The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors

CoTracker is a model for tracking any point (pixel) on a video.

Simple UI for LLM Model Finetuning

Data & Code for my video on the Pandas library of Python

Visualizing the internal board state of a GPT trained on chess PGN strings, and performing interventions on its internal board state and representation of player Elo.

Code for our MIDL2020 submission "Well-Calibrated Regression Uncertainty in Medical Imaging with Deep Learning".

Ensemble based transfer learning approach for accurately classifying common thoracic diseases from Chest X-Rays