Skip to content

GitLab

Switch branch/tag
  1. 11 Jun, 2020 2 commits
  3. 10 Jun, 2020 1 commit
  5. 04 Jun, 2020 2 commits
  7. 18 May, 2020 2 commits
    • Steven Basart's avatar
      Add pil_to_tensor to functionals (#2092) · e6d3f8c5
      Steven Basart authored 
      * Adds as_tensor to functional.py

Similar functionality to to_tensor without the default conversion to float and division by 255.
Also adds support for Image mode 'L'.

* Adds tests to AsTensor()

Adds tests to AsTensor and removes the conversion to float and division by 255.

* Adds AsTensor to transforms.py

Calls the as_tensor function in functionals and adds the function AsTensor as callable from transforms.

* Removes the pic.mode == 'L'

This was handled by the else condition previously so I'll remove it.

* Fix Lint issue

Adds two line breaks between functions to fix lint issue

* Replace from_numpy with as_tensor

Removes the extra if conditionals and replaces from_numpy with as_tensor.

* Renames as_tensor to pil_to_tensor

Renames the function as_tensor to pil_to_tensor and narrows the scope of the function.  At the same time also creates a flag that defaults to True for swapping to the channels first format.

* Renames AsTensor to PILToImage

Renames the function AsTensor to PILToImage and modifies the description.  Adds the swap_to_channelsfirst boolean variable to indicate if the user wishes to change the shape of the input.

* Add the __init__ function to PILToTensor 

Add the __init__ function to PILToTensor since it contains the swap_to_channelsfirst parameter now.

* fix lint issue

remove trailing white space

* Fix the tests

Reflects the name change to PILToTensor and the parameter to the function as well as the new narrowed scope that the function only accepts PIL images.

* fix tests

Instead of undoing the transpose just create a new tensor and test that one.

* Add the view back

Add img.view(pic.size[1], pic.size[0], len(pic.getbands())) back to outside the if condition.

* fix test

fix conversion from torch tensor to PIL back to torch tensor.

* fix lint issues

* fix lint

remove trailing white space

* Fixed the channel swapping tensor test

Torch tranpose operates differently than numpy transpose.  Changed operation to permute.

* Add mode='F'

Add mode information when converting to PIL Image from Float Tensor.

* Added inline comments to follow shape changes

* ToPILImage converts FloatTensors to uint8

* Remove testing not swapping

* Removes the swap_channelsfirst parameter

Makes the channel swapping the default behavior.

* Remove the swap_channelsfirst argument

Remove the swap_channelsfirst argument and makes the swapping the default functionality.
      e6d3f8c5
    • Francisco Massa's avatar
      Fix Python lint (#2226) · e2e511be
      Francisco Massa authored
      e2e511be
  9. 05 May, 2020 1 commit
  11. 04 May, 2020 1 commit
  13. 03 Apr, 2020 1 commit
  15. 02 Apr, 2020 1 commit
  17. 01 Apr, 2020 2 commits
  19. 31 Mar, 2020 1 commit
  21. 30 Mar, 2020 1 commit
  23. 24 Mar, 2020 1 commit
  25. 23 Mar, 2020 2 commits
  27. 27 Feb, 2020 1 commit
  29. 25 Feb, 2020 1 commit
    • Phoenix Meadowlark's avatar
      Improved error messages for transforms.functional.normalize(). (#1915) · 2f433e0a
      Phoenix Meadowlark authored 
      * Improved error messages for transforms.functional.normalize().

Split the original TypeError into 1. a TypeError if `tensor` is not a torch.Tensor and 2. a ValueError if `tensor` does not have the correct dimensionality.

Added more detail to the error for when `tensor` has the wrong dimension to make it easier to diagnose. This is useful when this function isn't called directly by the user (e.g. when the user uses transforms.Normalize and can't directly see this functions doc string).

Deleted hanging function `_is_tensor_image()`. It isn't used in this file and isn't used internally anywhere else in torchvision that I can see. (Some users will have used it despite the underscore prefix, but a quick google search for "F._is_tensor_image" suggests this is rare).

* Value checking to prevent division by zero runtime crashes.

Added a ValueError to check for and avoid division by zero in `div_`. Not preventing the call leads to runtime crashes, at least in some environments.

