def test_wide_deep_model_with_sub_model_trained(self):
linear_model = linear.LinearModel(units=1)
dnn_model = sequential.Sequential([core.Dense(units=1, input_dim=3)])
wide_deep_model = wide_deep.WideDeepModel(
linear.LinearModel(units=1),
sequential.Sequential([core.Dense(units=1, input_dim=3)]))
linear_inp = np.random.uniform(low=-5, high=5, size=(64, 2))
dnn_inp = np.random.uniform(low=-5, high=5, size=(64, 3))
inputs = [linear_inp, dnn_inp]
output = .3 * linear_inp[:, 0] + .2 * dnn_inp[:, 1]
linear_model.compile(optimizer='sgd',
loss='mse',
metrics=[],
run_eagerly=testing_utils.should_run_eagerly())
dnn_model.compile(optimizer='adam',
loss='mse',
metrics=[],
run_eagerly=testing_utils.should_run_eagerly())
linear_model.fit(linear_inp, output, epochs=50)
dnn_model.fit(dnn_inp, output, epochs=50)
wide_deep_model.compile(optimizer=['sgd', 'adam'],
loss='mse',
metrics=[],
run_eagerly=testing_utils.should_run_eagerly())
wide_deep_model.fit(inputs, output, epochs=50)
def test_linear_model(self, distribution, use_dataset_creator, data_fn):
if ((not use_dataset_creator) and isinstance(
distribution,
tf.distribute.experimental.ParameterServerStrategy)):
self.skipTest(
'Parameter Server strategy requires dataset creator to be used in '
'model.fit.')
if (not tf.__internal__.tf2.enabled() and use_dataset_creator
and isinstance(
distribution,
tf.distribute.experimental.ParameterServerStrategy)):
self.skipTest(
'Parameter Server strategy with dataset creator needs to be run when '
'eager execution is enabled.')
with distribution.scope():
model = linear.LinearModel()
opt = gradient_descent.SGD(learning_rate=0.1)
model.compile(opt, 'mse')
if use_dataset_creator:
x = dataset_creator.DatasetCreator(dataset_fn)
hist = model.fit(x, epochs=5, steps_per_epoch=INPUT_SIZE)
else:
if data_fn == 'numpy':
inputs, output = get_numpy()
hist = model.fit(inputs, output, epochs=5)
else:
hist = model.fit(get_dataset(), epochs=5)
self.assertLess(hist.history['loss'][4], 0.2)
def test_linear_model_with_single_input(self):
model = linear.LinearModel()
inp = np.random.uniform(low=-5, high=5, size=(64, 2))
output = .3 * inp[:, 0] + .2 * inp[:, 1]
model.compile('sgd', 'mse', [])
model.fit(inp, output, epochs=5)
self.assertTrue(model.built)
def test_wide_deep_model_with_two_feature_columns(self):
vocab_list = ['alpha', 'beta', 'gamma']
vocab_val = [0.4, 0.6, 0.9]
data = np.random.choice(vocab_list, size=256)
y = np.zeros_like(data, dtype=np.float32)
for vocab, val in zip(vocab_list, vocab_val):
indices = np.where(data == vocab)
y[indices] = val + np.random.uniform(
low=-0.01, high=0.01, size=indices[0].shape)
cat_column = tf.feature_column.categorical_column_with_vocabulary_list(
key='symbol', vocabulary_list=vocab_list)
ind_column = tf.feature_column.indicator_column(cat_column)
emb_column = tf.feature_column.embedding_column(cat_column,
dimension=5)
linear_feature_layer = dense_features_v2.DenseFeatures([ind_column])
linear_model = linear.LinearModel(use_bias=False,
kernel_initializer='zeros')
combined_linear = sequential.Sequential(
[linear_feature_layer, linear_model])
dnn_model = sequential.Sequential([core.Dense(units=1)])
dnn_feature_layer = dense_features_v2.DenseFeatures([emb_column])
combined_dnn = sequential.Sequential([dnn_feature_layer, dnn_model])
wide_deep_model = wide_deep.WideDeepModel(combined_linear,
combined_dnn)
opt = gradient_descent.SGD(learning_rate=0.1)
wide_deep_model.compile(opt,
'mse', [],
run_eagerly=testing_utils.should_run_eagerly())
wide_deep_model.fit(x={'symbol': data}, y=y, batch_size=32, epochs=10)
def test_wide_deep_model_backprop(self):
with self.cached_session():
linear_model = linear.LinearModel(units=1,
kernel_initializer='zeros')
dnn_model = sequential.Sequential(
[core.Dense(units=1, kernel_initializer='zeros')])
wide_deep_model = wide_deep.WideDeepModel(linear_model, dnn_model)
linear_inp = np.array([1.])
