Tutorial 1a: Building the SPN Graph Using Single Op Nodes

The simplest and most readable way to make small SPNs is through 'single op' nodes like Sum or Product.

In [1]:
import libspn as spn
import tensorflow as tf

Build the SPN

In [2]:
indicator_leaves = spn.IndicatorLeaf(
    num_vars=2, num_vals=2, name="indicator_x")

# Connect first two sums to indicators of first variable
sum_11 = spn.Sum((indicator_leaves, [0,1]), name="sum_11")
sum_12 = spn.Sum((indicator_leaves, [0,1]), name="sum_12")

# Connect another two sums to indicators of the second variable
sum_21 = spn.Sum((indicator_leaves, [2,3]), name="sum_21")
sum_22 = spn.Sum((indicator_leaves, [2,3]), name="sum_22")

# Connect three product nodes
prod_1 = spn.Product(sum_11, sum_21, name="prod_1")
prod_2 = spn.Product(sum_11, sum_22, name="prod_2")
prod_3 = spn.Product(sum_12, sum_22, name="prod_3")

# Connect a root sum
root = spn.Sum(prod_1, prod_2, prod_3, name="root")

# Connect a latent indicator
indicator_y = root.generate_latent_indicators(name="indicator_y") # Can be added manually

# Generate weights
spn.generate_weights(root, initializer=tf.initializers.random_uniform()) # Can be added manually
[WARNING] [tensorflow:__getattr__] From /home/jos/spn/libspn/libspn/graph/node.py:40: The name tf.get_default_graph is deprecated. Please use tf.compat.v1.get_default_graph instead.

[WARNING] [tensorflow:__getattr__] From /home/jos/spn/libspn/libspn/graph/leaf/indicator.py:63: The name tf.placeholder is deprecated. Please use tf.compat.v1.placeholder instead.


In [3]:
# Inspect
[Scope({indicator_x:1, indicator_y:0, indicator_x:0})]

Visualize the SPN Graph

The visualization below uses graphviz. Depending on your setup (e.g. jupyter lab vs. jupyter notebook) this might fail to show. At least Chrome + jupyter notebook seems to work.

In [4]:
# Visualize SPN graph