# for weight in map_weights:
# weight[-1] = backtransform_constrained_scale(0.014, transform_unconstrained_scale_factor).numpy()
ensemble.set_weights(map_weights)
[network.noise_sigma for network in ensemble.networks]
initial_unconstrained_scales = [map_weights[i][-1] for i in range(len(map_weights))]
predictions = [network.predict(x_train) for network in ensemble.networks]
print(
"Initial samples' mean train negative log likelihood",
[
-tf.reduce_mean(prediction.log_prob(y_train)).numpy()
for prediction in predictions
],
)
ensemble.fit(
x_train=x_train, y_train=y_train, batch_size=batch_size, epochs=10, verbose=0
)
predictions = [network.predict(x_train) for network in ensemble.networks]
print(
"After gradients descent training mean train negative log likelihood",
[
-tf.reduce_mean(prediction.log_prob(y_train)).numpy()
for prediction in predictions
],
)
[network.noise_sigma for network in ensemble.networks]
map_weights = ensemble.get_weights()
# for weight, scale in zip(map_weights, initial_unconstrained_scales):
# weight[-1] = scale # backtransform_constrained_scale(0.014, transform_unconstrained_scale_factor).numpy() #backtransform_constrained_scale(np.array([0.1]), transform_unconstrained_scale_factor).numpy().astype(np.float32)
# ensemble.set_weights(map_weights)
initial_learning_rate = 0.01
lr_schedule = tf.keras.optimizers.schedules.ExponentialDecay(
initial_learning_rate, decay_steps=n_train, decay_rate=0.9, staircase=True)
ensemble = MapDensityEnsemble(
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,
initial_learning_rate, decay_steps=20, decay_rate=0.9, staircase=True
)
ensemble = MapDensityEnsemble(
n_networks=2,
input_shape=[1],
layer_units=layer_units,
layer_activations=layer_activations,
learning_rate=lr_schedule,
seed=0,
)
ensemble.fit(
x_train=x_train, y_train=y_train, batch_size=batchsize_train, epochs=100, verbose=0
)
# %%
mog_prediction = ensemble.predict(x_plot) # Mixture Of Gaussian prediction
plot_moment_matched_predictive_normal_distribution(
x_plot=_x_plot,
predictive_distribution=mog_prediction,
x_train=_x_train,
y_train=y_train,
y_ground_truth=y_ground_truth,
y_lim=y_lim,
)
# %%
ensemble.fit_additional_memebers(