Code to fine-tune t5-small model and push it to hugging face, and a flask server that can use the deployed model to run our application.

Developed a personalized scholarly title generation system by fine-tuning the Flan-T5 base language model on the LaMP dataset, enhancing the ROUGE score by 80%. Conducted a comparative analysis of …

The Auto Grader system is designed to automatically evaluate coding solutions submitted by students against predefined test cases.

The classic Tic-Tac-Tow game with a modified rule of board getting refreshed after certain turns.

Trained a CNN to perform facial key-point detection. The key-points are positioned on the features of a face, such as the eyebrow, nose, and mouth.

This is used for capstone project

We worked on action recognition in search and rescue using drone surveillance. Our aim was to classify a video on help or non-help class. Which can be used during a disaster as at many places peopl…

Applied various ML models for Image Denoising on CIFAR-10 Dataset

We have built a profound neural network that capacities as a major aspect of a machine translation pipeline. The pipeline acknowledges English content/picture as info and returns the French interpr…

Made a CNN achieving accuracy greater than 99.94% with less than 8000 parameters on MNIST Dataset.

Contains all the codes which i did while learning machine learning.

Classifier project as a part of IBM data science professional certification

Adding a new system call Trace in XV6.

Solving Josephus Problem using C++