualization: Visualize learned filters and feature maps to develop intuition about what each layer captures.

Problems will be released closer to the due date.