Sample fix #3
Open
Sample fix #3
Conversation
This file contains 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
|
Hey, I just wanted to say that this was a really helpful PR for me! I could get the model up and running with the changes you suggested. Thanks! |
|
I also figured out that you need to specify the following option or something similar (e.g. in redesign_regions: ["L1", "L2", "H1", "H2"]Otherwise, every index gets masked, and sampling never changes the seed values! |
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Outdated suggestions cannot be applied.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.
I encountered some bugs while sampling. Maybe it's just me, but when instantiating the model in
src/walkjump/cmdline/_sample.py, The instantiate_model_for_sample_mode function doesn't seem to accept the DictConfig input. This is solved by either giving the specific inputs like
def instantiate_model_for_sample_mode( model_type, checkpoint_path, denoise_path) -> NoiseEnergyModel | DenoiseModel:Or by instantiating the model by calling the function directly, like what is done with instantiate_redesign_mask and instantiate_seeds.
I also added some examples and comments.