decoder_output2 = DeterministicVariable(decoder2(z2),
name="decoder_output2")
z3 = NormalVariable(BF.relu(decoder_output2["mean"]),
z3sd * np.ones((latent_size3, )),
name="z3")
decoder_output3 = DeterministicVariable(decoder3(z3),
name="decoder_output3")
x = BinomialVariable(total_count=1,
logits=decoder_output3["mean"],
name="x")
model = ProbabilisticModel([x, z1, z2, z3, labels])
# Amortized variational distribution
minibatch_indices = RandomIndices(dataset_size=dataset_size,
batch_size=b_size,
name="indices",
is_observed=True)
Qx = EmpiricalVariable(dataset,
indices=minibatch_indices,
name="x",
is_observed=True)
Qlabels = EmpiricalVariable(output_labels,
indices=minibatch_indices,
name="labels",
is_observed=True)
encoder_output1 = DeterministicVariable(encoder1(Qx),
name="encoder_output1")
Qz3 = NormalVariable(encoder_output1["mean"],
train=True,
download=True,
transform=None)
test = torchvision.datasets.MNIST(root='./data',
train=False,
download=True,
transform=None)
dataset_size = len(train)
input_variable = np.reshape(train.train_data.numpy(),
newshape=(dataset_size, number_pixels, 1))
output_labels = train.train_labels.numpy()
# Data sampling model
minibatch_size = 30
minibatch_indices = RandomIndices(dataset_size=dataset_size,
batch_size=minibatch_size,
name="indices",
is_observed=True)
x = EmpiricalVariable(input_variable,
indices=minibatch_indices,
name="x",
is_observed=True)
labels = EmpiricalVariable(output_labels,
indices=minibatch_indices,
name="labels",
is_observed=True)
# Architecture parameters
number_hidden_units = 20
b1 = NormalVariable(np.zeros((number_hidden_units, 1)), 10 * np.ones(
(number_hidden_units, 1)), "b1")
b2 = NormalVariable(np.zeros((number_output_classes, 1)), 10 * np.ones(
import numpy as np import chainer import chainer.links as L import chainer.functions as F from brancher.variables import DeterministicVariable, RandomVariable, ProbabilisticModel from brancher.standard_variables import NormalVariable, EmpiricalVariable, RandomIndices from brancher.functions import BrancherFunction import brancher.functions as BF ## Data ## dataset_size = 100 number_dimensions = 1 dataset1 = np.random.normal(0, 1, (dataset_size, number_dimensions)) ## Variables ## indices = RandomIndices(dataset_size=dataset_size, batch_size=5, name="indices") a = EmpiricalVariable(dataset1, indices=indices, name='a', is_observed=True) b = EmpiricalVariable(dataset1, indices=indices, name='a', is_observed=True) model = ProbabilisticModel([a, b]) ## Sample ## samples = model._get_sample(1) print(samples[a]) print(samples[b])
