chilland

open_clip

An open source implementation of CLIP.

Transformers-Tutorials

This repository contains demos I made with the Transformers library by HuggingFace.

burn

Burn is a new comprehensive dynamic Deep Learning Framework built using Rust with extreme flexibility, compute efficiency and portability as its primary goals.

awesome-mlops

:sunglasses: A curated list of awesome MLOps tools

sam-hq

Segment Anything in High Quality [NeurIPS 2023]

ov

🎑Feature-rich terminal-based text viewer. It is a so-called terminal pager.

curated-transformers

🤖 A PyTorch library of curated Transformer models and their composable components

yunikorn-core

Apache YuniKorn Core

titiler

Build your own Raster dynamic map tile services

finetune-anything

Fine-tune SAM (Segment Anything Model) for computer vision tasks such as semantic segmentation, matting, detection ... in specific scenarios

geoarrow

Specification for storing geospatial data in Apache Arrow

lens

This is the official repository for the LENS (Large Language Models Enhanced to See) system.

segment-anything-with-clip

Segment Anything combined with CLIP

mvits_for_class_agnostic_od

[ECCV'22] Official repository of paper titled "Class-agnostic Object Detection with Multi-modal Transformer".

devit

Awesome-Open-Vocabulary-Object-Detection

A curated list of papers, datasets and resources pertaining to open vocabulary object detection.

Geo-SAM

A QGIS plugin tool using Segment Anything Model (SAM) to accelerate segmenting or delineating landforms in geospatial raster images.

satclip

PyTorch implementation of SatCLIP

Battle-of-the-Backbones

satlas

Major-TOM

Expandable Datasets for Earth Observation

satmae_pp

Official repository for "Rethinking Transformers Pre-training for Multi-Spectral Satellite Imagery" (CVPR 2024)

GFM

AstroCLIP

Multimodal contrastive pretraining for astronomical data

earthPT

A time series foundation model for Earth Observation

bsk_rl

RL environments and tools for spacecraft autonomy research, built on Basilisk. Developed by the AVS Lab.

HVSA

Official PyTorch implementation for Hypersphere-Based Remote Sensing Cross-Modal Text–Image Retrieval via Curriculum Learning.

earth-text

Adding language to Clay

mind_back

repository for a paper, Mind the Backbone: Minimizing Backbone Distortion for Robust Object Detection

maxar-geospatial-platform

A repo for SDKs for the Maxar Geospatial Platform