Pinned Repositories
attention-mechanism-simulation
This notebook implements a basic attention mechanism to demonstrate its functionality using a simple RGB matrix as an input. It includes steps for creating random matrices for RGB channels, computing attention weights, and applying the attention mechanism in a simulated environment.
Control-Bluetooth-Speaker-by-Gesture-Recognition
Controlling a Bluetooth speaker by gesture recognition enables users to adjust volume, skip tracks, and perform other functions through hand movements, eliminating the need for physical interaction.
Dataset-for-Image-Colorization
This repository contains Python scripts for preparing and augmenting the COCO 2017 dataset for image colorization tasks.
diffusion-model-from-scratch
HEIC-to-JPEG
This repository contains a Python script, heic_to_jpeg.py, designed to convert HEIC files to JPEG format. The script utilizes the Pillow and pillow-heif packages for efficient image processing.
ICP-Point-Cloud
Iterative Closet Point (ICP) is an algorithm employed to minimize the difference of two point clouds
Kmeans-Clustering
K-means clustering is an algorithm that groups similar data points into a predetermined number of clusters by minimizing the sum of squared distances between data points and their cluster centroids.
text-guided-image-colorization
This repository provides an interactive image colorization tool that leverages Stable Diffusion (SDXL) and BLIP for user-controlled color generation. With a retrained model using the ControlNet approach, users can upload images and specify colors for different objects, enhancing the colorization process through a user-friendly Gradio interface.
Video-Shot-Detection
Video shot detection is a computer vision technique used to automatically identify the boundaries between shots in a video sequence.
ViT-Classification-CIFAR10
This repository contains an implementation of the Vision Transformer (ViT) from scratch using PyTorch. The model is applied to the CIFAR-10 dataset for image classification.
nick8592's Repositories
nick8592/text-guided-image-colorization
This repository provides an interactive image colorization tool that leverages Stable Diffusion (SDXL) and BLIP for user-controlled color generation. With a retrained model using the ControlNet approach, users can upload images and specify colors for different objects, enhancing the colorization process through a user-friendly Gradio interface.
nick8592/HEIC-to-JPEG
This repository contains a Python script, heic_to_jpeg.py, designed to convert HEIC files to JPEG format. The script utilizes the Pillow and pillow-heif packages for efficient image processing.
nick8592/ICP-Point-Cloud
Iterative Closet Point (ICP) is an algorithm employed to minimize the difference of two point clouds
nick8592/Video-Shot-Detection
Video shot detection is a computer vision technique used to automatically identify the boundaries between shots in a video sequence.
nick8592/ViT-Classification-CIFAR10
This repository contains an implementation of the Vision Transformer (ViT) from scratch using PyTorch. The model is applied to the CIFAR-10 dataset for image classification.
nick8592/Kmeans-Clustering
K-means clustering is an algorithm that groups similar data points into a predetermined number of clusters by minimizing the sum of squared distances between data points and their cluster centroids.
nick8592/attention-mechanism-simulation
This notebook implements a basic attention mechanism to demonstrate its functionality using a simple RGB matrix as an input. It includes steps for creating random matrices for RGB channels, computing attention weights, and applying the attention mechanism in a simulated environment.
nick8592/Control-Bluetooth-Speaker-by-Gesture-Recognition
Controlling a Bluetooth speaker by gesture recognition enables users to adjust volume, skip tracks, and perform other functions through hand movements, eliminating the need for physical interaction.
nick8592/Dataset-for-Image-Colorization
This repository contains Python scripts for preparing and augmenting the COCO 2017 dataset for image colorization tasks.
nick8592/diffusion-model-from-scratch
nick8592/sorting-algorithms
This repository provides implementations of several sorting algorithms, widely used in computer science for ordering data. These algorithms differ in terms of complexity, efficiency, and use cases.
nick8592/Ubuntu-20.04-CUDA-cuDNN-PyTorch
nick8592/AutoAvatar-Installation-Guide
Installation Guide for AutoAvatar
nick8592/Awesome-Image-Colorization
:books: A collection of Deep Learning based Image Colorization and Video Colorization papers.
nick8592/Docker-User-Guide
Useful docker information.
nick8592/Fore-Background
Separate Image into foreground image and background image
nick8592/GCP-Colorization
Official code for ICCV 2021 paper "Towards Vivid and Diverse Image Colorization with Generative Color Prior".
nick8592/GLLRE
Implement of paper "Image segmentation based on gray level and local relative entropy two dimensional histogram"
nick8592/Hand-Detection-masOS
nick8592/Install-Tensorflow-on-VScode
nick8592/Magic-Projection
This assignment involves creating three magical tricks using computer vision techniques.
nick8592/Markov-Decision-Processes
nick8592/Multi-Armed-Bandit
nick8592/GoogleAPI-Download-File
Download file on google drive via google provided API.
nick8592/Monte-Carlo-Algorithm
nick8592/opencv-framebuffer
This project captures live video from the default camera, stores the last 10 frames in a buffer, calculates and displays the FPS (Frames Per Second), and prints memory addresses of the frames. It uses OpenCV for video capture and processing, providing a simple example of real-time video processing and frame management.
nick8592/opencv-plane-arrange
This program combines three image planes of different sizes and colors into a 1920x1080 screen buffer and displays the result using OpenCV. It demonstrates basic image manipulation and composition in C++.
nick8592/pytorch-stable-diffusion
Stable Diffusion implemented from scratch in PyTorch
nick8592/Snaklish