Skip to content

GitLab

Switch branch/tag
  1. 22 Oct, 2021 1 commit
    • Vasilis Vryniotis's avatar
      Additional SOTA ingredients on Classification Recipe (#4493) · b280c318
      Vasilis Vryniotis authored 
      * Update EMA every X iters.

* Adding AdamW optimizer.

* Adjusting EMA decay scheme.

* Support custom weight decay for Normalization layers.

* Fix identation bug.

* Change EMA adjustment.

* Quality of life changes to faciliate testing

* ufmt format

* Fixing imports.

* Adding FixRes improvement.

* Support EMA in store_model_weights.

* Adding interpolation values.

* Change train_crop_size.

* Add interpolation option.

* Removing hardcoded interpolation and sizes from the scripts.

* Fixing linter.

* Incorporating feedback from code review.
      b280c318
  3. 21 Oct, 2021 2 commits
  5. 20 Oct, 2021 3 commits
  7. 19 Oct, 2021 1 commit
  9. 18 Oct, 2021 1 commit
  11. 13 Oct, 2021 1 commit
  13. 08 Oct, 2021 1 commit
  15. 05 Oct, 2021 1 commit
  17. 04 Oct, 2021 2 commits
    • Nicolas Hug's avatar
      Fix all outstanding flake8 issues (#4535) · b81d189d
      Nicolas Hug authored
      b81d189d
    • Philip Meier's avatar
      Add ufmt (usort + black) as code formatter (#4384) · 5f0edb97
      Philip Meier authored 
      

* add ufmt as code formatter

* cleanup

* quote ufmt requirement

* split imports into more groups

* regenerate circleci config

* fix CI

* clarify local testing utils section

* use ufmt pre-commit hook

* split relative imports into local category

* Revert "split relative imports into local category"

This reverts commit f2e224cde2008c56c9347c1f69746d39065cdd51.

* pin black and usort dependencies

* fix local test utils detection

* fix ufmt rev

* add reference utils to local category

* fix usort config

* remove custom categories sorting

* Run pre-commit without fixing flake8

* got a double import in merge
Co-authored-by: default avatarNicolas Hug <nicolashug@fb.com>
      5f0edb97
  19. 01 Oct, 2021 1 commit
  21. 29 Sep, 2021 3 commits
    • Kai Zhang's avatar
      Add RegNet Architecture in TorchVision (#4403) · 194a0846
      Kai Zhang authored 
      * initial code

* add SqueezeExcitation

* initial code

* add SqueezeExcitation

* add SqueezeExcitation

* regnet blocks, stems and model definition

* nit

* add fc layer

* use Callable instead of Enum for block, stem and activation

* add regnet_x and regnet_y model build functions, add docs

* remove unused depth

* use BN/activation constructor and ConvBNActivation

* add expected test pkl files

* allow custom activation in SqueezeExcitation

* use ReLU as the default activation

* initial code

* add SqueezeExcitation

* initial code

* add SqueezeExcitation

* add SqueezeExcitation

* regnet blocks, stems and model definition

* nit

* add fc layer

* use Callable instead of Enum for block, stem and activation

* add regnet_x and regnet_y model build functions, add docs

* remove unused depth

* use BN/activation constructor and ConvBNActivation

* reuse SqueezeExcitation from efficientnet

* refactor RegNetParams into BlockParams

* use nn.init, replace np with torch

* update README

* construct model with stem, block, classifier instances

* Revert "construct model with stem, block, classifier instances"

This reverts commit 850f5f3ed01a2a9b36fcbf8405afd6e41d2e58ef.

* remove unused blocks

* support scaled model

* fuse into ConvBNActivation

* make reset_parameters private

* fix type errors

* fix for unit test

* add pretrained weights for 6 variant models, update docs
      194a0846
    • Nicolas Hug's avatar
      Prevent tests from leaking their respective RNG (#4497) · 13bd09dd
      Nicolas Hug authored 
      

* Add autouse fixture to save and reset RNG in tests

* Add other RNG generators

* delete freeze_rng_state

* Hopefully fix GaussianBlur test

* Alternative fix, probably better

* revert changes to test_models
Co-authored-by: default avatarFrancisco Massa <fvsmassa@gmail.com>
      13bd09dd
    • Aditya Oke's avatar
      Add JIT tests (#4472) · b5d81f02
      Aditya Oke authored 
      
Co-authored-by: default avatarFrancisco Massa <fvsmassa@gmail.com>
      b5d81f02
  23. 27 Sep, 2021 1 commit
    • Loi Ly's avatar
      Added gray image support to `adjust_saturation` function (#4480) · f483e71b
      Loi Ly authored 
      * update channels parameter to every calling to check_functional_vs_PIL_vs_scripted

