Skip to content
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

Jump to bottom

Correction of sizefactors #69

Open
SabrinaRichter opened this issue Mar 20, 2019 · 4 comments
Open

Correction of sizefactors #69

SabrinaRichter opened this issue Mar 20, 2019 · 4 comments

Comments

@SabrinaRichter
Copy link
Member

SabrinaRichter commented Mar 20, 2019 •
edited

I think here

batchglm/batchglm/train/tf/glm_norm/estimator.py

Line 246 in 27b648e

init_mean = init_mean + np.log(size_factors_init)

it should be init_mean = init_mean / size_factors_init.
@davidsebfischer
Copy link
Contributor

Yes, this is true.

@SabrinaRichter
Copy link
Member Author

Then this

batchglm/batchglm/train/tf/glm_norm/model.py

Line 82 in 27b648e

eta_loc = tf.add(eta_loc, size_factors)

should probably also be eta_loc = tf.divide(eta_loc, size_factors).

@SabrinaRichter
Copy link
Member Author

How about this?

batchglm/batchglm/models/base_glm/model.py

Line 75 in 27b648e

eta += self.link_loc(np.expand_dims(self.size_factors, axis=1))

@davidsebfischer
Copy link
Contributor

I don't see an issue with this, give it a go, if it works we could use this as a general syntax.

@SabrinaRichter SabrinaRichter mentioned this issue Mar 20, 2019
Merged
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@davidsebfischer @SabrinaRichter