In this lab, we learn how to create and train a Convolutional Neural Network (CNN) using PyTorch.
The main goal is to classify images from the CIFAR-10 dataset and compare the performance of Fully Connected Networks (FCN) and CNNs.
- Basic PyTorch operations
- Understanding CNN architecture and components
- Loading and preprocessing image data
- Building and training a simple CNN
- Evaluating performance on a test set
- Using pre-trained models for image classification
- Python
- PyTorch
- torchvision, torchsummary
- NumPy, Pandas
- Matplotlib, scikit-learn