Master's Thesis on Simultaneous Localization and Mapping in dynamic environments. Separately reconstructs both the static environment and the dynamic objects from it, such as cars.

Density-aware Single Image De-raining using a Multi-stream Dense Network (CVPR 2018)

[ACCV22] Structure Representation Network and Uncertainty Feedback Learning for Dense Non-Uniform Fog Removal, https://arxiv.org/abs/2210.03061

Efficient matrix representations for working with tabular data

Implementation of Artificial Neural Networks using NumPy

The RAG Experiment Accelerator is a versatile tool designed to expedite and facilitate the process of conducting experiments and evaluations using Azure Cognitive Search and RAG pattern.

Upsampling method for an input cloud using mls method of PCL

A QT tool used to annotate temporal segments of a video with events which each have unique and customisable information.

Hand Gesture Recognition using CNNs and Perceptrons in realtime (OpenCV)

Continuation of the original pimd-dense from 1998-1999, gaps filled with frog DNA from pimd

A subpixel dense refinement U-NET like architecture for Vessel Segmentation from Retinal fundas images

Intrusion Detection System - IDS example using Dense, Conv1d and Lstm layers in Keras / TensorFlow

layers

Cholesterol is calculated from the given set of data.

CP-APR Tensor Decomposition with PyTorch backend. pyCP_APR can perform non-negative Poisson Tensor Factorization on GPU, and includes an interface for anomaly detection using the extracted latent patterns.

PIM-DM multicast routing protocol implementation (RFC3973)

Free WordPress Plugin: This volume calculator uses a density formula ρ = m/V to find densities of different substances and objects. It calculates the third one for two given values - density, mass, or volume of a substance. www.calculator.io/density-calculator/

Implementation of a multicast routing protocol named HPIM-DM (dissertation work)

A Fast, Extensible Trainer and Extensions for Pytorch

Cross-platform mobile Neural network C library for training and inference on the device. CPU only. It fits for time-series data.