issues Search Results · repo:sbi-dev/sbi language:Python
Filter by
763 results
(67 ms)763 results
insbi-dev/sbi (press backspace or delete to remove)🐛 Bug Description
The following message is returned by simulate_for_sbi when an arbitrary TypeError is encountered in the simulator:
TypeError: For multiprocessing, we switch to numpy arrays. Make sure ...
bug
vagechirkov
- Opened 15 hours ago
- #1688
Small bug when using NPSE with the training interface: for z-scoring, when calling build_vector_field_estimator, one has
to move data to CPU, otherwise a device mismatch will emerge.
An easy way to fix ...
bug
michaeldeistler
- 1
- Opened yesterday
- #1686
We use the sum across theta-dimensions for NPSE here.
Because of this, we should technically use a different learning rate for different theta-dimensions. Should we not just
use the mean?
When doing ...
- 2
- Opened yesterday
- #1685
🚀 Feature Request
Add NPE-PFN to the library (in the same way as autogluon)
NPE-PFN is easy-to-use and has strong performance, particularly for small simulation budgets. But currently it is based
on ...
enhancement
jsvetter
- 5
- Opened 8 days ago
- #1682
All of our vectorfield estimators force the use use of structured z-scoring, see here.
I think this is really detrimental if parameters live on different scales. Is there a reason this is like that? Am ...
bug
- Opened 12 days ago
- #1680
from sbi.inference import NPSE
from sbi.utils import BoxUniform
import torch
import pickle
prior = BoxUniform(-torch.ones(3,), torch.ones(3,))
theta = prior.sample((100,))
x = torch.randn((100, 2))
inference ...
bug
- 1
- Opened 12 days ago
- #1678
🐛 Bug Description
When using NPE and calling the train() method a second time, while setting both force_first_round_loss and
resume_training arguments to False. The assertion set on this line is raised ...
bug
abelaba
- Opened 15 days ago
- #1676
🚀 Feature Request
Add support for multimodal x_o
SBI expects data x_o to be Tensor, which makes it difficult to work with multimodal data. In many real-world scientific
applications data can contain ...
enhancement
feature
StarostinV
- 3
- Opened 28 days ago
- #1672
🐛 Bug Description
When attempting to pickle a posterior built with NPSE, the process fails with an error:
AttributeError: Can t pickle local object ConditionalScoreEstimator._set_weight_fn. locals . ...
bug
joshvillarreal
- Opened on Oct 2
- #1670
Context
- pairplot refactoring in #1631 introduces typed options and upper/lower/diag API; offdiag is deprecated.
- Pain point remains: users still pass many repeated args (labels, limits, ticks) ...
enhancement
janfb
- Opened on Sep 18
- #1667
Learn how you can use GitHub Issues to plan and track your work.
Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub IssuesProTip!
Restrict your search to the title by using the in:title qualifier.Learn how you can use GitHub Issues to plan and track your work.
Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub IssuesProTip!
Restrict your search to the title by using the in:title qualifier.