Pinned Loading

1. MNIST-Classification MNIST-Classification Public

   Implementation of ViT (Vision Transformer) and LeNet from scratch using PyTorch for the MNIST classification task. Ran multiple experiments to understand the impact of dataset size, network depth, …

   Jupyter Notebook

2. Object_Detection_And_Tracking Object_Detection_And_Tracking Public

   Explored Classical and DL based approaches - Employed the Viola-Jones facial classifier for face detection and tracking, adjusting hyperparameters to optimize the quality of detections and tracks. …

   Jupyter Notebook

3. UNet_Segmentation UNet_Segmentation Public

   Segmentation pipeline that uses a U-Net backbone to perform segmentation on the Cityscapes dataset. Conducted experiments to analyse the impact of the skip connections of the U-Net on the quality o…

   Jupyter Notebook

4. Pose_Shape_Optimisation_Pipeline Pose_Shape_Optimisation_Pipeline Public

   Pipeline to accurately and efficiently compute the shape and orientation (pose) of a car given its RGB image by using keypoints generated from an hourglass network after optimising the estimates us…

   Python

5. Camera_LiDAR_Calibration Camera_LiDAR_Calibration Public

   Implemented an end-to-end calibration pipeline starting with an uncalibrated camera. Utilized checkerboards along with Zhang's camera calibration method to calibrate the camera. Applying the PnP al…

   Jupyter Notebook

6. Statistical-Methods-In-AI-M23 Statistical-Methods-In-AI-M23 Public

   Coursework done as part of the Statistical Methods in AI course offered in Monsoon 2023 by Prof. Ravi Kiran Sarvadevabhatla, IIITH. Topics covered include KNNs, Decision Trees, Dimensionality Reduc…

   Jupyter Notebook 1