Unified input for F.affine #2444
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
16 tasks
vfdev-5
force-pushed
the
vfdev-5/issue-2292-affine
branch
from
d7ae44c to
f33b391
Compare
fmassa
reviewed
Jul 10, 2020
torchvision/transforms/functional.py
Outdated
| @@ -1,12 +1,11 @@ | |||
| import math | |||
| import numbers | |||
| import warnings | |||
| from collections.abc import Iterable | |||
| from typing import Any | |||
| from typing import Any, Optional, Sequence | |||
|
|
|||
| import numpy as np | |||
| from numpy import sin, cos, tan | |||
There was a problem hiding this comment.
maybe this import is not needed anymore?
test/test_transforms.py
Outdated
| # Accept 3 wrong pixels | ||
| self.assertLess(n_diff_pixels, 3, | ||
| # Accept 7 wrong pixels | ||
| self.assertLess(n_diff_pixels, 7, |
There was a problem hiding this comment.
Was this test flaky before? Or is this needed due to the change in the center of the transform pixel (the +0.5 is added in a different location now)
|
|
||
| if need_cast: | ||
| # it is better to round before cast | ||
| img = torch.round(img).to(out_dtype) |
There was a problem hiding this comment.
I saw you did this round for a couple of functions, does it make results closer to PIL?
There was a problem hiding this comment.
Yes, rounding makes sense for example when floating results is
tensor([[ 0.09, 1.01, 1.97, 2.96, 3.99],
[10.94, 12.15, 13.35, 14.56, 15.77],
[22.92, 24.13, 25.34, 26.54, 27.75],
[34.90, 36.11, 37.32, 38.53, 39.73],
[46.88, 48.09, 49.30, 50.51, 51.72]])
and so casting without round gives
tensor([[ 0, 1, 1, 2, 3],
[10, 12, 13, 14, 15],
[22, 24, 25, 26, 27],
[34, 36, 37, 38, 39],
[46, 48, 49, 50, 51]], dtype=torch.uint8)
fmassa
approved these changes
Jul 16, 2020
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Related to #2292
Description:
=> adapted corresponding tests on PIL images.