dnn_inp = np.array([1.])
inputs = [linear_inp, dnn_inp]
output = linear_inp + 2 * dnn_inp
linear_opt = gradient_descent.SGD(learning_rate=.1)
dnn_opt = gradient_descent.SGD(learning_rate=.3)
wide_deep_model.compile(
optimizer=[linear_opt, dnn_opt],
loss='mse',
metrics=[],
run_eagerly=testing_utils.should_run_eagerly())
self.evaluate(tf.compat.v1.global_variables_initializer())
wide_deep_model.fit(inputs, output, epochs=1)
self.assertAllClose(
[[0.6]],
self.evaluate(
wide_deep_model.linear_model.dense_layers[0].kernel))
self.assertAllClose(
[[1.8]],
self.evaluate(wide_deep_model.dnn_model.layers[0].kernel))
def test_linear_model_with_dict_input(self):
model = linear.LinearModel()
input_a = np.random.uniform(low=-5, high=5, size=(64, 1))
input_b = np.random.uniform(low=-5, high=5, size=(64, 1))
output = .3 * input_a + .2 * input_b
model.compile('sgd', 'mse', [])
model.fit({'a': input_a, 'b': input_b}, output, epochs=5)
def test_wide_deep_model(self, distribution, use_dataset_creator, data_fn):
if ((not use_dataset_creator) and isinstance(
distribution,
tf.distribute.experimental.ParameterServerStrategy)):
self.skipTest(
'Parameter Server strategy requires dataset creator to be used in '
'model.fit.')
if (not tf.__internal__.tf2.enabled() and use_dataset_creator
and isinstance(
distribution,
tf.distribute.experimental.ParameterServerStrategy)):
self.skipTest(
'Parameter Server strategy with dataset creator needs to be run when '
'eager execution is enabled.')
with distribution.scope():
linear_model = linear.LinearModel(units=1)
dnn_model = sequential.Sequential([core.Dense(units=1)])
wide_deep_model = wide_deep.WideDeepModel(linear_model, dnn_model)
linear_opt = gradient_descent.SGD(learning_rate=0.05)
dnn_opt = adagrad.Adagrad(learning_rate=0.1)
wide_deep_model.compile(optimizer=[linear_opt, dnn_opt],
loss='mse')
if use_dataset_creator:
x = dataset_creator.DatasetCreator(dataset_fn)
hist = wide_deep_model.fit(x,
epochs=5,
steps_per_epoch=INPUT_SIZE)
else:
if data_fn == 'numpy':
inputs, output = get_numpy()
hist = wide_deep_model.fit(inputs, output, epochs=5)
else:
hist = wide_deep_model.fit(get_dataset(), epochs=5)
self.assertLess(hist.history['loss'][4], 0.2)
def test_config(self):
linear_model = linear.LinearModel(units=1)
dnn_model = sequential.Sequential([core.Dense(units=1, input_dim=3)])
wide_deep_model = wide_deep.WideDeepModel(linear_model, dnn_model)
config = wide_deep_model.get_config()
cloned_wide_deep_model = wide_deep.WideDeepModel.from_config(config)
self.assertEqual(linear_model.units,
cloned_wide_deep_model.linear_model.units)
self.assertEqual(dnn_model.layers[0].units,
cloned_wide_deep_model.dnn_model.layers[0].units)
def test_wide_deep_model_with_single_input(self):
linear_model = linear.LinearModel(units=1)
dnn_model = sequential.Sequential([core.Dense(units=1, input_dim=3)])
wide_deep_model = wide_deep.WideDeepModel(linear_model, dnn_model)
inputs = np.random.uniform(low=-5, high=5, size=(64, 3))
output = .3 * inputs[:, 0]
wide_deep_model.compile(optimizer=['sgd', 'adam'],
loss='mse',
metrics=[],
run_eagerly=testing_utils.should_run_eagerly())
