DenseNet implementation in Keras

A Simple Traffic Generator for Hyperledger Fabric

Learning Finite State Representations of Recurrent Policy Networks

SKYProfiler is a performance monitoring tool for Integration Server. SKYProfiler tracks the service invocations and the monitored data can be seen in real time. This helps users track the time each service invocation takes and further drills down to the child service to identify which service contributes to time.

Tensorflow implementation of deep variational information bottleneck

This project consists of C++ implementations of a 3D Rapidly Exploring Random Tree and three other extensions called RRT*, Execution Extended RRT and Synchronised Greedy Biased RRT. It also includes a heuristically guided RRT* with biased sampling towards relevant bottleneck points predicted by a 3D CNN(modified VoxNet in Tensorflow).

Leibniz is a python package which provide facilities to express learnable partial differential equations with PyTorch

Code for the paper: "On the Bottleneck of Graph Neural Networks and Its Practical Implications"

99.7% accuracy solution for Dogs vs Cats Redux Kaggle competition

Finding bottlenecks in applications -- an example

A sparse bottleneck neural network to predict electrophysiological properties of neurons from their gene expression.

🔧 Performance Optimization Project - Simulated real-world scenario where a Desktop VR application must be optimized for release

Visualize the Latent Space of an Autoencoder using matplotlib

simple ABM program to simulate a moving danger (e.g., fire) and people in a confined space trying to escape the danger

Logs times of page creations and intermediate results to spot bottlenecks in Islandora stack.

Term 2 Project 1 Dog Breed Classifier and human face detector using ImageNet, superhuman CNNs, and Haar Cascades

single-file "bottle.py" , a website-application µ framework

A Keras implementation of YOLOv3 (Tensorflow backend)

A likely error-prone bottleneck.