def _get_multi_io_model():
inp_1 = layers.Input(shape=(1, ), name='input_1')
inp_2 = layers.Input(shape=(1, ), name='input_2')
d = testing_utils.Bias(name='output')
out_1 = d(inp_1)
out_2 = d(inp_2)
return keras.Model([inp_1, inp_2], [out_1, out_2])
def _get_simple_bias_model(self):
model = testing_utils.get_model_from_layers([testing_utils.Bias()],
input_shape=(1, ))
model.compile(keras.optimizer_v2.gradient_descent.SGD(0.1),
'mae',
run_eagerly=testing_utils.should_run_eagerly())
return model
def multi_input_functional():
"""Functional Model that adds its inputs and then adds a bias."""
input_1 = keras.Input(shape=(1, ))
input_2 = keras.Input(shape=(1, ))
input_3 = keras.Input(shape=(1, ))
added = keras.layers.Add()([input_1, input_2, input_3])
output = testing_utils.Bias()(added)
return keras.Model([input_1, input_2, input_3], output)
def test_invalid_variable_input(self):
inputs = Input(shape=(1,))
outputs = testing_utils.Bias()(inputs)
model = Model(inputs, outputs)
with self.assertRaisesRegex(
ValueError,
'Expected a symbolic Tensors or a callable for the loss value'):
model.add_loss(model.weights[0])
def get_model_and_train_step(): inputs = Input(shape=(1,)) targets = Input(shape=(1,)) outputs = testing_utils.Bias()(inputs) model = Model([inputs, targets], outputs) model.add_loss(MAE()(targets, outputs)) model.add_loss(tf.reduce_mean(mae(targets, outputs))) return get_ctl_train_step(model)
def test_add_entropy_loss_on_functional_model(self):
inputs = Input(shape=(1,))
targets = Input(shape=(1,))
outputs = testing_utils.Bias()(inputs)
model = Model([inputs, targets], outputs)
model.add_loss(losses.binary_crossentropy(targets, outputs))
model.compile('sgd', run_eagerly=testing_utils.should_run_eagerly())
with tf.compat.v1.test.mock.patch.object(logging, 'warning') as mock_log:
model.fit([self.x, self.y], batch_size=3, epochs=5)
self.assertNotIn('Gradients do not exist for variables',
str(mock_log.call_args))
def get_model_and_train_step():
inputs = Input(shape=(1,))
targets = Input(shape=(1,))
outputs = testing_utils.Bias()(inputs)
model = Model([inputs, targets], outputs)
def callable_loss():
return tf.reduce_sum(model.weights)
model.add_loss(callable_loss)
return get_ctl_train_step(model)
def test_loss_on_model_fit(self):
inputs = Input(shape=(1,))
targets = Input(shape=(1,))
outputs = testing_utils.Bias()(inputs)
model = Model([inputs, targets], outputs)
model.add_loss(MAE()(targets, outputs))
model.add_loss(tf.reduce_mean(mae(targets, outputs)))
model.compile(
optimizer_v2.gradient_descent.SGD(0.05),
run_eagerly=testing_utils.should_run_eagerly())
history = model.fit([self.x, self.y], batch_size=3, epochs=5)
self.assertAllClose(history.history['loss'], [2., 1.8, 1.6, 1.4, 1.2], 1e-3)
def test_loss_callable_on_model_fit(self):
model = testing_utils.get_model_from_layers([testing_utils.Bias()],
input_shape=(1,))
def callable_loss():
return tf.reduce_sum(model.weights)
model.add_loss(callable_loss)
model.compile(
optimizer_v2.gradient_descent.SGD(0.1),
run_eagerly=testing_utils.should_run_eagerly())
history = model.fit(self.x, batch_size=3, epochs=5)
self.assertAllClose(history.history['loss'], [0., -.1, -.2, -.3, -.4], 1e-3)
def test_loss_with_sample_weight_on_model_fit(self):
inputs = Input(shape=(1,))
targets = Input(shape=(1,))
sw = Input(shape=(1,))
outputs = testing_utils.Bias()(inputs)
model = Model([inputs, targets, sw], outputs)
model.add_loss(MAE()(targets, outputs, sw))
model.add_loss(3 * tf.reduce_mean(sw * mae(targets, outputs)))
model.compile(
optimizer_v2.gradient_descent.SGD(0.025),
run_eagerly=testing_utils.should_run_eagerly())
history = model.fit([self.x, self.y, self.w], batch_size=3, epochs=5)
self.assertAllClose(history.history['loss'], [4., 3.6, 3.2, 2.8, 2.4], 1e-3)
def __init__(self):
super(MultiInputSubclassed, self).__init__()
self.add = keras.layers.Add()
self.bias = testing_utils.Bias()
def __init__(self): super(MyLayer, self).__init__() self.bias = testing_utils.Bias()
