n_networks=n_networks,
input_shape=[1],
layer_units=layer_units,
layer_activations=layer_activations,
learning_rate=lr_schedule,
seed=seed,
)
ensemble.fit(x_train=x_train,
y_train=y_train,
batch_size=batch_size,
epochs=epochs,
verbose=0)
# %%
prediction = ensemble.predict(x_plot) # Mixture Of Gaussian prediction
fig, ax = plt.subplots(figsize=figsize)
plot_moment_matched_predictive_normal_distribution(
x_plot=_x_plot,
predictive_distribution=prediction,
x_train=_x_train,
y_train=y_train,
y_ground_truth=y_ground_truth,
fig=fig,
ax=ax,
y_lim=y_lim,
title="Ensemble of ten MAP networks",
save_path=figure_dir.joinpath(
f"ensemble_moment_matched_{experiment_name}.pdf"),
)
layer_units=layer_units,
layer_activations=layer_activations,
initial_unconstrained_scale=initial_unconstrained_scale,
transform_unconstrained_scale_factor=transform_unconstrained_scale_factor,
preprocess_x=preprocess_x,
preprocess_y=preprocess_y,
learning_rate=lr_schedule,
names=[None, "feature_extractor", "output"],
seed=0,
)
ensemble.fit(x_train=x_train,
y_train=y_train,
batch_size=batch_size,
epochs=epochs,
verbose=0)
prediction = ensemble.predict(x_plot)
plot_moment_matched_predictive_normal_distribution(
x_plot=x_plot,
predictive_distribution=prediction,
x_train=x_train,
y_train=y_train,
y_ground_truth=y_ground_truth,
y_lim=y_lim,
)
# %%
llb_ensemble = LLBEnsemble(
input_shape=[1],
layer_units=layer_units,
layer_activations=layer_activations,
initial_unconstrained_scale=initial_unconstrained_scale,