def test_summary(self):
class ToString:
def __init__(self):
self.contents = ''
def __call__(self, msg):
self.contents += msg + '\n'
# Single-io
model = test_utils.SmallSubclassMLP(
num_hidden=32, num_classes=4, use_bn=True, use_dp=True)
model(np.ones((3, 4))) # need to build model first
print_fn = ToString()
model.summary(print_fn=print_fn)
self.assertIn('Trainable params: 356', print_fn.contents)
# Multi-io
model = model_util.get_multi_io_subclass_model(
num_classes=(5, 6), use_bn=True, use_dp=True)
model([np.ones((3, 4)), np.ones((3, 4))]) # need to build model first
print_fn = ToString()
model.summary(print_fn=print_fn)
self.assertIn('Trainable params: 587', print_fn.contents)
# Single-io with unused layer
model = test_utils.SmallSubclassMLP(
num_hidden=32, num_classes=4, use_bn=True, use_dp=True)
model.unused_layer = keras.layers.Dense(10)
model(np.ones((3, 4))) # need to build model first
print_fn = ToString()
model.summary(print_fn=print_fn)
self.assertIn('Trainable params: 356', print_fn.contents)
self.assertIn('0 (unused)', print_fn.contents)
def test_single_io_dimension_subclass_build(self):
num_classes = 2
input_dim = tf.compat.v1.Dimension(50)
batch_size = tf.compat.v1.Dimension(None)
model = test_utils.SmallSubclassMLP(
num_hidden=32, num_classes=num_classes, use_dp=True, use_bn=True
)
self.assertFalse(model.built, "Model should not have been built")
self.assertFalse(
model.weights,
("Model should have no weights since it " "has not been built."),
)
model.build(input_shape=(batch_size, input_dim))
self.assertTrue(
model.weights,
(
"Model should have weights now that it "
"has been properly built."
),
)
self.assertTrue(
model.built, "Model should be built after calling `build`."
)
model(tf.ones((32, input_dim)))
def __init__(self, num_classes=2):
super().__init__(name="nested_model_1")
self.num_classes = num_classes
self.dense1 = keras.layers.Dense(32, activation="relu")
self.dense2 = keras.layers.Dense(num_classes, activation="relu")
self.bn = keras.layers.BatchNormalization()
self.test_net = test_utils.SmallSubclassMLP(
num_hidden=32, num_classes=4, use_bn=True, use_dp=True
)
def test_invalid_input_shape_build(self):
num_classes = 2
input_dim = 50
model = test_utils.SmallSubclassMLP(
num_hidden=32, num_classes=num_classes, use_dp=True, use_bn=True)
self.assertFalse(model.built, 'Model should not have been built')
self.assertFalse(model.weights, ('Model should have no weights since it '
'has not been built.'))
with self.assertRaisesRegex(ValueError,
'input shape is not one of the valid types'):
model.build(input_shape=tf.compat.v1.Dimension(input_dim))
def test_single_io_workflow_with_tensors(self):
num_classes = 2
num_samples = 10
input_dim = 50
with tf.Graph().as_default(), self.cached_session():
model = test_utils.SmallSubclassMLP(
num_hidden=32, num_classes=num_classes, use_dp=True, use_bn=True)
model.compile(loss='mse', optimizer='rmsprop')
x = tf.ones((num_samples, input_dim))
y = tf.zeros((num_samples, num_classes))
model.fit(x, y, epochs=2, steps_per_epoch=10, verbose=0)
_ = model.evaluate(steps=10, verbose=0)
def test_single_io_subclass_build(self):
num_classes = 2
input_dim = 50
batch_size = None
model = test_utils.SmallSubclassMLP(
num_hidden=32, num_classes=num_classes, use_dp=True, use_bn=True)
self.assertFalse(model.built, 'Model should not have been built')
self.assertFalse(model.weights, ('Model should have no weights since it '
'has not been built.'))
model.build(input_shape=(batch_size, input_dim))
self.assertTrue(model.weights, ('Model should have weights now that it '
'has been properly built.'))
self.assertTrue(model.built, 'Model should be built after calling `build`.')
model(tf.ones((32, input_dim)))
def test_single_io_workflow_with_np_arrays(self):
num_classes = 2
num_samples = 100
input_dim = 50
model = test_utils.SmallSubclassMLP(num_hidden=32,
num_classes=num_classes,
use_dp=True,
use_bn=True)
model.compile(loss='mse',
optimizer='rmsprop',
metrics=['acc',
keras.metrics.CategoricalAccuracy()],
run_eagerly=test_utils.should_run_eagerly())
x = np.ones((num_samples, input_dim))
y = np.zeros((num_samples, num_classes))
model.fit(x, y, epochs=2, batch_size=32, verbose=0)
_ = model.evaluate(x, y, verbose=0)
def test_single_io_workflow_with_datasets(self):
num_classes = 2
num_samples = 10
input_dim = 50
with self.cached_session():
model = test_utils.SmallSubclassMLP(num_hidden=32,
num_classes=num_classes,
use_dp=True,
use_bn=True)
model.compile(loss='mse',
optimizer='rmsprop',
run_eagerly=test_utils.should_run_eagerly())
x = np.ones((num_samples, input_dim), dtype=np.float32)
y = np.zeros((num_samples, num_classes), dtype=np.float32)
dataset = tf.data.Dataset.from_tensor_slices((x, y))
dataset = dataset.repeat(100)
dataset = dataset.batch(10)
model.fit(dataset, epochs=2, steps_per_epoch=10, verbose=0)
_ = model.evaluate(dataset, steps=10, verbose=0)
