Nwoye Chinedu's repositories
ConvLSTM-Surgical-Tool-Tracker
This repo contains an implementation code for the weakly supervised surgical tool tracker. In this research, the temporal dependency in surgical video data is modeled using a convolutional LSTM which is trained only on image level labels to detect, localize and track surgical instruments.
ivtmetrics
A Python evaluation metrics package for surgical action triplet recognition
Chatbot
My Chat bot codes
cholectriplet2022
CholecTriplet 2022 challenge on surgical action triplet detection
nwoyecid.github.io
Research Outlook of Chinedu Nwoye
rendezvous
A transformer-inspired neural network for surgical action triplet recognition from laparoscopic videos.
Doccou
A file pages counter
google-research
Google Research
Graph-Cut
Graph-cut Image Segmentation ---------------------------- Implements Boykov/Kolmogorov’s Max-Flow/Min-Cut algorithm for computer vision problems. Two gray-scale images have been used to test the system for image segmentation (foreground/background segmentation) problem. Steps: 1. defined the graph structure and unary and pairwise terms. For graph structure, i have used available packages/libraries such as PyMaxflow. 2. likelihood function for background and foreground has been generated. 3. General energy function consisting of unary and pairwise energy functionals have been written. 4. Likelihood maps (intensity map ranging from 0 to 1) for foreground and background have been displayed. 5. Use Boykov/Kolmogorov maxflow / mincut approach for solving the energy minimization problem. 6. Final segmentation have been displayed. Created an image for which the background pixels are red, and the foreground pixels have the color of the input image. Relevant paper can be found here: http://www.csd.uwo.ca/~yuri/Papers/pami04.pdf
imagen-pytorch
Implementation of Imagen, Google's Text-to-Image Neural Network, in Pytorch
MachineLearningTechniques
Southampton Machine learning lab practices
MCMOT-ByteTrack
ByteTracker with a multi-class capability
ML_Algo_Implemented
Bare-bone and simple implementations of few Machine Learning Algorithms
new_website
a fork of https://jonbarron.info/ for use in jekyll builds with markdown page updates
option_pricing
Black Scholes, Binomial Lattice of Pricing European and American call and put options
tensorflow
Computation using data flow graphs for scalable machine learning
TensorFlow-Tutorials
TensorFlow Tutorials with YouTube Videos
TrackEval
HOTA (and other) evaluation metrics for Multi-Object Tracking (MOT).
YOLOV4_MCMOT
Using YOLOV4 as detector for MCMOT.