Skip to content

improve performance of {invert, solarize}_image_tensor #6819

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 6 commits into from
Oct 24, 2022
Merged

improve performance of {invert, solarize}_image_tensor #6819

Changes from 2 commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
f1a248f
improve performance of invert_image_tensor
pmeier Oct 24, 2022
0cc6cdd
cleanup
pmeier Oct 24, 2022
34c075c
lint
pmeier Oct 24, 2022
7adfeb5
more cleanup
pmeier Oct 24, 2022
d8af69b
Merge branch 'main' into perf/invert
pmeier Oct 24, 2022
f8f68d7
use new invert in solarize
pmeier Oct 24, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 9 additions & 1 deletion torchvision/prototype/transforms/functional/_color.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -435,7 +435,15 @@ def equalize(inpt: features.InputTypeJIT) -> features.InputTypeJIT:
return equalize_image_pil(inpt)


invert_image_tensor = _FT.invert
def invert_image_tensor(image: torch.Tensor):
_FT._assert_image_tensor(image)

if image.dtype == torch.uint8:
return image.bitwise_not()
else:
return _FT._max_value(image.dtype) - image
Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I couldn't believe it, but this seems to be fastest way:

def scalar_sub(image):
    return _max_value(image.dtype) - image


def new_full(image):
    return image.new_full(image.shape, _max_value(image.dtype)).sub_(image)


def full_like(image):
    return torch.full_like(image, _max_value(image.dtype)).sub_(image)
[-------------------- invert float or signed integer tensors -------------------]
                                         |  scalar_sub  |  new_full  |  full_like
1 threads: ----------------------------------------------------------------------
      (3, 256, 256)    / int32   / cpu   |      20      |     28     |      26   
      (3, 256, 256)    / int32   / cuda  |       5      |      8     |       7   
      (3, 256, 256)    / int64   / cpu   |      88      |    109     |     107   
      (3, 256, 256)    / int64   / cuda  |      13      |     22     |      22   
      (3, 256, 256)    / float64 / cpu   |      35      |     49     |      49   
      (3, 256, 256)    / float64 / cuda  |      12      |     21     |      21   
      (5, 3, 256, 256) / int32   / cpu   |      76      |    112     |     110   
      (5, 3, 256, 256) / int32   / cuda  |      34      |     67     |      67   
      (5, 3, 256, 256) / int64   / cpu   |     439      |    510     |     524   
      (5, 3, 256, 256) / int64   / cuda  |      68      |    133     |     133   
      (5, 3, 256, 256) / float64 / cpu   |     140      |    215     |     220   
      (5, 3, 256, 256) / float64 / cuda  |      68      |    133     |     133   

Times are in microseconds (us).



invert_image_pil = _FP.invert


Expand Down