GitLab

* Fix bug to Random Erasing

1. Avoid forever loop for getting parameters of erase.
2. replace' img_b' by 'img_c', because it indicates the channel.
3. replace v = torch.rand([img_c, h, w]) by v = torch.empty([img_c, h, w], dtype=torch.float32).normal_(). Normally distributed achieves better performance.

* add test

* Update test_transforms.py

* Update transforms.py

* Update test_transforms.py

* Update transforms.py

* Update functional.py

* initial commit

* add more checks, fix lint, fix doc

* updates on normalize

* test fixes

* Update test_transforms.py

* test improved

* Update test_transforms.py

* behaviour changes RandomErasing

* test fixes

* linter fix

* add erase function

* add Random Erasing

* Update transforms.py

* Update transforms.py

* add test for random erasing

* Update test_transforms.py

* fix flake8

* Update test_transforms.py

* Update functional.py

* Update test_transforms.py

* fix bug for per-pixel erasing

* Update transforms.py

* specific for coordinate (x, y)

* add raise TypeError for img

* Update transforms.py

* Update transforms.rst

* fix:error message of to_tensor

The error "pic should be PIL Image or ndarray. Got '<numpy.ndarray>'" is confusing.

* fix:a clearer function name

_is_numpy_image is clearer than _is_numpy_image_dim

* fix:add a test case

Add a test case in test/test_transforms.py to test the error message

* fix:pass ci check

* fix:wrong random matrix

* Fix normalize for different dtype than float32

* Fix lint

* Make tests work on fbcode

* Lint

* Fix rebase error

* Properly use get_file_path_2

* Fix wrong use of get_file_path_2 again

* Missing import

* final changes

* final

* linter

* test changes

* linter

* lint

* indent

* lint

* minor changes

* parameter added

* ci

* ci fixes

* indent

* indent

* indent

* arg fixed

* Update test_transforms.py

* Update transforms.py

* Add basic model testing.

Also fixes flaky test

* Fix flake8

* Add Affinetransformation

Add Affinetransformation to superseed LinearTransformation

* Add test

* Add zero mean_vector in LinearTransformation and improved docs

* update

* minor fix

* minor fix2

* fixed flake8

* fix flake8

* fixed transpose syntax

* fixed shape of mean_vector in test

* fixed test

* print est cov and mean

* fixed flake8

* debug

* reduce num_samples

* debug

* fixed num_features

* fixed rtol for cov

* fix __repr__

* Update transforms.py

* Update test_transforms.py

* Update transforms.py

* fix flake8

* Update transforms.py

* Update transforms.py

* Update transforms.py

* Update transforms.py

* Changed dim of mean_vector to 1D, doc and removed .numpy () from format_string

* Restore test_linear_transformation()

* Update test_transforms.py

* randomresizedmods

* lint checks

* test to randomrescrop added

* updates

* tests updated

* tests updated

* upd

* updates

* Update torchvision/transforms/transforms.py
Co-Authored-By: surgan12 <33121121+surgan12@users.noreply.github.com>

* tests changed

* trvis

* travis

* fixes syntax

* ...

* flake fixes

* flake_fixes

* flake_fixes2

The tests were previously taking 2 minutes, not they take 4 seconds

* modes added

* tests_added

* Update test_transforms.py

* Update test_transforms.py

* Update test_transforms.py

* added separate checks for dimensionality in to_pil_image and added tests

* updated to_pil_image to use both 2D ndarrays and tensors, as well as refactored the tests

Improve `test_pad_with_non_constant_padding_modes` to avoid data multiplication in `transforms.ToPILImage()` on float data:
```python
img = torch.zeros(3, 27, 27)  # Float32
img[:, :, 0] = 1   # we add 1 and not 255
img = transforms.ToPILImage()(img)  # This converts 1 to 255 due to [pic = pic.mul(255).byte()](https://github.com/pytorch/vision/blob/master/torchvision/transforms/functional.py#L107)
```
and thus test's correct values are [..., 200, 1, 0]

* Add case in test_to_tensor for PIL Images mode '1'

* Add support in ToTensor for PIL Images mode '1'

* Fix pep8 issues

* Made transorms.RandomCrop tolerate images smaller than the given size.

* Extended the tescase for transforms.RandomCrop

* Made the testcase test for owidth=width+1

* Fixed the one pixel pading and the testcase

* Fixed minor lintint errors. flake8 passes.

* Added reflect, symmetric and edge padding

* Updated padding docs, added tests

* Add random affine transformation

* Rewrite __repr__

* Refactor affine transform and update tests

* Add RandomApply, RandomChoice, RandomOrder transformations

* Rename argument `proba` to `p`

* Set probability as configuration parameter in RandomHorizontalFlip and RandomHorizontalFlip (#414)

* Fix documentation

* add __repr__ for all transform objects

* add tests for __repr__

* add to_grayscale + randomGrayscale

add rotate and RandomRotation to transforms

* refactor transforms and add transforms/functional.py

* add __all__ to transforms.py

* add assert for byte tensor to_pil_image

* add mode param to ToPILImage

* add some more tests

* fix formatiing on error messages

* added tests for to_pil_image with mode param

* flake8 fixes

expands coverage on test_to_tensor to 1 and 4 image channels

* added Whiten transform and relative section in README

* added Whiten transform and its section in README

* fixed lint

* fixed lint again

* added linear transformation and whitening test unitary covariance

* fixed lint and test

* commit before rebasing

* before rebase

* added assertion to check matrix size

* fix readme

* added space around operator

* replace assert with raise ValueError, fix spaces and readme

* increase num_samples, reduce alpha and fix seed for hflip and vflip tests

* flake8 fixes

* Add adjust_hue and adjust_saturation

* Add adjust_brightness, adjust_contrast

Also
* Change adjust_saturation to use pillow implementation
* Documentation made clear

* Add adjust_gamma

* Add ColorJitter

* Address review comments

* Fix documentation for ColorJitter

* Address review comments 2

* Fallback to adjust_hue in case of BW images

* Add tests

* fix dtype