* Improve sampler performance for pixel-aligned files
* Skip merge if only a single file
* Undo changes to hyperparams
* Fix shape, read all bands
* Remove manual single-file reading
* Always keep workers alive
* Various changes in a desperate attempt to improve performance
* Increase epoch size
* Add missing import, fix model name
* Fix tests
* Persistent workers not used unless entire dataset is consumed
* add RESISC45 trainer
* update working locally
* Adding ability to choose the random split sizes via config
* If you don't have a val or test split, then return the train split so the Trainer doesn't break by default. If you actually want to train without val/test though, then you should set the appropriate Trainer args.
* RESISC experiments
* Reverting accidental changes
* mypy fix
* add dataset_split unit tests
* Document dataset_split
Co-authored-by: Caleb Robinson <calebrob6@gmail.com>
* Added RCF model
* Rename to RCF
* Update tests/models/test_rcf.py
Co-authored-by: Adam J. Stewart <ajstewart426@gmail.com>
Co-authored-by: Adam J. Stewart <ajstewart426@gmail.com>
* Added support for training on different splits to Chesapeake trainer
* Fixed test script
* Specifying test splits in the test script
* Removing useless prepare_data function from SEN12MS trainer
* Updating LandCoverAI trainer to reflect Chesapeake trainer changes
* Remove verbose in Chesapeake trainer
* Remove adamw in conf files
* Black
* Added experiment run script
* Add augmentation to the landcoverai trainer
* Add augmentation to the landcoverai trainer
* Adding So2Sat trainer
* Fixing style
* Adding So2Sat trainer
* Adding So2Sat trainer
* Adding to so2sat
* Fixing tests
* Add kornia dependency
* Test coverage for GridGeoSampler length
* Added tests for so2sat
* Cleaning up
* Isort
* Adding capability to reindex So2Sat
* Renaming gpu to device
* Setting up so2sat trainer for paper experiments
* So2Sat training sweep
* Idontsort
* Call trainer.tune() step if auto_lr_find is set
* So2Sat trainer work
* Adding SSL method (#162)
* Added support for training on different splits to Chesapeake trainer
* Fixed test script
* Specifying test splits in the test script
* Removing useless prepare_data function from SEN12MS trainer
* Updating LandCoverAI trainer to reflect Chesapeake trainer changes
* Remove verbose in Chesapeake trainer
* Remove adamw in conf files
* Black
* Added experiment run script
* Add augmentation to the landcoverai trainer
* Add augmentation to the landcoverai trainer
* Adding So2Sat trainer
* Fixing style
* Adding So2Sat trainer
* starting SSL trainers
* starting SSL trainers
* Adding BYOL as SSL method, it is fully functional and works for any encoder, next steps includes adding other SSL aproaches like Seasonal Contrast and SSL evaluation at large
* Adding BYOL as SSL method, it is fully functional and works for any encoder, next steps includes adding other SSL aproaches like Seasonal Contrast and SSL evaluation at large
* Making pydocstyle happy
Co-authored-by: Anthony O <anthony.ortiz@microsoft.com>
* Working on experiments
* Updates to So2Sat
* Experiments
* Experiments
* Review changes
* Review changes
* Grabbing the kornia mypy workaround
* updating BYOL to support resnet 50 and updating some docstring
* updating BYOL to support resnet 50 and updating some docstring
* addressing flake8 concerns
* trying to address mypy issues
* mypy
* mypy
* mypy
* adding byol documentation corrections
* Updating byol default and moving experiment scripts to experiments subdir
* Setting up experiment scripts
* Working
* Moving landcoverai seed experiment script
* Fixing formatting in the experiment scripts
* Update torchgeo/trainers/so2sat.py
Co-authored-by: Adam J. Stewart <ajstewart426@gmail.com>
* Update torchgeo/trainers/so2sat.py
Co-authored-by: Adam J. Stewart <ajstewart426@gmail.com>
* Update torchgeo/trainers/byol.py
Co-authored-by: Adam J. Stewart <ajstewart426@gmail.com>
