Skip to content

GitLab

Switch branch/tag
  1. 25 Apr, 2019 5 commits
  3. 24 Apr, 2019 1 commit
  5. 18 Apr, 2019 1 commit
  7. 12 Apr, 2019 2 commits
  9. 05 Apr, 2019 1 commit
  11. 04 Apr, 2019 1 commit
    • Philip Meier's avatar
      Refactoring of the datasets (#749) · 6cabab3a
      Philip Meier authored 
      * introduced new super class for all vision datasets

* Removed root from repr if dataset has no root

* reverted some overly-ambitious autoformatting

* reverted some overly-ambitious autoformatting

* added split attribute to repr of STL10 dataset

* made Python2 friendly and more robust

* Fixed call of the superclass constructor

* moved transform and target_transform back to the base classes

* added check if transforms are present before printing to avoid setting them within the constructor

* added missing transforms and target_transforms to base classes

* fixed linter error
      6cabab3a
  13. 03 Apr, 2019 1 commit
    • James Hamm's avatar
      Replace endswith calls in a loop with a single endswith call (#832) · f566fac8
      James Hamm authored 
      str.endswith can take a single string, or a tuple of strings. This replaces a loop over each extension and a call to endswith with a single call to endswith passing in all the allowed extensions. This has the advantage that the loop over each extension is done in c rather than python, and the code is a little less verbose.
      f566fac8
  15. 26 Mar, 2019 1 commit
  17. 19 Mar, 2019 1 commit
    • Philip Meier's avatar
      ImageNet dataset (#764) · 69382912
      Philip Meier authored 
      * initial commit

* fixed Python2 issue

* fixed naming incorrectness and Python2 compability

* fixed preparation of train folder

* removed detection dataset

* added docstring and repr

* moved import of scipy to make the import of torchvision independent of it

* improved conversion from class string to index

* removed support for other years than 2012

* removed accidentally added file

* moved emptying of split folder to avoid accidental deletion

* removed deletion of the images

* removed error conversion for Python2

* Aligned class indices with the indices identified by ImageFolder class
      69382912
  19. 09 Mar, 2019 1 commit
  21. 07 Mar, 2019 2 commits
  23. 01 Mar, 2019 1 commit
  25. 28 Feb, 2019 1 commit
  27. 13 Feb, 2019 2 commits
  29. 12 Feb, 2019 2 commits
  31. 11 Feb, 2019 1 commit
  33. 25 Jan, 2019 1 commit
  35. 25 Dec, 2018 2 commits
  37. 21 Dec, 2018 1 commit
  39. 13 Dec, 2018 1 commit
  41. 06 Dec, 2018 1 commit
    • Benjamin Pinaya's avatar
      VOCSegmentation, VOCDetection, linting passing, examples. (#663) · e489abc6
      Benjamin Pinaya authored 
      

* VOC Dataset, linted, flak8 passing, samples on gist.

* Double backtick on values.

* Apply suggestions from code review

Add suggestions from @ellisbrown, using dict of dicts instead of array index.
Co-Authored-By: default avatarbpinaya <bpg_92@hotmail.com>

* Fixed errors with the new comments.

* Added documentation on RST

* Removed getBB, added parse_voc_xml, variable naming change.

* Removed unused variable, removed VOC_CLASSES, two new gists for test.
      e489abc6
  43. 04 Dec, 2018 2 commits
  45. 30 Oct, 2018 1 commit
  47. 26 Oct, 2018 1 commit
    • Leon Sixt's avatar
      Fix FashionMNIST loading MNIST (#640) · 36215690
      Leon Sixt authored 
      Before this would lead FashionMNIST to contain mnist data:

```
MNIST(root, download=True)
FashionMNIST(root, download=True)
```

As MNIST and FashionMNIST are the same classes, the processed
outputs actual ended up to be the same files. This commit now
stores them at different files and also stores the class name when
saving them. I also added md5 sums.
      36215690
  49. 25 Oct, 2018 1 commit
  51. 21 Sep, 2018 1 commit
  53. 17 Sep, 2018 2 commits
  55. 11 Sep, 2018 2 commits