Make transfer_model more user-friendly #115
Merged
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
gngdb
commented
Feb 16, 2022
| @@ -142,7 +142,9 @@ def __init__( | |||
| shapedirs = data_struct.shapedirs | |||
| if (shapedirs.shape[-1] < self.SHAPE_SPACE_DIM): | |||
| print(f'WARNING: You are using a {self.name()} model, with only' | |||
| ' 10 shape coefficients.') | |||
|
@gngdb can you update the description for the Trust NCG optimizer? I fixed the packaging in that repo, so the rollback is no longer needed. |
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Outdated suggestions cannot be applied.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 added some example code, sample data and steps for how to use the
transfer_modelutility. Also, I updated the install instructions based on my experience, which should keep working for a bit longer.Also, I cleaned up
joint_names.pyand added a class to make it easier to convert between SMPL and SMPL-H joint names, which is faster and more convenient than running thetransfer_model.pyutility when converting between those two body models. Although, it may not be preferred because I think two hand joints get dropped in the conversion instead of getting matched to the set of hand joints in SMPL-H, is that right?Bodyclass usage is based on scipy.spatial.transform.Rotation. If we have some body pose dataxin SMPL format (rotational formalism doesn't matter) that is an array of shape(number of joints, number of rotational dimensions), convert it to SMPL-H arrayy:y = Body.from_smpl(x).as_smplh().This pull request would address #75, #82 and other issues.