sowmya-iyer Goto Github PK

abc-to-midi-

for Music Generation

adaptive-learning-rate-and-regularization-from-scratch-using-pytorch

Adaptive Learning rates: Momentum, Nesterov Momentum, and Adam; Regularization: L2

approaching-data

Ways to approach data before deciding on a model for csv and image data as well

bayesianadversarialdefense

Estimating the robustness of Baysian models towards Gradient-based Adversarial attacks

binary-sentiment-classification

Implemented Perceptron and Logistic Regression and compared their performance on the sentiment classification task

blood-vessel-segmentation-in-fundus-images-for-diabetic-retinopathy

We propose LadderNet, a convolutional network for semantic segmentation with more paths for information flow. We demonstrate that LadderNet can be viewed as an ensemble of FCNs, and validate its superior performance on blood vessel segmentation task in retinal images.

careerquest.in

In Progress

cognitive-ai-led-categorization-of-driver-stops-application

Unsupervised learning was leveraged on data (electric vehicle (two-wheeler) with GPS location fired every few seconds of delivery agents of a company) to analyze and categorize stops as hubs, driver location, illegal stops and delivery locations by clustering and reinforced it with location description extracted using Google Places APls

deep-learning-experiments

Notes and experiments to understand deep learning concepts

deploy-wordpress-to-a-non-window-instance

disaster-tweet-classification

edge-detection-using-opencv

fruit-image-classifier

Building a CNN from scratch

hmc-for-gaussian-mixture-model-parameters

GMM descibes a set of points in the 2D plane. Implemented a posterior sampler using the Hamiltion Monte Carlo (HMC) algorithm.

image-classification-on-cifar-10

isl2mocap

Using supervised learning, ISL Mocap dataset is built and rendered in blender

kaggle

leetcode-solutions

Sharing my leetcode submissions for reference

margsetu

Machine Learning powered Web Application to recommend you Massive Open Online Courses (MOOC) from Coursera 💙⚡

ml-for-beginners

Quick implementation of ML Concepts

mocapnet

We present MocapNET, an ensemble of SNN encoders that estimates the 3D human body pose based on 2D joint estimations extracted from monocular RGB images. MocapNET provides BVH file output which can be rendered in real-time or imported without any additional processing in most popular 3D animation software. The proposed architecture achieves 3D human pose estimations at state of the art rates of 400Hz using only CPU processing.

multimodal-transformers

opencv-basics

Looking beyond the images

opencv-mini-projects

OpenCV

qos-class-label-based-network-traffic-classification

reading-a-.db-file-using-python-sqlite3

scrape-youtube-video-python-

save youtube videos in a local file and also convert them into a gif

sowmya-iyer

sowmya-iyer.github.io

sowmya.github.io

My Portfolio Site | Made With @Gatsbyjs