def test_transposition(self):
"""This test is for evaluating caching when the same variable is used as two different arguments of the same predicate"""
World.reset()
def inside(x, y):
centers_distance = tf.sqrt(
tf.reduce_sum(tf.squared_difference(x[:, 0:2], y[:, 0:2]),
axis=1) + 1e-6)
return tf.cast((centers_distance + x[:, 2]) < y[:, 2], tf.float32)
circles = tfl.Domain(label="Circles",
data=[[0., 0, 1], [0, 0, 2], [0, 0, 3]])
inside = tfl.Predicate(label="inside",
domains=["Circles", "Circles"],
function=inside)
tfl.setTNorm(id=tfl.SS, p=1)
sess = tf.Session()
# Constraint 1
x = tfl.variable(circles, name="x")
y = tfl.variable(circles, name="y")
a = tfl.atom(inside, (x, y))
b = tfl.atom(inside, (y, x))
rule = tfl.and_n(a, b)
assert np.greater(sess.run(rule), np.zeros(shape=[3, 3, 3])).all()
assert len(World._predicates_cache) == 1
def test_subdomain(self):
World.reset()
"""Checking caching mechanism works"""
# Program Model
nn = tfl.functions.FeedForwardNN(input_shape=[2], output_size=2)
images = tfl.Domain(label="Images", data=[[0., 0], [1, 1], [0.2, 0.3]])
supervised_images = tfl.Domain(label="SupImages",
data=[[0., 0], [1, 1]],
father=images)
zero = tfl.Predicate(label="zero",
domains=["Images"],
function=tfl.functions.Slice(nn, 0))
one = tfl.Predicate(label="one",
domains=["Images"],
function=tfl.functions.Slice(nn, 1))
tfl.setTNorm(id=tfl.PRODUCT, p=None)
# Constraint 1
c1 = tfl.constraint("zero(x) and one(x)", {"x": supervised_images})
x = tfl.variable(supervised_images, name="x")
c2 = tfl.and_n(zero(x), one(x))
sess = tf.Session()
sess.run(tf.global_variables_initializer())
assert len(sess.run(c1)) == supervised_images.size
assert np.equal(sess.run(c1), sess.run(c2)).all()
def test_parser_forall(self):
World.reset()
World._evaluation_mode = tfl.LOGIC_MODE
tfl.setTNorm(id=tfl.SS, p=1)
sess = tf.Session()
def inside(x, y):
centers_distance = tf.sqrt(
tf.reduce_sum(tf.squared_difference(x[:, 0:2], y[:, 0:2]),
axis=1) + 1e-6)
return tf.cast((centers_distance + x[:, 2]) < y[:, 2], tf.float32)
circles = tfl.Domain(label="Circles",
data=[[0., 0, 1], [0, 0, 2], [0, 0, 3]])
inside = tfl.Predicate(label="inside",
domains=["Circles", "Circles"],
function=inside)
x = tfl.variable(circles, "x")
y = tfl.variable(circles, "y")
symmetric_formula = tfl.forall(
x, tfl.forall(y, tfl.and_n(inside(x, y), inside(y, x))))
symmetric_parsed = tfl.constraint(
"forall x: forall y: inside(x,y) and inside(y,x)")
assert np.equal(sess.run(symmetric_formula),
sess.run(symmetric_parsed))
def test_parser_and(self):
World.reset()
World._evaluation_mode = tfl.LOGIC_MODE
def inside(x, y):
centers_distance = tf.sqrt(
tf.reduce_sum(tf.squared_difference(x[:, 0:2], y[:, 0:2]),
axis=1) + 1e-6)
return tf.cast((centers_distance + x[:, 2]) < y[:, 2], tf.float32)
tfl.setTNorm(id=tfl.SS, p=1)
circles = tfl.Domain(label="Circles",
data=[[0., 0, 1], [0, 0, 2], [0, 0, 3]])
inside = tfl.Predicate(label="inside",
domains=["Circles", "Circles"],
function=inside)
x = tfl.variable(circles, "x")
y = tfl.variable(circles, "y")
a = tfl.atom(inside, (x, y))
b = tfl.atom(inside, (y, x))
f = tfl.and_n(a, b)
tensor = tfl.constraint("inside(x,y) and inside(y,x)")
sess = tf.Session()
assert np.equal(sess.run(tensor), sess.run(f)).all()
def test_slice_caching(self):
World.reset()
"""Checking caching mechanism works"""
# Program Model
nn = tfl.functions.FeedForwardNN(input_shape=[2], output_size=2)
images = tfl.Domain(label="Images", data=[[0., 0], [1, 1], [0.2, 0.3]])
zero = tfl.Predicate(label="zero",
domains=["Images"],
function=tfl.functions.Slice(nn, 0))
one = tfl.Predicate(label="one",
domains=["Images"],
function=tfl.functions.Slice(nn, 1))
close = tfl.Predicate(
label="close",
domains=["Images", "Images"],
function=lambda x: tf.reduce_sum(tf.abs(x[0] - x[1]), axis=1))
tfl.setTNorm(id=tfl.PRODUCT, p=None)
# Constraint 1
c1 = tfl.constraint("forall x: zero(x) and one(x) and one(y)")
def test_cache(self):
World.reset()
a = tf.zeros([10, 10])
print(a)
"""Checking caching mechanism works"""
# Program Model
nn1 = lambda x: tf.constant([0., 1, 0])
nn2 = lambda x: tf.constant([0., 0, 0])
images = tfl.Domain(label="Images", data=[[0., 0], [1, 1], [0.2, 0.3]])
zero = tfl.Predicate(label="zero", domains=["Images"], function=nn1)
one = tfl.Predicate(label="one", domains=["Images"], function=nn2)
close = tfl.Predicate(
label="close",
domains=["Images", "Images"],
function=lambda x, y: tf.reduce_sum(tf.abs(x - y), axis=1))
tfl.setTNorm(id=tfl.PRODUCT, p=None)
# Constraint 1
"zero(x) and one(y)"
x = tfl.variable(images)
y = tfl.variable(images)
a = tfl.atom(zero, (x, ))
b = tfl.atom(one, (y, ))
andd = tfl.and_n(a, b)
# Constraint 2
z = tfl.variable(images)
h = tfl.variable(images)
c = tfl.atom(zero, (z, ))
d = tfl.atom(one, (h, ))
papapa = tfl.and_n(c, d)
ab = tfl.atom(close, (x, y))
assert len(World._predicates_cache
) == 3 # one of zero, one for one and one for close
"horse": 7,
"ship": 8,
"truck": 9,
"onroad": 10,
"mammal": 11,
"otherleaves": 12,
"flies": 13,
"notflies": 14,
"animal": 15,
"transport": 16
})
tfl.World.reset()
tfl.World._evaluation_mode = tfl.LOSS_MODE
tfl.setTNorm(id=tfl.SS, p=1)
# Domains Definition
images = tfl.Domain("Images", data=x_final, size=minibatch_size)
# Predicates Definition
for k,v in predicates_dict.items():
tfl.Predicate(k, domains=("Images",), function=tfl.functions.Slice(cifar, v))
# Constraints
constraints = []
constraints.append(tfl.constraint("forall x: transport(x) <-> airplane(x) or ship(x) or onroad(x)"))
constraints.append(tfl.constraint("forall x: onroad(x) <-> automobile(x) or truck(x)"))
constraints.append(tfl.constraint("forall x: animal(x) <-> bird(x) or frog(x) or mammal(x)"))
constraints.append(tfl.constraint("forall x: mammal(x) <-> cat(x) or deer(x) or dog(x) or horse(x)"))