* update adjust_saturation

* update docstrings for functional transformations

* parametrize channels

* update docstring of ColorJitter class

* move channels to class's parameter

* remove testing channels for geometric transforms

* revert redundant changes

* revert redundant changes

* update grayscale test cases for randaugment, autoaugment, trivialaugment

* update docstrings of randaugment, autoaugment, trivialaugment

* update docstring of ColorJitter

* fix adjust_hue's docstring

* change test equal tolerance

* refactor grayscale tests

* make get_grayscale_test_image private
      f483e71b
  25. 24 Sep, 2021 3 commits
  27. 21 Sep, 2021 3 commits
  29. 16 Sep, 2021 1 commit
  31. 15 Sep, 2021 1 commit
    • Vasilis Vryniotis's avatar
      Adding Mixup and Cutmix (#4379) · c8e3b2a5
      Vasilis Vryniotis authored 
      * Add RandomMixupCutmix.

* Add test with real data.

* Use dataloader and collate in the test.

* Making RandomMixupCutmix JIT scriptable.

* Move out label_smoothing and try roll instead of flip

* Adding mixup/cutmix in references script.

* Handle one-hot encoded target in accuracy.

* Add support of devices on tests.

* Separate Mixup from Cutmix.

* Add check for floats.

* Adding device on expect value.

* Remove hardcoded weights.

* One-hot only when necessary.

* Fix linter.

* Moving mixup and cutmix to references.

* Final code clean up.
      c8e3b2a5
  33. 14 Sep, 2021 1 commit
    • Muhammed Abdullah's avatar
      Added LFW Dataset (#4255) · d85aa6d3
      Muhammed Abdullah authored 
      

* Added LFW Dataset

* Added dataset to list in __init__.py

* Updated lfw.py
* Created a common superclass for people and pairs type datatsets
* corrected the .download() method

* Added docstrings and updated datasets.rst

* Wrote tests for LFWPeople and LFWPairs

* Resolved mypy error: Need type annotation for "data"

* Updated inject_fake_data method for LFWPeople

* Updated tests for LFW

* Updated LFW tests and minor changes in lfw.py

* Updated LFW
* Added functionality for 10-fold validation view
* Optimized the code so to replace repeated lines by method in super
  class
* Updated LFWPeople to get classes from all lfw-names.txt rather than
  just the classes fron trainset

* Updated lfw.py and tests
* Updated inject_fake_data method to create 10fold fake data
* Minor changes in docstring and extra_repr

* resolved py lint errors

* Added checksums for annotation files

* Minor changes in test

* Updated docstrings, defaults and minor changes in test

* Removed 'os.path.exists' check
Co-authored-by: default avatarABD-01 <myac931@gmai.com>
Co-authored-by: default avatarPhilip Meier <github.pmeier@posteo.de>
Co-authored-by: default avatarFrancisco Massa <fvsmassa@gmail.com>
      d85aa6d3
  35. 13 Sep, 2021 1 commit
  37. 08 Sep, 2021 1 commit
  39. 07 Sep, 2021 1 commit
  41. 06 Sep, 2021 3 commits
  43. 02 Sep, 2021 1 commit
  45. 27 Aug, 2021 1 commit
  47. 26 Aug, 2021 2 commits
    • Vasilis Vryniotis's avatar
      Make get_image_size and get_image_num_channels public. (#4321) · 96f6e0a1
      Vasilis Vryniotis authored
      96f6e0a1
    • Vasilis Vryniotis's avatar
      Add EfficientNet Architecture in TorchVision (#4293) · 37a9ee5b
      Vasilis Vryniotis authored 
      * Adding code skeleton

* Adding MBConvConfig.

* Extend SqueezeExcitation to support custom min_value and activation.

* Implement MBConv.

* Replace stochastic_depth with operator.

* Adding the rest of the EfficientNet implementation

* Update torchvision/models/efficientnet.py

* Replacing 1st activation of SE with SiLU.

* Adding efficientnet_b3.

* Replace mobilenetv3 assets with custom.

* Switch to standard sigmoid and reconfiguring BN.

* Reconfiguration of efficientnet.

* Add repr

* Add weights.

* Update weights.

* Adding B5-B7 weights.

* Update docs and hubconf.

* Fix doc link.

* Fix typo on comment.
      37a9ee5b
  49. 23 Aug, 2021 1 commit
  51. 20 Aug, 2021 1 commit
  53. 19 Aug, 2021 1 commit