Ayanabha's repositories
rice-classification-pytorch
Rice Species Classification using ResNet-18 and a Custom defined CNN, both using PyTorch. If you are getting started with PyTorch, then you may consider cloning this repo and start learning :)
bangla-ocr-transformer
Implementation of the paper 'Towards Full page Offline Bangla Handwritten Text Recognition using Image-to-Sequence Architecture'. For details, please read the README section.
handwritten-character-recognition-banglalekha
Handwritten Bangla Character Classification using ResNet-34 trained using BanglaLekha Dataset. System has been implemented in PyTorch. For details, see the README file.
banglalekha-numerals-classification
Handwritten Bangla Numeric Digits Classification using ResNet-34. The work uses a subset of the BanglaLekha-Isolated dataset. For details, read the README file.
blockchain-from-scratch-sample
This is my solution of Blockchain implementation for the fulfillment of Assignment-1 of the course 'Introduction to Blockchain' (Instructor : Dr. Debashis Das; Run : Fall 2022). Go through the README file for execution instructions.
cuda-samples
Samples for CUDA Developers which demonstrates features in CUDA Toolkit
data-structures-c
Includes implementations of basic data structures using C language. This Repo is the Solutions of Assignment-1 of DSA Bridge Course, which is a mandatory course for all M.Tech. CSE, M.Tech. AI and M.Tech. DCS students and offered in Fall 2021, Indian Institute of Technology Jodhpur.
data-structures-python
Includes implementations of basic data structures using Python language. This Repo is the Solutions of Assignment-1 of DSA Bridge Course, which is a mandatory course for all M.Tech. CSE, M.Tech. AI and M.Tech. DCS students and offered in Fall 2021, Indian Institute of Technology Jodhpur.
get-started-python
A Python application and tutorial that use Flask framework to provide a REST API to receive requests from the UI. The API then persists the data to a Cloudant database.
machine-learning-csl7550
This repository contains the solutions of all the assignments which were given in the course Machine Learning (CSL7550). For details, please refer to the README.md file.
scene-reconstruction-edge-metadata
Reconstruction or Approximation of environment from edge data. Using pre-trained models, we are analyzing the incoming edge data (CCTV camera footage) and extracting the detected objects and person's pose. These metadata are sent to remote server, where using these metadata, the video scene is reconstructed or approximated on a Real-time manner.
sentiment-analysis-imdb
Using different Supervised Learning techniques with different settings of their hyperparameters to capture the sentiment from IMDb Movie Reviews dataset.
heart-failure-random-forest
Using the Heart Failure Prediction dataset from Kaggle, I have tried to build a basic classifier using Random Forest to determine whether a patient can die based on some clinical diagnosis (features). Furthermore, I have tried to show whether there is a direct correlation between Diabetes and Death due to Heart failure by determining the number of patients having Diabetes died due to Heart failure. For more details, please go through the Readme file.
information_retrieval_au20
Information Retrieval assignment solutions done by me. Course Code - ECS44204, Elective. Instructor : Mr. Dipanjan Banerjee, Asst. Prof of CSE, Dept. of CSE, Adamas University, Kolkata.
logistic-regression-imdb
Sentiment analysis using 50,000 reviews taken from IMDb movie reviews. The classifier used is Logistic Regression and the Pipeline uses TFIDF-LR.
machine-learning-business-fall2022
All Assignment solutions of the course Machine Learning Applications for Business (MSL7380) of Fall 2022 run, School of Management and Entrepreneurship, IIT Jodhpur.
mnist-cnn-pytorch-beginners
Basic custom CNN for MNIST dataset classification using PyTorch. If you are getting started with pytorch and want to get some elementary example, this notebook is for you :)
simple-mnist-cnn-beginners
A basic Convolutional Neural Network for classifying the MNIST handwritten digits. For understanding the code, read the brief documentation in the uploaded Jupyter notebook.