- 17 Mar, 2022 2 commits
-
-
Philip Meier authored
Co-authored-by:Vasilis Vryniotis <datumbox@users.noreply.github.com>
-
Federico Pozzi authored
Co-authored-by:Federico Pozzi <federico.pozzi@argo.vision>
-
- 16 Mar, 2022 1 commit
-
-
Philip Meier authored
* port Pad to prototype transforms * use literal
-
- 15 Mar, 2022 3 commits
-
-
Vasilis Vryniotis authored
-
Joao Gomes authored
* replace most asserts with exceptions * fix formating issues * fix linting and remove more asserts * fix regresion * fix regresion * fix bug * apply ufmt * apply ufmt * fix tests * fix format * fix None check * fix detection models tests * non scriptable any * add more checks for None values * fix retinanet test * fix retinanet test * Update references/classification/transforms.py Co-authored-by:
Nicolas Hug <contact@nicolas-hug.com> * Update references/classification/transforms.py Co-authored-by:
-
vfdev authored
* Added functional affine_bounding_box op with tests * Updated comments and added another test case * Update _geometry.py * Fixed device mismatch issue Added a cude/cpu test Reduced the number of test samples
-
- 14 Mar, 2022 4 commits
-
-
Federico Pozzi authored
* refactor: port RandomHorizontalFlip to prototype API (#5523) * refactor: merge HorizontalFlip and RandomHorizontalFlip Add unit tests for RandomHorizontalFlip * test: RandomHorizontalFlip with p=0 * refactor: remove type annotations from tests * refactor: improve tests * Update test/test_prototype_transforms.py Co-authored-by:
Philip Meier <github.pmeier@posteo.de>
-
Georg Grab authored
Co-authored-by: -
Vasilis Vryniotis authored
* Moving `sequence_to_str` to `torchvision._utils` * Fix linter * Rename test_prototype_utils test to test_internal_utils
-
Philip Meier authored
* port RandomZoomOut from detection references to prototype transforms * copy by default * move padding parsing to stable API * merge zoom out kernels into transform * lint * fix filling if no padding was done * resolve todo
-
- 11 Mar, 2022 2 commits
-
-
vfdev authored
Co-authored-by: -
Vasilis Vryniotis authored
-
- 10 Mar, 2022 1 commit
-
-
Abhijit Deo authored
* basic stanford cars structure added. * added class in the init. * how to decode the images * fix typo in init * works partially * formatting * formatting * formatting * formatting * formatting * minor changes * minor changes * issue resolved * both datapipes are in sync * checksum dict keys changed * formatting * "ufmt formatting" * "ufmt formatting" * formatting * minor change * minor change * test added * lint (end of line issue) * lint (end of line issue) * minor changes * mock dataset formatting * minor changes * hopefully final * formatting * prototype test * prototype test * prototype test * prototype test * prototype test * prototype test * prototype test * prototype test * Update builtin_dataset_mocks.py * Update stanford_cars.py * Update torchvision/prototype/datasets/_builtin/stanford_cars.py Co-authored-by:
-
- 09 Mar, 2022 3 commits
-
-
Philip Meier authored
* support grayscale / RGB alpha conversions * use _max_valu from stable * remove extra copy for PIL conversion * simplify test image generation for color spaces with alpha channel * use common _max_value in tests * replace dynamically created dicts with if/else * make color space conversion more explicit * make even more explicit * simplify alpha image generation * fix if / elif * add error for unknown conversions * rename RGBA to RGB_ALPHA * cleanup * GRAYSCALE to GRAY
-
Philip Meier authored
-
vfdev authored
* Removed _max_value method and added a dictionary Related to https://github.com/pytorch/vision/issues/5502 * Addressed failing tests and restored _max_value method * Added xfailing test to switch quicker * Switch to if/else impl
-
- 07 Mar, 2022 5 commits
-
-
Vasilis Vryniotis authored
* Refactor preset transforms * Making presets public.
