microsoft
/
torchgeo
зеркало из https://github.com/microsoft/torchgeo.git
1
0
Форкнуть 0
Код Задачи Пакеты Проекты Релизы Вики Активность
581 коммит 12 Ветки 13 Теги 787 MiB
Граф коммитов

20 Коммитов

Автор SHA1 Сообщение Дата
Caleb Robinson a82d3f47b4
Cleaning up ChesapeakeCVPR (#131) 
* 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>
 2021-09-15 11:52:51 -05:00
Caleb Robinson ccb7f1912d Refactoring how the trainer modules are called from train.py and how the configuration files are structured 2021-09-09 15:12:22 -07:00
Adam J. Stewart 5ff5a02027 Add trainer for NAIP + Chesapeake 2021-09-03 14:18:50 -05:00
Caleb Robinson c27f0f4e5c Removing useless TODOs 2021-09-02 15:17:03 -05:00
Caleb Robinson 13be61440f File permissions? 2021-08-31 13:25:05 -05:00
Adam J. Stewart da7e120350 Add license header to all files 2021-08-31 13:25:05 -05:00
Caleb Robinson a54359dcde
Refactor trainer logic (#54) 
* Moving task specific configuration logic from train.py into respective classes

* Small fixes

* Adding basic FCN model for benchmarking

* Adding simple FCN model

* Removing OrderedDict from model definitions

* Adding torchgeo.models to docs

* Adding model tests

* Making all the formatters happy

* Adding optimizer options to landcoverai

* Fixing conda environment I think

* How do you feel about a Makefile, Adam?

* Formatting

* Adding some documentation to the readme

* Sanity check command in README

* Fixes in the landcoverai datamodule to make multi-GPU training possible

* Closing figures that we send to Tensorboard

* Fix sphinx missing target warning

* Fix pytest coverage

* Fix flake8

* Update torchgeo/models/__init__.py

Co-authored-by: Adam J. Stewart <ajstewart426@gmail.com>

Co-authored-by: Adam J. Stewart <ajstewart426@gmail.com>
 2021-07-30 20:58:49 -05:00
Caleb Robinson aeaffb1dbc Initial commit for the landcoverai trainer 2021-07-26 15:32:26 -05:00
Adam J. Stewart 13b360dc83 Add tests for sen12ms trainer 2021-07-25 18:56:00 -04:00
Adam J. Stewart 0bc26a667d Add tests for train.py 2021-07-25 18:02:30 -04:00
Caleb Robinson 5d2dc8f96e Updated test_train to match new way of passing arguments. Fixed mypy problem. 2021-07-23 22:14:09 -05:00
Caleb Robinson 34769f9f6c Changing all configuration definitions to be in YAML files 2021-07-23 22:14:09 -05:00
Caleb Robinson ee7b3c779b Adding accuracy reporting to SEN12MS task 
Finishing up OmegaConf based configuration
 2021-07-23 22:14:09 -05:00
Caleb Robinson ac14409d85 Revamp of train.py to use OmegaConf based configs 2021-07-23 22:14:09 -05:00
Adam J. Stewart e399a51ce3 Mypy fixes 2021-07-21 12:23:35 -05:00
Adam J. Stewart 90ba939135 Add tests for SEN12MS task 2021-07-21 12:23:35 -05:00
Caleb Robinson 38e85378e8 Fixed mypy and made loss argument actually work 2021-07-21 12:23:35 -05:00
Caleb Robinson 1a67b02a4c Formatting updates 2021-07-21 12:23:35 -05:00
Caleb Robinson c799eb9d04 Adding SEN12MS training task 2021-07-21 12:23:35 -05:00
Caleb Robinson e460d5af23
Pytorch lightning based training framework (#42) 
* Initial commit of lightning based model training framework

* Made save directories work correctly

* Add pytorch-lightning dependency and some comments

* More documentation and cosmetic tweaks

* Typo fix

Co-authored-by: Adam J. Stewart <ajstewart426@gmail.com>

* Fix some style issues

* Fix pydocstyle

* Add missing sklearn dependency

* Try to get conda environment working

* Add documentation

* Ignore missing target reference

* Make train.py executable

* Ignore logs and output dirs

* Raise exceptions instead of returning

* Move all argparse stuff to set_up_parser

* Add tests for train.py

* Fix Python 3.6 compatibility

* Fix support for older versions of pytorch-lightning

Co-authored-by: Adam J. Stewart <ajstewart426@gmail.com>
 2021-07-17 16:57:18 -07:00