* Update torchgeo/trainers/byol.py
Co-authored-by: Adam J. Stewart <ajstewart426@gmail.com>
* Update torchgeo/trainers/byol.py
Co-authored-by: Adam J. Stewart <ajstewart426@gmail.com>
* Update torchgeo/trainers/byol.py
Co-authored-by: Adam J. Stewart <ajstewart426@gmail.com>
* Update torchgeo/trainers/byol.py
Co-authored-by: Adam J. Stewart <ajstewart426@gmail.com>
* Update torchgeo/trainers/byol.py
Co-authored-by: Adam J. Stewart <ajstewart426@gmail.com>
* Update torchgeo/trainers/byol.py
Co-authored-by: Adam J. Stewart <ajstewart426@gmail.com>
* Update torchgeo/trainers/byol.py
Co-authored-by: Adam J. Stewart <ajstewart426@gmail.com>
* Black formatting
* Reorganizing and documenting BYOL code
* Formatting
* BYOL trainer is not Chesapeake specific
* Updating docstrings
* changing to input_channels uniformly
* Fixing BYOL
* Formatting fixes
* Update experiments/run_landcoverai_experiments.py
Co-authored-by: Adam J. Stewart <ajstewart426@gmail.com>
* Update experiments/run_landcoverai_experiments.py
Co-authored-by: Adam J. Stewart <ajstewart426@gmail.com>
* Update experiments/run_landcoverai_experiments.py
Co-authored-by: Adam J. Stewart <ajstewart426@gmail.com>
* Update torchgeo/trainers/byol.py
Co-authored-by: Adam J. Stewart <ajstewart426@gmail.com>
* Docstring changes
* Docstring fixes
* Black formatting
* Forward slashes have been judiciously eliminated and I threw in some comments for free
* flake8
* flake8
Co-authored-by: Anthony O <anthony.ortiz@microsoft.com>
Co-authored-by: Adam J. Stewart <ajstewart426@gmail.com>
* draft indices transform
* import sort
* added AugmentationSequential wrapper for dicts
* updated indices
* fix dim concat bugs
* format
* add kornia dependency
* add augmentationsequenal unit tests
* add augmentationsequential support for boxes and mask dtypes
* add indices tests
* Draft indices tutorial notebook
* move notebook to tutorials folder
* mypy fixes
* fix bug when only image key used in AugmentationSequential
* Created using Colaboratory
* added tutorial to docs
* format
* added kornia master branch dependency'
* refactor notebook to use % cell magic and python to download files
* revert kornia version
* install kornia master branch for mypy checks
* update mypy github action install order
* fix divide by zero error in indices
* Created using Colaboratory
* fix nbsphinx errors
* add TODO to remove kornia in tests action
* format setup.cfg
* minor fixes to indices
* remove unecessary variable
* update mask to cast to original dtype
* removed unused ignore comment
* added gray/rgb/multispectral unit tests
* added tests with boxes
* Created using Colaboratory
* Created using Colaboratory
* fix mypy issues
* updated notebooks in docs
* Updates to tutorials
* Created using Colaboratory
* Created using Colaboratory
Co-authored-by: Adam J. Stewart <ajstewart426@gmail.com>
* updated docs
* added VisionClassificationDataset
* refactor PatternNet and RESISC45 to inherit VisionClassificationDataset
* added unit tests and sample data
* refactor PatternNet and RESISC45 to new download/verify checks and fix code coverage
* remove override of __str__
* set default_loader as loader default
* removed loader arg from datasets
* update tests
* format
* remove duplicate code
* updated docstrings
* Added EuroSat dataset
* Cleaning up
* Removing unzipped data
* Added to docs
* EuroSat --> EuroSAT to match paper
* Changing class listing to use bullets
* Update torchgeo/datasets/eurosat.py
Co-authored-by: Adam J. Stewart <ajstewart426@gmail.com>
* Addressing review
Co-authored-by: Adam J. Stewart <ajstewart426@gmail.com>
* add FarSeg model
* Revised.
* Ran black and working on mypy fixes
* Fixed other mypy issues
* try to fix mypy issues
* Fixing rest of mypy issues
* try to fix mypy issues
* Fixed issue with in_channels and backbone_pretrained
* Removing change to in_channels, formatting doc
* revised.
- improving the docstring of FarSeg
- removing the scale_aware_proj option in FSRelation class
- removing the in_channels option in FarSeg class
- improving the test_farseg.py by parametrization
* changestar
* removing the function `backbone_forward`
* update ChangeStar
* update changestar
* fixed a typo in docstring
* fixing mypy, pytest, sphinx issues
* revised.
major:
- removing unused import
- split the testing case
- removing the redundant docstring
* fixing mypy and sphinx issues
major:
- adding more description for docstring of ChangeStar
* fixing mypy and sphinx issues
* fixing mypy and sphinx issues
* fixing mypy issues
* Update torchgeo/models/changestar.py
Co-authored-by: isaac <22203655+isaaccorley@users.noreply.github.com>
* Update torchgeo/models/changestar.py
Co-authored-by: isaac <22203655+isaaccorley@users.noreply.github.com>
* revised.
* fixing flake8 issues
* fixing mypy issues.
- replacing Tensor with Any, because a list of tensor as value stored in dictionary.
* update ChangeStar
* fixing mypy issues
* fixing mypy issues
* fixing mypy issues
* Adding more docstring about how to use ChangeStar for multi-class change detection
* Adding missing test cases
* revised.
- replacing Dict[str, Any] with Dict[str, Tensor]
Co-authored-by: Caleb Robinson <calebrob6@gmail.com>
Co-authored-by: isaac <22203655+isaaccorley@users.noreply.github.com>
* add FarSeg model
* Revised.
* Ran black and working on mypy fixes
* Fixed other mypy issues
* try to fix mypy issues
* Fixing rest of mypy issues
* try to fix mypy issues
* Fixed issue with in_channels and backbone_pretrained
* Removing change to in_channels, formatting doc
* revised.
- improving the docstring of FarSeg
- removing the scale_aware_proj option in FSRelation class
- removing the in_channels option in FarSeg class
- improving the test_farseg.py by parametrization
* removing the function `backbone_forward`
* Various improvements
Co-authored-by: Caleb Robinson <calebrob6@gmail.com>
Co-authored-by: Adam J. Stewart <ajstewart426@gmail.com>
* Proposal: better handling of partial timestamps
* Parse format string directly
* Add unit tests
* Windows is broken
* Windows is still broken
* Fix mypy
* Simplify logic
* Fix bug for month 12, add details to docstring
* Implemented way to test if ChesapeakeCVPR has been downloaded
* Cleaned up the way transforms are used in ChesapeakeCVPRDataModule and changed the test dataloader to use a GridGeoSampler
* Adding other transforms and cleaning up style
* Changing masks to mask throughout
* Organize the way metrics are logged
* Formatting
* Adding rasterio data loadering best practices and fixing trainer a bit
* Script for evaluating trained models over all states
* Forgot to update the MD5 after changing the dataset nodata masks
* Update test_chesapeakecvpr_models.py
Co-authored-by: Adam J. Stewart <ajstewart426@gmail.com>
* Changes recommended by Adam
* Idon'tsort
Co-authored-by: Adam J. Stewart <ajstewart426@gmail.com>
* Add Spacenet 1
* Add test data
* Style fixes
* Convert Spacenet1 to VisionDataset
* Add option for selecting imagery
* Consolidate spacenet
* Create single spacenet.py for all spacenet datasets
* Create single spacenet directory for all spacenet test data
* Create single test_spacenet.py for testing all spacenet datasets
* Add copyright
* Reorder Spacenet in docs
* Test both rgb & 8band
* Rename Spacenet -> SpaceNet
* add dataset to docs
* add sample test data
* add dataset unit tests
* add etci2021 dataset
* updated tests
* updated dataset to download only desired split file
* removed flood mask from file list for test set and other formatting
* Update torchgeo/datasets/etci2021.py
Co-authored-by: Adam J. Stewart <ajstewart426@gmail.com>
* fixed doc formatting
Co-authored-by: Adam J. Stewart <ajstewart426@gmail.com>
isaac
Adam J. Stewart
Ashwin Nair
Caleb Robinson
Zhuo Zheng