-
Vasilis Vryniotis authored
* Adding improved MobileNetV2 weights * Fix eval sizes. * Update accuracy with batch-size 1 run
-
kaijieshi authored
Co-authored-by: -
Philip Meier authored
* port FiveCrop and TenCrop to prototype API * fix ten crop for pil * Update torchvision/prototype/transforms/_geometry.py Co-authored-by:
-
Vasilis Vryniotis authored
-
- 05 Mar, 2022 1 commit
-
-
Philip Meier authored
* fix vanilla tensor image detection * fix naming Co-authored-by:
-
- 04 Mar, 2022 3 commits
-
-
Nicolas Hug authored
* Fix accimage tests * Adding workaround for accimage * Refactoring * restore channels Co-authored-by: -
Vasilis Vryniotis authored
* Remove from models and references. * Adding most tests and docs. * Adding transforms tests. * Remove unnecesary ipython notebook. * Simplify tests. * Addressing comments.
-
Xu Zhao authored
Co-authored-by:
-
- 03 Mar, 2022 3 commits
-
-
Philip Meier authored
* simplify Feature implementation * fix mypy
-
Drishti Bhasin authored
* add eurosat * revert formatting * port test and make style changes * add eurosat to __init__ * fix pathlib error * create dataset zipfile and revert pre commit changes * remove unecessary variable in resources * revert auto formatter changes and modify ufmt version * revert change to contributing guide Co-authored-by:
Dbhasin1 <drishti_b@me.iitr.c.in> Co-authored-by:
Nicolas Hug <nicolashug@fb.com>
-
Drishti Bhasin authored
* add country211 * remove unused import * map val to valid and use path comparator * remove unused import * resolve keyerror * map split names in dataset mock Co-authored-by:
-
- 02 Mar, 2022 3 commits
-
-
Philip Meier authored
* improve StrEnum * use StrEnum for model weights * fix test * migrate StrEnum to main area
-
Vasilis Vryniotis authored
* Extend the EfficientNet class to support v1 and v2. * Refactor config/builder methods and add prototype builders * Refactoring weight info. * Update dropouts based on TF config ref * Update BN eps on TF base_config * Use Conv2dNormActivation. * Adding pre-trained weights for EfficientNetV2-s * Add Medium and Large weights * Update stats with single batch run. * Add accuracies in the docs.
-
Prabhat Roy authored
-
- 01 Mar, 2022 6 commits
-
-
Prabhat Roy authored
-
Prabhat Roy authored
-
Prabhat Roy authored
* Move VideoReader out of __init__ * Fix linter error
-
Philip Meier authored
* fix grayscale to RGB for batches * make unsupported types in auto augment a parameter * make auto augment kwargs explicit * add missing error message * add support for specifying probabilites on RandomChoice * remove TODO for deprecating p on random transforms * streamline sample type checking * address comments * split image_size into height and width in auto augment Co-authored-by: -
vfdev authored
-
Philip Meier authored
* expand prototype functional scriptability tests * remove obsolete skips
-
- 28 Feb, 2022 2 commits
-
-
Philip Meier authored
* add prototype AugMix transform * cleanup * refactor auto augment subclasses to only trnasform a single image * address review comments
-
Vasilis Vryniotis authored
* Replace get_image_size/num_channels with get_image_dims * Reduce verbosity * Fix JIT-scriptability * Refactoring * More refactoring * Replace all _FP/_FT direct calls. * Remove usages of get_image_size and get_image_num_channels from code-base. * Fix JIT issues * Adding missing assertion.
-
- 27 Feb, 2022 1 commit
-
-
Hu Ye authored
* Create dropblock.py * add dropblock2d * fix pylint * refactor dropblock * add dropblock * Rename dropblock.py to drop_block.py * fix pylint * add dropblock * add dropblock3d * add drop_block3d * add dropblock * Update drop_block.py * Update torchvision/ops/drop_block.py Co-authored-by:
-
