https://github.com/GPflow/GPflow
Revision aff62bcc29d77b740b81cbadc83656efe2adc080 authored by st-- on 30 March 2020, 09:32:58 UTC, committed by GitHub on 30 March 2020, 09:32:58 UTC
* Adds an explicit check to Scipy() that all elements of `variables` are actually tf.Variable instances (unconstrained variables) - accidentally passing `model.trainable_parameters` may work but give the wrong answers for parameters with transforms! Passing `model.trainable_variables` is the right thing to do. * Updates _compute_loss_and_gradients to only compute gradients wrt passed-in variables. * Fix mixture density network notebook, which had erroneously passed model.trainable_parameters instead of model.trainable_variables.
1 parent d41d6eb
Tip revision: aff62bcc29d77b740b81cbadc83656efe2adc080 authored by st-- on 30 March 2020, 09:32:58 UTC
Make Scipy more robust & faster (#1377)
Make Scipy more robust & faster (#1377)
Tip revision: aff62bc
File | Mode | Size |
---|---|---|
conditionals | ||
config | ||
covariances | ||
expectations | ||
inducing_variables | ||
kernels | ||
likelihoods | ||
models | ||
optimizers | ||
utilities | ||
__init__.py | -rw-r--r-- | 1.1 KB |
base.py | -rw-r--r-- | 10.7 KB |
ci_utils.py | -rw-r--r-- | 1.3 KB |
kullback_leiblers.py | -rw-r--r-- | 5.8 KB |
logdensities.py | -rw-r--r-- | 3.3 KB |
mean_functions.py | -rw-r--r-- | 5.8 KB |
monitor.py | -rw-r--r-- | 12.2 KB |
probability_distributions.py | -rw-r--r-- | 1.7 KB |
py.typed | -rw-r--r-- | 27 bytes |
quadrature.py | -rw-r--r-- | 7.7 KB |
versions.py | -rw-r--r-- | 177 bytes |
Computing file changes ...