Skip to content

GitLab

Switch branch/tag
  1. 27 Apr, 2022 8 commits
  3. 26 Apr, 2022 3 commits
  5. 25 Apr, 2022 5 commits
  7. 22 Apr, 2022 2 commits
    • Vasilis Vryniotis's avatar
      Restructuring metrics meta-data (#5859) · 6f016dd9
      Vasilis Vryniotis authored 
      * Restructuring metrics meta-data for detection, segmentation and optical flow.

* Renaming acc to pixel_acc for segmentation

* Restructure video meta-data.

* Restructure classification and quantization meta-data.

* Fix tests.

* Fix documentation
      6f016dd9
    • YosuaMichael's avatar
      Adding revamp docs for vision_transformers and regnet (#5856) · ca265374
      YosuaMichael authored 
      * Add docs for regnet, still need to update the comment docs on models

* Fix a little typo on .rst file

* Update regnet docstring

* Add vision_transformer docs, and fix typo on regnet docs

* Update docstring to make sure it does not exceed 120 chars per line

* Improve formatting

* Change the new line location for vision_transformer docstring
      ca265374
  9. 19 Apr, 2022 3 commits
    • Nicolas Hug's avatar
      Add docs for `SomeWeight.DEFAULT` fields (#5831) · e8cb0bac
      Nicolas Hug authored 
      * First PR for model doc revamp

* Deactivating fail on warning, temporarily

* Remove commnet

* Minor changes

* Typos

* Added TODO in Makefile

* Keep old models.rst file intact, move new docs into new models_new.rst file

* Added docs LOL
      e8cb0bac
    • Nicolas Hug's avatar
      Add docs for SqueezeNet (#5832) · f1cd8b23
      Nicolas Hug authored
      f1cd8b23
    • Nicolas Hug's avatar
      Model doc revamp - first PR (#5821) · 111fe85d
      Nicolas Hug authored 
      * First PR for model doc revamp

* Deactivating fail on warning, temporarily

* Remove commnet

* Minor changes

* Typos

* Added TODO in Makefile

* Keep old models.rst file intact, move new docs into new models_new.rst file
      111fe85d
  11. 05 Apr, 2022 1 commit
    • YosuaMichael's avatar
      Adding the huge vision transformer from SWAG (#5721) · 63576c9f
      YosuaMichael authored 
      

* Add vit_b_16_swag

* Better handling idiom for image_size, edit test_extended_model to handle case where number of param differ from default due to different image size input

* Update the accuracy to the experiment result on torchvision model

* Fix typo missing underscore

* raise exception instead of torch._assert, add back publication year (accidentally deleted)

* Add license information on meta and readme

* Improve wording and fix typo for pretrained model license in readme

* Add vit_l_16 weight

* Update README.rst
Co-authored-by: default avatarVasilis Vryniotis <datumbox@users.noreply.github.com>

* Update the accuracy meta on vit_l_16_swag model to result from our experiment

* Add vit_h_14_swag model

* Add accuracy from experiments

* Add to vit_h_16 model to hubconf.py

* Add docs and expected pkl file for test

* Remove legacy compatibility for ViT_H_14 model
Co-authored-by: default avatarVasilis Vryniotis <datumbox@users.noreply.github.com>

* Test vit_h_14 with smaller image_size to speedup the test
Co-authored-by: default avatarVasilis Vryniotis <datumbox@users.noreply.github.com>
      63576c9f
  13. 24 Mar, 2022 1 commit
  15. 23 Mar, 2022 1 commit
  17. 22 Mar, 2022 1 commit
    • Vasilis Vryniotis's avatar
      Port Multi-weight support from prototype to main (#5618) · 11bd2eaa
      Vasilis Vryniotis authored 
      

* Moving basefiles outside of prototype and porting Alexnet, ConvNext, Densenet and EfficientNet.

* Porting googlenet

* Porting inception

* Porting mnasnet

* Porting mobilenetv2

* Porting mobilenetv3

* Porting regnet

* Porting resnet

* Porting shufflenetv2

* Porting squeezenet

* Porting vgg

* Porting vit

* Fix docstrings

* Fixing imports

* Adding missing import

* Fix mobilenet imports

* Fix tests

* Fix prototype tests

* Exclude get_weight from models on test

* Fix init files

* Porting googlenet

* Porting inception

* porting mobilenetv2

* porting mobilenetv3

* porting resnet

* porting shufflenetv2

* Fix test and linter

* Fixing docs.

* Porting Detection models (#5617)

* fix inits

* fix docs

* Port faster_rcnn

* Port fcos

* Port keypoint_rcnn

* Port mask_rcnn

* Port retinanet

* Port ssd

* Port ssdlite

* Fix linter

* Fixing tests

* Fixing tests

* Fixing vgg test

* Porting Optical Flow, Segmentation, Video models (#5619)

* Porting raft

* Porting video resnet

* Porting deeplabv3

* Porting fcn and lraspp

* Fixing the tests and linter

* Porting docs, examples, tutorials and galleries (#5620)

* Fix examples, tutorials and gallery

* Update gallery/plot_optical_flow.py
Co-authored-by: default avatarNicolas Hug <contact@nicolas-hug.com>

* Fix import

* Revert hardcoded normalization

* fix uncommitted changes

* Fix bug

* Fix more bugs

* Making resize optional for segmentation

* Fixing preset

* Fix mypy

* Fixing documentation strings

* Fix flake8

* minor refactoring
Co-authored-by: default avatarNicolas Hug <contact@nicolas-hug.com>

* Resolve conflict

* Porting model tests (#5622)

* Porting tests

* Remove unnecessary variable

* Fix linter

* Move prototype to extended tests

* Fix download models job

* Update CI on Multiweight branch to use the new weight download approach (#5628)

* port Pad to prototype transforms (#5621)

* port Pad to prototype transforms

* use literal

* Bump up LibTorchvision version number for Podspec to release Cocoapods (#5624)
Co-authored-by: default avatarAnton Thomma <anton@pri.co.nz>
Co-authored-by: default avatarVasilis Vryniotis <datumbox@users.noreply.github.com>

* pre-download model weights in CI docs build (#5625)

* pre-download model weights in CI docs build

* move changes into template

* change docs image

* Regenerated config.yml
Co-authored-by: default avatarPhilip Meier <github.pmeier@posteo.de>
Co-authored-by: default avatarAnton Thomma <11010310+thommaa@users.noreply.github.com>
Co-authored-by: default avatarAnton Thomma <anton@pri.co.nz>

* Porting reference scripts and updating presets (#5629)

* Making _preset.py classes

* Remove support of targets on presets.

* Rewriting the video preset

* Adding tests to check that the bundled transforms are JIT scriptable

* Rename all presets from *Eval to *Inference

* Minor refactoring

* Remove --prototype and --pretrained from reference scripts

* remove  pretained_backbone refs

* Corrections and simplifications

* Fixing bug

* Fixing linter

* Fix flake8

* restore documentation example

* minor fixes

* fix optical flow missing param

* Fixing commands

* Adding weights_backbone support in detection and segmentation

* Updating the commands for InceptionV3

* Setting `weights_backbone` to its fully BC value (#5653)

* Replace default `weights_backbone=None` with its BC values.

* Fixing tests

* Fix linter

* Update docs.

* Update preprocessing on reference scripts.

* Change qat/ptq to their full values.

* Refactoring preprocessing

* Fix video preset

* No initialization on VGG if pretrained

* Fix warning messages for backbone utils.

* Adding star to all preset constructors.

* Fix mypy.
Co-authored-by: default avatarNicolas Hug <contact@nicolas-hug.com>
Co-authored-by: default avatarPhilip Meier <github.pmeier@posteo.de>
Co-authored-by: default avatarAnton Thomma <11010310+thommaa@users.noreply.github.com>
Co-authored-by: default avatarAnton Thomma <anton@pri.co.nz>
      11bd2eaa
  19. 10 Mar, 2022 1 commit
  21. 04 Mar, 2022 1 commit
  23. 02 Mar, 2022 1 commit
    • Vasilis Vryniotis's avatar
      Adding EfficientNetV2 architecture (#5450) · e6d82f7d
      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.
      e6d82f7d
  25. 28 Feb, 2022 1 commit
    • Vasilis Vryniotis's avatar
      Replace get_image_size/num_channels with get_dimensions (#5487) · 095437aa
      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.
      095437aa
  27. 27 Feb, 2022 1 commit
  29. 25 Feb, 2022 1 commit
  31. 24 Feb, 2022 1 commit
  33. 18 Feb, 2022 1 commit
    • Vasilis Vryniotis's avatar
      Adding AugMix implementation (#5411) · 48a61df2
      Vasilis Vryniotis authored 
      

* Adding basic augmix implementation.

* Finish the implementation.

* Add tests and documentation.

* Fix tests.

* Simplify code.

* Speed optimizations.

* Per image weights instead of per batch.

* Fix tests.

* Update torchvision/transforms/autoaugment.py
Co-authored-by: default avatarvfdev <vfdev.5@gmail.com>

* Changing the default severity value to get by default the same strength as RandAugment.
Co-authored-by: default avatarvfdev <vfdev.5@gmail.com>
      48a61df2
  35. 08 Feb, 2022 3 commits
  37. 03 Feb, 2022 1 commit
  39. 02 Feb, 2022 1 commit
  41. 01 Feb, 2022 2 commits