tarunsharma1 Goto Github PK

antcam

Repository containing code to detect, track and count ant species Liometopum occidentale in the wild (at ant nests).

bloom-filter

Bloom Filter in Python using Murmurhash3

caffe

Caffe: a fast open framework for deep learning.

caffe_examples

caltech-ee148-spring2020-hw01

Starter Code for Homework #1.

caltech-ee148-spring2020-hw02

Starter code for Homework #2.

caltech-ee148-spring2020-hw03

Starter code for Homework #3.

convergent-learning-between-deep-networks-on-different-tasks

This is an implementation of this paper http://arxiv.org/pdf/1511.07543v3.pdf

ct_classifier

Example repository for the CV4Ecology 2022 Summer School (lecture 4)

ethocam

Design files for ethocam project.

face-detection-in-unity-with-opencv-and-websockets

Face detection in unity using opencv and .net sockets to send frames. Also includes the python server file which is to be run. Video demo here - https://www.youtube.com/watch?v=QBSPOozqapI

github.io

handwritting-recognition-using-neural-networks

Handwritting recognition using 3 layer neural network

ka-lite

KA Lite: lightweight web server for serving core Khan Academy content (videos and exercises) without needing internet connectivity

ml_linear_and_logistic_regression_algorithms

Machine learning linear and logistic regression algorithm assignments , Coursera course on ML by Andrew NG

my_diary-app-wp8-for-beginers

Basic windows phone 8 diary app using sqlite for beginners. SQLite needs to be downloaded first using nuget packet manager.

olsen_classifier

opencv-projects

A collection of OpenCV projects done by me

phoneaswiiremote

Use your phone as a wii remote to play pc games.Accelerometer values from a windows phone are sent to a server build using nodejs and websockets .The server then sends the data to a java class which uses websockets in java and java.Robot class to perform approriate actions like keyPress

quadcopterarduino

Arduino code for a quadcopter which uses an mpu 6050 imu to read accelerometer , gyro and magnetometer readings and run it through a PID control system in order to make changes to the quadcopters rotor speeds.A kalman.h file is also included so that the user can use his own accelerometer plus gyro instead of using the mpu6050

real-time-video-content-based-ad-generator

Generates ads in real time based on the content of the video. The audio form a video is downloaded, split into smaller parts, and then each part is send to GoogleSpeechToText API to get the corresponding text for that part. The text is then sent to Alchemy API to get the semantic content , i.e. keywords and entities. The word 'ad' is then added to these keywords and a search is made on ask.com . The resulting images are scraped and placed in the webpage beside the video (Youtube API). Thus the ads on the side of the video change in real time as the content of the video changes. If the person is talking about cars, an ad about cars shows up and when he talks about bikes, an ad about bikes shows up. To download the audio only, and split the audio, we use ffmpeg and youtube-dl .We run the shell commands from php itself.

reinventing-the-process-of-buying-and-selling-land

Made at Housing Hackathon. Used Google Maps API, Google Places API, Android, HTML, Javascript, PHP and CSS

rockafly

saliency_metrics

semantic-content-based-app-recommender

A personilized app recommender for google play store which recommends an app based on the content of the most visited websites in the users web browsing history. Three layers of filtering is done to recommend the most useful app to a user based on his present interests(based on content of most visited sites). We get the content tags of a website from SimilarWeb API and then scrape the play store to recommend an app which is most similar to the content(most number of similar tags).

simclr

PyTorch implementation of SimCLR: A Simple Framework for Contrastive Learning of Visual Representations

simclr-pytorch

PyTorch implementation of SimCLR: supports multi-GPU training and closely reproduces results

skycams_flytracker

tracking flies using sky-facing cameras

suncet

Code to reproduce the results in the FAIR research papers "Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samples" https://arxiv.org/abs/2104.13963 and "Supervision Accelerates Pre-training in Contrastive Semi-Supervised Learning of Visual Representations" https://arxiv.org/abs/2006.10803

swachh_bharat

Volumetric estimation of garbage