[Tests] reduce block sizes of UNet and VAE tests #7560
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
sayakpaul
commented
Apr 2, 2024
| enable_full_determinism() | ||
|
|
||
|
|
||
| @skip_mps |
Member
Author
There was a problem hiding this comment.
More than 60% of the tests under this class fails on my Mac Silicon (because Silicon currently doesn't have support for Conv3D). Better to just skip them entirely.
DN6
reviewed
Apr 3, 2024
DN6
reviewed
Apr 3, 2024
DN6
reviewed
Apr 3, 2024
DN6
reviewed
Apr 3, 2024
| def prepare_init_args_and_inputs_for_common(self): | ||
| init_dict = { | ||
| "block_out_channels": (32, 64), | ||
| "block_out_channels": (16, 32), |
Member
Author
There was a problem hiding this comment.
There's a hard-coded 32 value somewhere in the TransformerSpatioTemporalModel module. It will lead to:
FAILED tests/models/unets/test_models_unet_motion.py::UNetMotionModelTests::test_output - ValueError: num_channels must be divisible by num_groupsSo, a little infeasible at the moment. But I have made a best effort to reduce the other dimensions (such as sample size, number of frames, cross attention dim, etc.). Hopefully that cuts it?
Member
Author
|
@DN6 up for another review. |
noskill
pushed a commit
to noskill/diffusers
that referenced
this pull request
Apr 5, 2024
* reduce block sizes for unet1d. * reduce blocks for unet_2d. * reduce block size for unet_motion * increase channels. * correctly increase channels. * reduce number of layers in unet2dconditionmodel tests. * reduce block sizes for unet2dconditionmodel tests * reduce block sizes for unet3dconditionmodel. * fix: test_feed_forward_chunking * fix: test_forward_with_norm_groups * skip spatiotemporal tests on MPS. * reduce block size in AutoencoderKL. * reduce block sizes for vqmodel. * further reduce block size. * make style. * Empty-Commit * reduce sizes for ConsistencyDecoderVAETests * further reduction. * further block reductions in AutoencoderKL and AssymetricAutoencoderKL. * massively reduce the block size in unet2dcontionmodel. * reduce sizes for unet3d * fix tests in unet3d. * reduce blocks further in motion unet. * fix: output shape * add attention_head_dim to the test configuration. * remove unexpected keyword arg * up a bit. * groups. * up again * fix
sayakpaul
added a commit
that referenced
this pull request
Dec 23, 2024
* reduce block sizes for unet1d. * reduce blocks for unet_2d. * reduce block size for unet_motion * increase channels. * correctly increase channels. * reduce number of layers in unet2dconditionmodel tests. * reduce block sizes for unet2dconditionmodel tests * reduce block sizes for unet3dconditionmodel. * fix: test_feed_forward_chunking * fix: test_forward_with_norm_groups * skip spatiotemporal tests on MPS. * reduce block size in AutoencoderKL. * reduce block sizes for vqmodel. * further reduce block size. * make style. * Empty-Commit * reduce sizes for ConsistencyDecoderVAETests * further reduction. * further block reductions in AutoencoderKL and AssymetricAutoencoderKL. * massively reduce the block size in unet2dcontionmodel. * reduce sizes for unet3d * fix tests in unet3d. * reduce blocks further in motion unet. * fix: output shape * add attention_head_dim to the test configuration. * remove unexpected keyword arg * up a bit. * groups. * up again * fix
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.
In some cases, changing the number of groups is simply not possible because internally it's hard-coded. So, I haven't touched those (UNetSpatioTemporal for example).