Computer Vision - BKJackson/BKJackson_Wiki GitHub Wiki
Real Time Object Detection
RF-DETR: SOTA Real-Time Object Detection Model
inference - Inference turns any computer or edge device into a command center for your computer vision projects.
Diffusion Models
HuggingFace Diffusers Home- 🤗 Diffusers is the go-to library for state-of-the-art pretrained diffusion models for generating images, audio, and even 3D structures of molecules.
HuggingFace Diffusers pypi - 🤗 Diffusers is the go-to library for state-of-the-art pretrained diffusion models for generating images, audio, and even 3D structures of molecules.
HF Diffusers Tutorials - Overview page
ControlNet - Let us control diffusion models!
Collecting image data
Fondant - Production-ready data processing made easy and shareable
Tutorials and Notebooks
Fine-tuning for Image Classification with 🤗 Transformers
Fine-Tune ViT for Image Classification with 🤗 Transformers - Nate Raw, 2022
Hugging Face SWIN Transformer
SWIN Transformer - Kaggle Notebook
Analyzing SWIN Transformer - Youtube
Simple and effective coin segmentation using Python and OpenCV
Measuring size of objects in an image with OpenCV Adrian Rosebrock
Image Datasets
img2dataset - Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.
Image Cleaning and Filtering
Compressing and enhancing hand-written notes A program to clean up scans of handwritten notes while simultaneously reducing file size.
Deep Learning and Computer Vision
A curated list of deep learning resources for computer vision Jiwon Kim and others.
PyStretch: Image Processing and Analysis for Large Raster Datasets in a Parallelized Environment
Note: Part of GeoDa Center at Arizona State U.
PyStretch Package PyPi Package download page
PyStretch abstract Jay Laura
Journals, Blogs
Fine-Tuning ViT for Image Classification with Hugging Face
Pyimagesearch Blog dedicated to building image search engines. Semi-commercial.
Deep Learning for Computer Vision with Caffe and cuDNN
Lucas Beyer Home - Co-author of the Google ViT paper
Courses
RIT Introduction to Digital Image Processing Taught by Harvey Rhody.