* Fixed div by zero check for non-scalar inputs.
      2f433e0a
  31. 10 Feb, 2020 1 commit
  33. 29 Jan, 2020 1 commit
  35. 27 Jan, 2020 1 commit
    • abdjava's avatar
      Fixed typo in comments (#1784) · 035ed162
      abdjava authored 
      I have fixed a typo that was persent in the Normalize class changed line 150 from     ``input[channel] = (input[channel] - mean[channel]) / std[channel]`` to     ``output[channel] = (input[channel] - mean[channel]) / std[channel]``
      035ed162
  37. 22 Jan, 2020 2 commits
  39. 19 Dec, 2019 1 commit
  41. 04 Dec, 2019 1 commit
  43. 05 Nov, 2019 1 commit
    • Ankit Jha's avatar
      [WIP] Add Scriptable Transform: Grayscale (#1505) · 8909ff43
      Ankit Jha authored 
      * Add Scriptable Transform: Grayscale

* add scriptable transforms: rgb_to_grayscale

* add scriptable transform: rgb_to_grayscale

* add scriptable transform: rgb_to_grayscale

* add scriptable transform: rgb_to_grayscale

* update code: rgb_to_grayscale

* add test: rgb_to_grayscale

* update parameters: rgb_to_grayscale

* add scriptable transform: rgb_to_grayscale

* update rgb_to_grayscale

* update rgb_to_grayscale
      8909ff43
  45. 29 Oct, 2019 1 commit
    • pedrofreire's avatar
      Make shear operation area preserving (#1529) · c226bb95
      pedrofreire authored 
      * Improve readability of affine transformation code

* Make shear transformation area preserving

The previous shear implementation did not preserve area, and we
implement a version that does.

The formula used was verified with the following sympy code:

from sympy import Matrix, cos, sin, tan, simplify
from sympy.abc import x, y, phi

Xs = Matrix(
        [[1, -tan(x)],
         [0, 1]]
        )

Ys = Matrix(
        [[1, 0],
         [-tan(y), 1]]
        )

R = Matrix(
        [[cos(phi), -sin(phi)],
         [sin(phi), cos(phi)]]
        )

RSS = Matrix(
        [[cos(phi - y)/cos(y), -cos(phi - y)*tan(x)/cos(y) - sin(phi)],
         [sin(phi - y)/cos(y), -sin(phi - y)*tan(x)/cos(y) + cos(phi)]])

print(simplify(R * Ys * Xs - RSS))

One thing that is not clear (and could be tested) is whether avoiding
the explicit products and calculations in _get_inverse_affine_matrix
really gives performance benefits - compared to doing the explicit
calculation done in _test_transformation.

* Use np.matmul instead of @

The @ syntax is not supported in Python 2.
      c226bb95
  47. 26 Oct, 2019 1 commit
    • pedrofreire's avatar
      Add adjustment operations for RGB Tensor Images. (#1525) · e79caddf
      pedrofreire authored 
      * Add adjustment operations for RGB Tensor Images.

Right now, we have operations on PIL images, but we want to have a version of the opeartions that act directly on Tensor images.

Here, we add such operations for adjust_brightness, adjust_contrast and adjust_saturation.

In PIL, those functions are implemented by generating an degenerate image from the first, and then interpolating them together.
- https://github.com/python-pillow/Pillow/blob/master/src/PIL/ImageEnhance.py
- https://github.com/python-pillow/Pillow/blob/master/src/libImaging/Blend.c

A few caveats:
* Since PIL operates on uint8, and the tensor operations might be on float, we can get slightly different values because of int truncation.
* We assume here the images are RGB; in particular, to handle an alpha channel, we need to check whether it is present, in which case we copy it to the final image.

* Keep dtype and use broadcast in adjust operations

- We make our operations have input.dtype == output.dtype, at the cost of
adding a few type checks and branches.

- By using Tensor broadcast, we can simplify the calls to _blend.

* Use is_floating_point to check dtype.

* Remove unpacking in tuple

It seems Python 2 does not support this type of unpacking, so it broke
Python 2 builds. This should fix it.

* Add from __future__ import division for Python 2
      e79caddf
  49. 18 Oct, 2019 2 commits
    • ekka's avatar
      Make crop scriptable (#1379) · d194082c
      ekka authored 
      * Make crop torchscriptable

Relevant #1375

* Invert x and y axis

* fix lint

* Add crop test

* revert deletion of space in functional

* add import random

* add dimension in doc

* add import

* fix flake8

* change to self.assert*

* convert to uint8

* assertTrue

* lint
      d194082c
    • Surgan Jandial's avatar
      PILLOW_VERSION deprecation updates (#1501) · b8ef5322
      Surgan Jandial authored 
      * doc-build fixed

* deprecation fixes

* deprecation updates
      b8ef5322
  51. 16 Oct, 2019 1 commit
  53. 08 Oct, 2019 1 commit
  55. 30 Sep, 2019 1 commit
  57. 24 Sep, 2019 1 commit
    • Zhicheng Yan's avatar
      Video transforms (#1353) · 64917bcc
      Zhicheng Yan authored 
      * video transforms

* [video transforms]in ToTensorVideo, divide value by 255.0

* [video transforms] fix a bug

* fix linting

* Make changes backwards-compatible
      64917bcc
  59. 11 Sep, 2019 1 commit
  61. 06 Sep, 2019 1 commit
  63. 30 Aug, 2019 1 commit
  65. 09 Jul, 2019 1 commit