This repository contains the solutions to the assignments of the EVA4 course conducted by The School of AI
Achieve 99.4% test accuracy on the MNIST dataset with a CNN using less than 20,000 parameters and 20 epochs.
Achieve 99.4% test accuracy on the MNIST dataset with a CNN using less than 10,000 parameters and 15 epochs.
Apply L1 and L2 regularization on Session 5 code and compare the models.
Achieve 80% test accuracy on the CIFAR-10 dataset with a CNN using less than 1M parameters and make use of advanced convolutions.
Achieve 85% test accuracy on the CIFAR-10 dataset with ResNet18 using image augmentation.
Achieve 87% test accuracy on the CIFAR-10 dataset with ResNet18 using albumentations for image augmentation. Implement GradCAM to visualize heatmaps.
Achieve 88% test accuracy on the CIFAR-10 dataset with ResNet18. Implement Leslie Smith LR finder to find the best starting learning rate and use ReduceLROnPlateau.
Achieve 90% test accuracy on the CIFAR-10 dataset with a custom ResNet architecture and One Cycle Policy for faster convergence.
Achieve 50% test accuracy on the tiny-imagenet-200 dataset. Make a custom dataset of 50 dogs and find optimal template anchor boxes.
Perform object detection using OpenCV Yolo implementation. Create a custom dataset of a unique object not present in the existing COCO classess and train YoloV3 on the custom class.
Create a custom dataset for monocular depth estimation and segmentation simultaneously.
Use the dataset created in Session 14 and build a monocular depth estimation and segmentation model.