Srinivas Venkatanarayanan's repositories
DetectNTrack
A multi threaded implementation of Detection and tracking with YoloV5 in C++
Adabins-FOHIS
Generating realistic Synthetic fog using FOHIS and Adabins
CerebralSignalNetworks
An exploration of experiments based on EEG signals used for vision tasks - Medical Image Computing
panoptes-service
Web service and aws deployment for Natural language video search engine
Adaptive-Networks-Experiments
Experiments on adaptive networks.
AE-NE
Original implementation of the model AE-NE described in the paper " Autoencoder-based background reconstruction and foreground segmentation with background noise estimation"
Brain-Tumour-Segmentation
Brain tumour segmentation on BRATS
ChestXRayClassification
Chest XRay Classification - Assignment work for Medical Image Computing
Deep-WB
Experiments for Neural illumination maps for color correction and White balance
DEI-Hate-Scoring-System
A DEI Hate scoring tool to identify hateful sentences for DEI Compliance audits
DL-AWB-Lib
A bunch of Automatic White-Balancing (AWB) Algorithm Implementations
ElementalExplorations
Fundamental explorations of all basic algorithms that we encounter in Life from Signals, AI, Math to philosophy
ENSA-Nets
Efficient Neural Scene adaptation Networks for video tasks
EZ-CLIP
EZ-CLIP Experiments
FlexiVit-Experiments
Experiments around FlexiVIT with different patch sizes, analysing the representation power. Knowledge distillation is also present.
gpt4v-browsing
Web Scraping with GPT-4 Vision API and Puppeteer
Graph-Language-Retrieval
Natural Language Retrieval from Language graphs
LaneDetector
Lane Detector C++ Implementation.
MADE
MADE experiments
observe-rs
A Video moment retrieval framework on Rust
obsidian-template
Starter templates for Obsidian
OpticalNeuralNetwork-LatentLensing
Optics Inspired Neural Network with Neural Lensing strategy - A new type of neural network
rust-design-patterns
Rust design patterns
segment-anything-fast
A batched offline inference oriented version of segment-anything
sheeprl-SSL
Distributed Reinforcement Learning accelerated by Lightning Fabric
vi-sri.github.io
A personal blog about exploring the sciences of perception and cognition modeled into computers.
VideoLAN-EyeMan
Stream Video over LAN Wifi, Do Pose estimation and classification over the stream.
vlm_distillation
Distilling Large Vision-Language Model