-
CNES
- Toulouse
- https://www.romain-thoreau.com/
Stars
FireBench is a Python library designed for the systematic benchmarking and inter-comparison of fire models.
Python tools for pre/post processing of the atmosphere-fire coupled model Méso-NH/Blaze.
User friendly Rasterio plugin to read raster datasets.
FlipnSlide: A Python Package for for Preserving Spatial Context when Preprocessing Large Scientific Images
A ready-to-use curated list of Spectral Indices for Remote Sensing applications.
Code repository for "Parameter Efficient Self-supervised Geospatial Domain Adaptation", CVPR 2024
Reference implementation for Deep Unsupervised Learning using Nonequilibrium Thermodynamics
Estimates the size of a PyTorch model in memory
Myria3D: Aerial Lidar HD Semantic Segmentation with Deep Learning
EuroSAT: Land Use and Land Cover Classification with Sentinel-2
Transformer with Untied Positional Encoding (TUPE). Code of paper "Rethinking Positional Encoding in Language Pre-training". Improve existing models like BERT.
Official code repository for NeurIPS 2022 paper "SatMAE: Pretraining Transformers for Temporal and Multi-Spectral Satellite Imagery"
MultiMAE: Multi-modal Multi-task Masked Autoencoders, ECCV 2022
Make your models invariant to changes in scale.
PyTorch implementation of MAE https//arxiv.org/abs/2111.06377
This repository contains examples of fine-tuning Harmonized Landsat and Sentinel-2 (HLS) Prithvi foundation model.
Implementation and analysis of GAN and their improvements using Tensorflow 2
Pytorch implementation of Wasserstein GANs with Gradient Penalty
Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.
Experiments for understanding disentanglement in VAE latent representations
code for "Isolating Sources of Disentanglement in Variational Autoencoders".