Snehashis Chatterjee's Projects
Here half adders also design in behaviral model.
4bit adder
During my internship at âAchilles Resolute Private Limitedâ I used Deep learning-based segmentation algorithms to segment out below 40 days of baby's retinopathy images and also calculate the tortuosity index to find the severity of the diseases. Challenge in this work is that mask binary dataset is not given. so we have to collect some datasets from different fundus datasets and train the model. Also, baby's retinopathy images are not very clear as fundus dataset, so image processing techniques also used to fix these issues.
Python library for adversarial machine learning, attacks and defences for neural networks, logistic regression, decision trees, SVM, gradient boosted trees, Gaussian processes and more with multiple framework support
Course Project for EE782. IIT Bombay, Autumn 2019
Determine whether an image contains a columnar cactus
Face-recognition using Siamese network
This is my work in SkyBits Technologies Pvt Ltd (http://sky-bits.com/) from 1st August 2019 to 30th September 2019. During this time, I was to design a novel machine learning-based model were using my Laptopâs microphone it recorded 15-sec audio and divided 15sec audio into three parts, took the decision for each part whether that part was loudly or non-loudly.
A curated list of awesome resources for image alignment and stitching ...
image registration related books, papers, videos, and toolboxes
Must read research papers and links to tools and datasets that are related to using machine learning for compilers and systems optimisation
A curated list of references for MLOps
Multi-camera Network research resources
âļī¸ An awesome list of awesome YouTubers that teach about technology. Tutorials about web development, computer science, machine learning, game development, cybersecurity, and more.
OpenAI Baselines: high-quality implementations of reinforcement learning algorithms
BCCD (Blood Cell Count and Detection) Dataset is a small-scale dataset for blood cells detection.
Bitwise is an educational project where we create the software/hardware stack for a computer from scratch.
Design a CNN based deep learning model which classify both blurred and not blurred versions of a data set where at least one class is extremely rare i.e it is a highly unbalanced dataset and deploys it in a web app
Deep Neural Networks Improve Radiologists' Performance in Breast Cancer Screening
ByteTrack: Multi-Object Tracking by Associating Every Detection Box
A simple trace-based cache simulator
using k means algorithm with the help of opencv python library detect the reduction of forest area.
TMI 19: CANet: Cross-disease Attention Network for Joint Diabetic Retinopathy and Diabetic Macular Edema Grading
Seed repo for CVPR'21 Continual Learning Challenge
This data set is downloaded from kaggle. Ultra sound images are.It is a binary classification using Deep learning CNN and our target metric is ROC-AUC score. AUC represents the probability that a random positive (green) example is positioned to the right of a random negative (red) example.My present ROC score is about 0.75.I try to further optimize it
Examples of clever code that I have found
Convert pre-trained classifier to object detector without training
Continual Learning tutorials and demo running on Google Colaboratory.