GitLab

Give a short example of how to build a transform pipeline for a
segmentation task.

Target `float` -> `long`

* ColorJitter Enhancement

* reduce redundancy

* improve functional

* check input in init

* fix ci fail

* Use scandir in _find_classes (#557)

* fix lint

* reduce tqdm version to 4.19 for py2.7 to avoid spurious error

* Update setup.py

* Missed =

* Update wrong version string

- Fix broken update calculation
- Make progress bar use the neat `unit_scale` feature
  of tqdm

* Addresses issue #145 as per @fmessa's suggestion.

* Removed blank line for styling.

* make vision depend on pillow-simd if already installed

* actually make pillow-simd optional

* Fix PIL link

* Make normalize more efficient

* fix a bug described in issue #488

* improve doc described in issue #488

* add arguments in RandomCrop as proposed by vfdev-5 in PR #489

This reverts commit 11da4f17.

* Add classes metadata to MNIST and FashionMNIST

* Add `targets` property to MNIST and FashionMNIST

* Add class metadata to CIFAR10/CIFAR100

* Add `targets` property to CIFAR10/CIFAR100

* Add targets attribute to DatasetFolder

This reverts commit 972b80c9.

* cifar10.meta['label_names']

* cifar100.meta['fine_label_names']

* cifar100.meta['coarse_label_names']

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]

* Added Progress Bar to the dataset downloading utility

* Updated progressbar to update by blcoks

* Added progressbar2 to the requirements

* fixed style issues

* Shifted from progressbar to tqdm

nit: replace 4 by expansion

Remove test with variables

* fix for PyTorch v0.4 (remove .data and add _ for the initializations in nn.init)

* fix m.**.**() style to nn.init.**(**) style

* remove .idea

* fix lines and indents

* fix lines and indents

* change to use `kaming_normal_`

* add `.data` for safety

* add nonlinearity='relu' for sure

* fix indents

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

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

* Fix pep8 issues