williamcfrancis

GPT4_fixes_reward_hacking

A simple method to fix reward hacking in the Deepmind AI Safety Gridworlds using GPT4

Blind-Motion-Deblurring-for-Legible-License-Plates

A novel approach to blind motion deblurring by converting a non-blind method (Weiner Deconvolution) to a blind method using Deep Learning

CNN-Image-Colorization-Pytorch

PyTorch implementation of a convolutional deep neural network to colorize grayscale images. Includes sample dataset and code for training, inference, and color temperature control.

EKF-and-UKF-for-3D-Robot-Orientation-Tracking

Python implementation of an Unscented Kalman Filter (UKF) to track the orientation of a robot in three dimensions given observations from an inertial measurement unit (IMU) that consists of gyroscopes and accelerometers and corresponding data from a motion-capture system called Vicon.

Enhancing-Image-Super-Resolution-with-Improved-ESRGAN

Pytorch Implementation of various experiments and proposed improvements to the state-of-the-art image super resolution model ESRGAN.

Location-Based-Panoptic-Segmentation-with-SOLOv2

Modification to the state-of-the-art EfficientPS model by replacing its instance head (Mask-RCNN) with SOLOv2, making it a location based-panoptic segmentation model

Machine-Learning-for-EEG-Prosthetic-Arm-Control

Implementation and benchmarking of machine learning methods for identifying hand motions from EEG recordings.

Variational-Autoencoder-for-MNIST

Pytorch implementation of a Variational Autoencoder (VAE) that learns from the MNIST dataset and generates images of altered handwritten digits.

Visual-Question-Answering-using-Stacked-Attention-Networks

Pytorch implementation of VQA using Stacked Attention Networks: Multimodal architecture for image and question input, using CNN and LSTM, with stacked attention layer for improved accuracy (54.82%). Includes visualization of attention layers. Contributions welcome. Utilizes Visual VQA v2.0 dataset.

YOLOv3-Object-Detection-from-Scratch

Pytorch implementation of the You Only Look Once (YOLO) algorithm for object detection

williamcfrancis/Variational-Autoencoder-for-MNIST

Pytorch implementation of a Variational Autoencoder (VAE) that learns from the MNIST dataset and generates images of altered handwritten digits.

williamcfrancis/CNN-Image-Colorization-Pytorch

PyTorch implementation of a convolutional deep neural network to colorize grayscale images. Includes sample dataset and code for training, inference, and color temperature control.

williamcfrancis/YOLOv3-Object-Detection-from-Scratch

Pytorch implementation of the You Only Look Once (YOLO) algorithm for object detection

williamcfrancis/Blind-Motion-Deblurring-for-Legible-License-Plates

A novel approach to blind motion deblurring by converting a non-blind method (Weiner Deconvolution) to a blind method using Deep Learning

williamcfrancis/EKF-and-UKF-for-3D-Robot-Orientation-Tracking

Python implementation of an Unscented Kalman Filter (UKF) to track the orientation of a robot in three dimensions given observations from an inertial measurement unit (IMU) that consists of gyroscopes and accelerometers and corresponding data from a motion-capture system called Vicon.

williamcfrancis/Visual-Question-Answering-using-Stacked-Attention-Networks

Pytorch implementation of VQA using Stacked Attention Networks: Multimodal architecture for image and question input, using CNN and LSTM, with stacked attention layer for improved accuracy (54.82%). Includes visualization of attention layers. Contributions welcome. Utilizes Visual VQA v2.0 dataset.

williamcfrancis/Machine-Learning-for-EEG-Prosthetic-Arm-Control

Implementation and benchmarking of machine learning methods for identifying hand motions from EEG recordings.

williamcfrancis/Canny-Edge-Detector

A multi-stage computer vision algorithm to detect edges in images. Developed by John Canny in 1986, widely used in image processing, computer vision, and other fields. This repo provides an implementation in Python

williamcfrancis/Location-Based-Panoptic-Segmentation-with-SOLOv2

Modification to the state-of-the-art EfficientPS model by replacing its instance head (Mask-RCNN) with SOLOv2, making it a location based-panoptic segmentation model

williamcfrancis/Particle-Filter-Based-SLAM-for-Humanoid-Robot

Simultaneous Localization and Mapping (SLAM) in an indoor environment using information from an IMU and a LiDAR sensor collected from a humanoid robot called THOR.

williamcfrancis/RL-Q-Learning-on-the-Cart-Pole-Challenge

Python implementation of the Q Learning algorithm with the DDQN trick on OpenAI's version of the cart-pole problem

williamcfrancis/SOLO-and-FPN-for-Instance-Segmentation

This is my Pytorch implementation of Segmenting Objects by Locations (SOLO) for instance segmentation

williamcfrancis/Enhancing-Image-Super-Resolution-with-Improved-ESRGAN

Pytorch Implementation of various experiments and proposed improvements to the state-of-the-art image super resolution model ESRGAN.

williamcfrancis/ai-note-taker

An AI-assisted note taking application that does mic calibration, voice to text and AI proofreading

williamcfrancis/ai2ai-conversation-loop

Endless conversations between GPT and Google Gemini with possible human interaction

williamcfrancis/Bias_Bountry_Hunt

williamcfrancis/Email-Spam-Classifier-using-SVM

Linear classifier using Support Vector Machines (SVM) which can determine whether an email is Spam or not with an accuracy of 98.7%. Used regularization to prevent over-fitting of data. Pre-processed the E-mails using Porter Stemmer algorithm. Used a spam vocabulary to create a Feature Vector for each E-mail. Prints the top 15 predictors of spam

williamcfrancis/image-colorization

williamcfrancis/Lane-Segmentation-and-Steering-Angle-Estimation

williamcfrancis/Laplacian-Blending

Python implementation of Laplacian pyramid algorithm for blending images using reduce/expand, Gaussian/Laplacian pyramids, and combine/collapse functions for realistic outputs

williamcfrancis/Neural-Net-From-Scratch-for-Digit-Recognition

Design of a Neural Network from scratch for recognizing digits written in numpy without using pytorch, keras, or tensorflow libraries

williamcfrancis/RAG_Pilot

williamcfrancis/RL-Policy-Iteration-for-robot-agent

Implementation of the policy iteration algorithm to find the best trajectory for a robot to go from the start to the goal cell in a 2D grid

williamcfrancis/RNN-Tolstoy-language-model

A Pytorch implementation of a Recurrent Neural Network trained on Leo Tolstoy's War and Peace to imitate the language style used in the book

williamcfrancis/Tracking-Robot-Position-Using-Bayesian-Filtering

Implementation of Bayes Filter to track the position of a robot operating in a 2D grid world

williamcfrancis/vision-transformer-pytorch

A simplified implementation of a vision transformer in PyTorch

williamcfrancis/vlm-comparison-gemini-cog

A comparitive study between the two of the best performing open source Vision Language Models - Google Gemini Vision and CogVLM

williamcfrancis/Wearable-Sleep-Monitoring-IoT-Device

An Arduino-based sleep tracker worn on the wrist which monitors the user's heart rate, and hand movements (using accelerometer and gyroscope readings) and estimates sleep quality.

williamcfrancis/williamcfrancis

My github bio

williamcfrancis/williamcfrancis.github.io

This is the generated source code for my personal blog.