Implementation of ResNet Model for CIFAR-10 Dataset with Data Augmentation

Developed a deep learning model using a custom ResNet architecture for image classification on the CIFAR-10 dataset. The model achieved a test accuracy of 91.65% with 4,991,306 trainable parameters. Utilized PyTorch framework, torchvision library, and implemented data augmentation techniques for improving model generalization. Employed early stopping and Adam optimizer during training for better convergence and model performance. Additionally, visualized training and validation accuracy/loss curves for model analysis.