Minimum-distortion embedding with PyTorch

An easy to use Neural Search Engine. Index latent vectors along with JSON metadata and do efficient k-NN search.

Unsupervised detection of opening / closing credits, recaps, and previews in video files 🎥🍿🎬

Tracktable: moving object trajectory analysis in C++ and Python

Language modelling for sound event detection

Librarian: An Empirical Study of Security Updates in Android Apps’ Native Code

This is a Content Based Image Retrieval System(CBIR) where the program takes some input images and extracts the image feature vectors and stores them. When another image is given as a query image to the program it searches for all similar images that are given as input

CRISP is a Fast Image Search application that retrieves similar images from a database based on the query image by using Parallel computing paradigm.

Computer Vision and Deep Learning exercises from Udacity's Computer Vision Nanodegree

In this project, we use a Deep Recurrent Architecture, which uses CNN (VGG-16 Net) pretrained on ImageNet to extract 4096-Dimensional image feature Vector and an LSTM which generates a caption from these feature vectors.

A study on encoding english sentences to tensorflow vectors or tensors using pre-trained BERT model from the Hugging Face Library.

recommendation engine project

This program demonstrates how to plot face feature vectors on a 2-D chart using t-SNE method to compress dimension of the vectors

Test fixtures for data science

Program performs text classification using BERT vector with Logistic Regression and Neural Network Models.

CNN with transfer learning for animal image detection