GitLab

This reverts commit 2f579d58.

Without clipping, any values larger than 255 will be replaced with
int(v mod 256) by byte(), which results in high freq noise in image.

is already downloaded* for CIFAR and STL10

* Running sanity checks on cropped parts of scipy.misc.ascent

Doing this to ensure that the image is of the size 100 x 212 which is being followed throughout the sanity checks

* Update sanity_checks.ipynb

Doing this to ensure that the image is of the size 100 x 212 which is being followed throughout the sanity checks

In python2, calling `make_grid` won't display the last images if the number of images doesn't divide `nrow`.
Int division...

This should fix that!

* fix for to_tensor when input is np.ndarray of shape [H,W,C]. Issue #48 pytorch/vision

* update cifar datasets to transpose images from CHW -> HWC

* fix flake8 issue on test_transforms.py

Fixed a wrong folder name.

Install pytorch with conda. Most of .travis.yml copied from the example
provided by the conda folks at:

https://conda.io/docs/travis.html

    git ls-files | grep '\.py$' | xargs -n1 -P`nproc` autopep8 -i

Previous assertion only allows numbers for `fill`, which rules out the possibility to pad multi-channel colors. For example, now fill=(255,255,255) or fill="white" can be used to achieve white padding for rgb inputs.

YCbCr breaks the code without warning. Changed the code to make `ToTensor()` cope with all PIL image types.