Complete set_attn_processor for prior and vae #3796
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
|
The documentation is not available anymore as the PR was closed or merged. |
patrickvonplaten
changed the title
sayakpaul
reviewed
Jun 15, 2023
|
|
||
| import torch | ||
| import torch.nn as nn | ||
|
|
||
| from ..configuration_utils import ConfigMixin, register_to_config | ||
| from ..utils import BaseOutput, apply_forward_hook | ||
| from .attention_processor import AttentionProcessor, AttnProcessor |
There was a problem hiding this comment.
Should we maybe also implement this automatic discoverability of AttnProcessor2_0?
There was a problem hiding this comment.
I don't fully follow here. Note that by default the ATTN 2.0 is always chosen whenever someone uses the Attention class which is done for both the AutoEncoder and the Prior, see:
-
and:
sayakpaul
reviewed
Jun 15, 2023
sayakpaul
reviewed
Jun 15, 2023
sayakpaul
reviewed
Jun 15, 2023
| @@ -182,8 +184,9 @@ def test_output_pretrained(self): | |||
| self.assertTrue(torch_all_close(output_slice, expected_output_slice, rtol=1e-3)) | |||
|
|
|||
|
|
|||
| class NCSNppModelTests(ModelTesterMixin, unittest.TestCase): | |||
| class NCSNppModelTests(ModelTesterMixin, UNetTesterMixin, unittest.TestCase): | |||
There was a problem hiding this comment.
Curiosity:
What does it mean by NCSNpp?
There was a problem hiding this comment.
sayakpaul
reviewed
Jun 15, 2023
| @@ -153,8 +154,9 @@ def test_unet_1d_maestro(self): | |||
| assert (output_max - 0.0607).abs() < 4e-4 | |||
|
|
|||
|
|
|||
| class UNetRLModelTests(ModelTesterMixin, unittest.TestCase): | |||
| class UNetRLModelTests(ModelTesterMixin, UNetTesterMixin, unittest.TestCase): | |||
There was a problem hiding this comment.
Curiosity?
What is it called UNetRLModelTests?
There was a problem hiding this comment.
Tests a RL model we've integrated
sayakpaul
reviewed
Jun 15, 2023
Co-authored-by: Sayak Paul <[email protected]>
yoonseokjin
pushed a commit
to yoonseokjin/diffusers
that referenced
this pull request
Dec 25, 2023
* relax tolerance slightly * Add more tests * upload readme * upload readme * Apply suggestions from code review * Improve API Autoencoder KL * finalize * finalize tests * finalize tests * Apply suggestions from code review Co-authored-by: Sayak Paul <[email protected]> * up --------- Co-authored-by: Sayak Paul <[email protected]>
AmericanPresidentJimmyCarter
pushed a commit
to AmericanPresidentJimmyCarter/diffusers
that referenced
this pull request
Apr 26, 2024
* relax tolerance slightly * Add more tests * upload readme * upload readme * Apply suggestions from code review * Improve API Autoencoder KL * finalize * finalize tests * finalize tests * Apply suggestions from code review Co-authored-by: Sayak Paul <[email protected]> * up --------- Co-authored-by: Sayak Paul <[email protected]>
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.
This adds cleans up the tests a bit and makes sure that:
UNet2DConditionModelPriorTransformerAutoencoderKLall have the same features. This PR also cleans up the tests a bit and adds a whole test suite for the prior transformer.