Skip to content

Fix typo and format BasicTransformerBlock attributes #2953

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 14 commits into from
Apr 11, 2023
Merged

Fix typo and format BasicTransformerBlock attributes #2953

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
14 commits
Select commit Hold shift + click to select a range
aee4e4b
⚙️chore(train_controlnet) fix typo in logger message
offchan42 Apr 3, 2023
9ef8a7d
⚙️chore(models) refactor modules order; make them the same as calling…
offchan42 Apr 3, 2023
768cfb6
Merge branch 'main' into main
patrickvonplaten Apr 4, 2023
476ff93
correct many tests
patrickvonplaten Apr 6, 2023
b6a8561
remove bogus file
patrickvonplaten Apr 6, 2023
bc2f848
make style
patrickvonplaten Apr 6, 2023
74de7db
Merge branch 'main' into main
patrickvonplaten Apr 11, 2023
4366416
correct more tests
patrickvonplaten Apr 11, 2023
2572b42
finish tests
patrickvonplaten Apr 11, 2023
7cc0984
fix one more
patrickvonplaten Apr 11, 2023
f587927
make style
patrickvonplaten Apr 11, 2023
5b95b5a
make unclip deterministic
patrickvonplaten Apr 11, 2023
865328c
Merge branch 'main' into main
patrickvonplaten Apr 11, 2023
b911a4f
⚙️chore(models/attention) reorganize comments in BasicTransformerBloc…
offchan42 Apr 11, 2023
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
2 changes: 1 addition & 1 deletion tests/pipelines/text_to_video/test_text_to_video.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -135,7 +135,7 @@ def test_text_to_video_default_case(self):
image_slice = frames[0][-3:, -3:, -1]

assert frames[0].shape == (64, 64, 3)
expected_slice = np.array([158., 160., 153., 125., 100., 121., 111., 93., 113.])
expected_slice = np.array([158.0, 160.0, 153.0, 125.0, 100.0, 121.0, 111.0, 93.0, 113.0])

assert np.abs(image_slice.flatten() - expected_slice).max() < 1e-2

Expand Down
4 changes: 2 additions & 2 deletions tests/test_layers_utils.py
View file
Open in desktop
Copy link
Contributor Author

@offchan42 offchan42 Apr 6, 2023 •
edited
Loading

Choose a reason for hiding this comment

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

I tried running pytest on this file and it said that the expected_slice should be tensor. Maybe it's because I have different pytorch version or something. I'm quite new to github actions and make file stuff that you have in the repo so not sure how to fix the tests. I also think I haven't installed the same python packages version from your repo so maybe it will make my tests more erroneous than what they should be.

Original file line number Diff line number Diff line change
Expand Up @@ -412,7 +412,7 @@ def test_spatial_transformer_cross_attention_dim(self):
assert attention_scores.shape == (1, 64, 64, 64)
output_slice = attention_scores[0, -1, -3:, -3:]

expected_slice = np.array([ 0.0143, -0.6909, -2.1547, -1.8893, 1.4097, 0.1359, -0.2521, -1.3359, 0.2598])
expected_slice = np.array([0.0143, -0.6909, -2.1547, -1.8893, 1.4097, 0.1359, -0.2521, -1.3359, 0.2598])
assert torch.allclose(output_slice.flatten(), expected_slice, atol=1e-3)

def test_spatial_transformer_timestep(self):
Expand Down Expand Up @@ -443,7 +443,7 @@ def test_spatial_transformer_timestep(self):
output_slice_1 = attention_scores_1[0, -1, -3:, -3:]
output_slice_2 = attention_scores_2[0, -1, -3:, -3:]

expected_slice = np.array([-0.3923, -1.0923, -1.7144, -1.5570, 1.4154, 0.1738, -0.1157, -1.2998, -0.1703])
expected_slice = np.array([-0.3923, -1.0923, -1.7144, -1.5570, 1.4154, 0.1738, -0.1157, -1.2998, -0.1703])
expected_slice_2 = torch.tensor(
[-0.3493, -1.0924, -1.6161, -1.5016, 1.4245, 0.1367, -0.2526, -1.3109, -0.0547], device=torch_device
)
Expand Down