The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

The fastai deep learning library

A game theoretic approach to explain the output of any machine learning model.

PyTorch code and models for the DINOv2 self-supervised learning method.

Python code for "Probabilistic Machine learning" book by Kevin Murphy

Time series Timeseries Deep Learning Machine Learning Python Pytorch fastai | State-of-the-art Deep Learning library for Time Series and Sequences in Pytorch / fastai

Create delightful software with Jupyter Notebooks

A data visualization curriculum of interactive notebooks.

Paper reading notes on Deep Learning and Machine Learning

Earth observation tools for Meta AI Segment Anything

Implementation of popular SOTA self-supervised learning algorithms as Fastai Callbacks.

This repository contains examples of fine-tuning Harmonized Landsat and Sentinel-2 (HLS) Prithvi foundation model.

Documentation for Ross Wightman's timm image model library

This is a lightweight web-interface for creating and sharing vector annotations over satellite/aerial imagery scenes.

FasterAI: Prune and Distill your models with FastAI and PyTorch

HugsVision is a easy to use huggingface wrapper for state-of-the-art computer vision

Image segmentations of trees outside forest

Code repository for the paper Tree species classification from airborne hyperspectral and LiDAR data using 3D convolutional neural networks

This repository contains the code for the paper "An unexpectedly large count of trees in the western Sahara and Sahel".

Source code for the paper "Growing urban bicycle networks", exploring algorithmically the limitations of urban bicycle network growth

Research repo for code that may or may not end up in fastai3

Satellite Vu submission for the AWS Disaster Response hackathon

A pytorch implementation of the (Tensorflow) MTLCC network implementation

Repo for testing foundation models

Collection of interactive notebooks for the OPERA Products

Sensor Independent Cloud and Shadow Masking with Ambiguous Labels and Multimodal Inputs

Scalable arbitrary analysis on COGs

Contains source code for the winning solution of the xView3 challenge https://iuu.xview.us/.