You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I expect the shape of the log_prob of a (sample_shape=[10], batch_shape=[], event_shape=[1]) sample+distribution to have shape [10].
Actual behavior: Result is of shape [10, 10]
RC: TransformedDistribution.log_prob is broadcasting a summation over a row / column vector
The text was updated successfully, but these errors were encountered:
feynmanliang
changed the title
Bijector.log_prob return shape incompatible with batch dimension semantic
TransformedDistribution.log_prob return shape incompatible with batch dimension semantic
Dec 17, 2020
When I run
I expect the shape of the
log_prob
of a (sample_shape=[10], batch_shape=[], event_shape=[1]) sample+distribution to have shape [10].Actual behavior: Result is of shape [10, 10]
RC:
TransformedDistribution.log_prob
is broadcasting a summation over a row / column vectorThe text was updated successfully, but these errors were encountered: