Adhiraj Ghosh's Projects
City Biking Project - Data Literacy
Object Detection Model to accurately detect whether a person in an image is wearing a face mask or not.
Training a neural net to classify whether a person is wearing a face mask or not.
Code for the paper: "No Zero-Shot Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance"
First repository on GitHub.
This project deals with the task of implementing instance segmentation for a given dataset using Mask-RCNN architecture.
This is the project page of the dataset for the binary and multi-label classification of irony in Bengali Tweets.
The first course of the Mathematics for Machine Learning Specialisation by Imperial College, London.
This repository contains the programming assignments of the popular Coursera Course, "Neural Networks and Deep Learning" by deeplearning.ai. This repository contains the notebooks used during the assignement as well as the course certificate.
Tool to render modified .png files from .svg encoded graphics for music notes. Helpful in post-processing for object detection in Optical Music Recognition.
[TISMIR'23] The official code for implementing Unsupervised Domain Adaptation from "Real world music object recognition"
This repository contains a working LSTM model for the Kaggle Competition to Predict Future Sales of a Russian Software firm.
Code for assignements and certificate of Python for Data Science by IBM on Coursera.
[WACV'23] The official code for "Relation Preserving Triplet Mining for Stabilising the Triplet Loss in Re-identification Systems"
Official code of the paper "Align Deep Features for Oriented Object Detection"
Superpixel based segment generation
Triplet Loss Optimization for car datasets
[EMNLP'23] ViPE: Visualise Pretty-much Everything
Generating music videos through ViPE and deforum stable diffusion