TorchGeo: datasets, samplers, transforms, and pre-trained models for geospatial data
Перейти к файлу
Adam J. Stewart f507b08252
Silence tensorboard deprecation warnings
2021-07-27 17:06:12 +00:00
.github/workflows Set PKG_CONFIG_PATH 2021-07-21 09:37:28 -05:00
conf Fixing paths 2021-07-26 15:32:26 -05:00
docs Adding example notebook for SEN12MS 2021-07-21 12:23:35 -05:00
tests Updating landcoverai tests to use 512x512 sized images 2021-07-26 15:32:26 -05:00
torchgeo Fix CDL link 2021-07-26 21:16:05 -04:00
.flake8 Pytorch lightning based training framework (#42) 2021-07-17 16:57:18 -07:00
.gitattributes gitattributes files don't automatically recurse 2021-06-22 00:00:41 +00:00
.gitignore Pytorch lightning based training framework (#42) 2021-07-17 16:57:18 -07:00
CODE_OF_CONDUCT.md Add Microsoft open-source template 2021-05-21 11:35:58 -05:00
LICENSE Add Microsoft open-source template 2021-05-21 11:35:58 -05:00
README.md Adding dataset list to the readme 2021-07-08 00:16:06 +00:00
SECURITY.md Add Microsoft open-source template 2021-05-21 11:35:58 -05:00
SUPPORT.md Add Microsoft open-source template 2021-05-21 11:35:58 -05:00
environment.yml torchvision 0.10 no longer has a conflict 2021-07-23 17:35:06 -05:00
pyproject.toml Silence tensorboard deprecation warnings 2021-07-27 17:06:12 +00:00
requirements.txt Adding torchmetrics as a dependency 2021-07-23 22:14:09 -05:00
setup.cfg Adding torchmetrics as a dependency 2021-07-23 22:14:09 -05:00
setup.py Also document setup.py 2021-07-19 15:10:29 +00:00
spack.yaml Adding torchmetrics as a dependency 2021-07-23 22:14:09 -05:00
train.py Initial commit for the landcoverai trainer 2021-07-26 15:32:26 -05:00

README.md

TorchGeo

Datasets, transforms, and models for geospatial data.

docs style tests

Project setup

Conda

conda env create --file environment.yml
conda activate torchgeo

Datasets

Dataset Imagery Type Label Type Dataset Type External Link
Smallholder Cashew Plantations in Benin Sentinel-2 (71 scene time series) Semantic segmentation GeoDataset https://registry.mlhub.earth/10.34911/rdnt.hfv20i/
Cars Overhead With Context (COWC) 0.15m/px overhead imagery Object detection VisionDataset https://gdo152.llnl.gov/cowc/
CV4A Kenya Crop Type Sentinel-2 (13 scene time series) Semantic segmentation GeoDataset https://registry.mlhub.earth/10.34911/rdnt.dw605x/
Tropical Cyclone Wind Estimation GOES single band imagery Regression VisionDataset http://registry.mlhub.earth/10.34911/rdnt.xs53up/
Landcover.ai RGB aerial imagery at 0.5m/px and 0.25m/px Semantic segmentation GeoDataset https://landcover.ai/
NWPU VHR-10 Google Earth RGB and Vaihingen CIR Object detection VisionDataset https://github.com/chaozhong2010/VHR-10_dataset_coco
SEN12MS Sentinel-1 and Sentinel-2 Semantic segmentation GeoDataset https://github.com/schmitt-muc/SEN12MS
So2Sat Sentinel-1 and Sentinel-2 Classification VisionDataset https://github.com/zhu-xlab/So2Sat-LCZ42

Contributing

This project welcomes contributions and suggestions. Most contributions require you to agree to a Contributor License Agreement (CLA) declaring that you have the right to, and actually do, grant us the rights to use your contribution. For details, visit https://cla.opensource.microsoft.com.

When you submit a pull request, a CLA bot will automatically determine whether you need to provide a CLA and decorate the PR appropriately (e.g., status check, comment). Simply follow the instructions provided by the bot. You will only need to do this once across all repos using our CLA.

This project has adopted the Microsoft Open Source Code of Conduct. For more information see the Code of Conduct FAQ or contact opencode@microsoft.com with any additional questions or comments.

Trademarks

This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow Microsoft's Trademark & Brand Guidelines. Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship. Any use of third-party trademarks or logos are subject to those third-party's policies.