Pinned Repositories
ColourModel
Just a tool which uses OpenCV to create bounding boxes around objects of requested colours.
ComptonCamera
Geant4 compton camera simulations
ImageComposer
Package to simplify creating simple synthetic image datasets. You specify the background and foreground objects, the package does the rest.
knowledge-repo
Trying out Air BnBs Knowledge repository
mbd
embd = embedded like koaning/bulk but with built in functionality provided by Quaternion for similarity model finetuning
QDrant-NLP
QDrant-NLP
sam-detect
Just an idea, SAM + image classifier for instance segmentation.
sqlite-streamlit-app
Streamlit app for learning SQL
streamlit-projects
A set of streamlit projects of increasing complexity, for Analytics and ML
VisionChain
Framework to support stitching together multiple models to create effective Computer Vision systems, as accurate or fast as you need them to be.
GeorgePearse's Repositories
GeorgePearse/QDrant-NLP
QDrant-NLP
GeorgePearse/ImageComposer
Package to simplify creating simple synthetic image datasets. You specify the background and foreground objects, the package does the rest.
GeorgePearse/VisionChain
Framework to support stitching together multiple models to create effective Computer Vision systems, as accurate or fast as you need them to be.
GeorgePearse/ColourModel
Just a tool which uses OpenCV to create bounding boxes around objects of requested colours.
GeorgePearse/mbd
embd = embedded like koaning/bulk but with built in functionality provided by Quaternion for similarity model finetuning
GeorgePearse/sam-detect
Just an idea, SAM + image classifier for instance segmentation.
GeorgePearse/unofficial-detectron2-docs
Everything the detectron2 docs should include.
GeorgePearse/vision-feedback
Just a placeholder for a hobby project to provide visual feedback to a computer vision model
GeorgePearse/aim
Aim 💫 — easy-to-use and performant open-source ML experiment tracker.
GeorgePearse/awesome-open-mlops-data-catalogues
The Fuzzy Labs guide to the universe of open source MLOps
GeorgePearse/bulk-demo
Demo of https://github.com/koaning/bulk on some interesting medical dataset. Ideally in radiology.
GeorgePearse/ActiveSupervision
Just gonna be a toy / demo built for online active-learning with Supervision.
GeorgePearse/CocoFrame
Everyone prefers working with DataFrames
GeorgePearse/diffusers-resize-fix
🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch
GeorgePearse/fiftyone
The open-source tool for building high-quality datasets and computer vision models
GeorgePearse/fiftyone-plugins
A curated list of FiftyOne Plugins that you can add to your local FiftyOne install or your FiftyOne Teams deployment
GeorgePearse/GeorgePearse
Just for the home page readme
GeorgePearse/GroundingDINO
Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection
GeorgePearse/GroupedNMS-
Often you want to run NMS over some pairs of classes, but not others which you expect to overlap.
GeorgePearse/introspector
Just an idea, hooks implemented for different deep learning frameworks to store the filenames / IDs of the top X losses (or relative losses for that point in training)
GeorgePearse/mmdetection
OpenMMLab Detection Toolbox and Benchmark
GeorgePearse/norfair
Lightweight Python library for adding real-time multi-object tracking to any detector.
GeorgePearse/onnx
Open standard for machine learning interoperability
GeorgePearse/python-introductory-data-science
Intro to python data science.
GeorgePearse/QwkGen
Tooling to quickly get a stable-diffusion like model generating images, but also configure filters to ignore images you don't want with QDrant.
GeorgePearse/simple-active-learning
Just for Instance Segmentation Models
GeorgePearse/social-research
Fran's quest into data science for social research
GeorgePearse/streamlit-html-parser
Creating a mini UI to assist with html parsing.
GeorgePearse/structured-vision
A repo to help you add useful metadata to your instance segmentation predictions.
GeorgePearse/unofficial-detectron-docs
Original Detectron2 docs show you what's available, but not how to achieve common results / get through common workflows etc.