wide_deep_model.fit(inputs, output, epochs=5)
def test_linear_model(self, distribution, data_fn):
with distribution.scope():
model = linear.LinearModel()
opt = gradient_descent.SGD(learning_rate=0.1)
model.compile(opt, 'mse')
if data_fn == 'numpy':
inputs, output = get_numpy()
hist = model.fit(inputs, output, epochs=5)
else:
hist = model.fit(get_dataset(), epochs=5)
self.assertLess(hist.history['loss'][4], 0.2)
def test_linear_model_with_mismatched_dict_inputs(self):
model = linear.LinearModel()
input_a = np.random.uniform(low=-5, high=5, size=(64, 1))
input_b = np.random.uniform(low=-5, high=5, size=(64, 1))
output = .3 * input_a + .2 * input_b
model.compile('sgd', 'mse', [])
model.build({
'a': tf.TensorShape([None, 1]),
'b': tf.TensorShape([None, 1])
})
with self.assertRaisesRegex(ValueError, 'Missing keys'):
model.fit({'c': input_a, 'b': input_b}, output, epochs=5)
def test_linear_model_as_layer(self):
input_a = input_layer.Input(shape=(1, ), name='a')
output_a = linear.LinearModel()(input_a)
input_b = input_layer.Input(shape=(1, ), name='b')
output_b = core.Dense(units=1)(input_b)
output = output_a + output_b
model = training.Model(inputs=[input_a, input_b], outputs=[output])
input_a_np = np.random.uniform(low=-5, high=5, size=(64, 1))
input_b_np = np.random.uniform(low=-5, high=5, size=(64, 1))
output_np = .3 * input_a_np + .2 * input_b_np
model.compile('sgd', 'mse', [])
model.fit([input_a_np, input_b_np], output_np, epochs=5)
def test_config_with_custom_objects(self):
def my_activation(x):
return x
linear_model = linear.LinearModel(units=1)
dnn_model = sequential.Sequential([core.Dense(units=1, input_dim=3)])
wide_deep_model = wide_deep.WideDeepModel(linear_model,
dnn_model,
activation=my_activation)
config = wide_deep_model.get_config()
cloned_wide_deep_model = wide_deep.WideDeepModel.from_config(
config, custom_objects={'my_activation': my_activation})
self.assertEqual(cloned_wide_deep_model.activation, my_activation)
def test_linear_model_with_sparse_input(self):
indices = tf.constant([[0, 0], [0, 2], [1, 0], [1, 1]], dtype=tf.int64)
values = tf.constant([.4, .6, .8, .5])
shape = tf.constant([2, 3], dtype=tf.int64)
model = linear.LinearModel()
inp = tf.SparseTensor(indices, values, shape)
output = model(inp)
self.evaluate(tf.compat.v1.global_variables_initializer())
if tf.executing_eagerly():
weights = model.get_weights()
weights[0] = np.ones((3, 1))
model.set_weights(weights)
output = model(inp)
self.assertAllClose([[1.], [1.3]], self.evaluate(output))
def test_wide_deep_model_with_single_optimizer(self):
linear_model = linear.LinearModel(units=1)
dnn_model = sequential.Sequential([core.Dense(units=1, input_dim=3)])
wide_deep_model = wide_deep.WideDeepModel(linear_model, dnn_model)
linear_inp = np.random.uniform(low=-5, high=5, size=(64, 2))
dnn_inp = np.random.uniform(low=-5, high=5, size=(64, 3))
inputs = [linear_inp, dnn_inp]
output = .3 * linear_inp[:, 0] + .2 * dnn_inp[:, 1]
wide_deep_model.compile(optimizer='sgd',
loss='mse',
metrics=[],
run_eagerly=testing_utils.should_run_eagerly())
wide_deep_model.fit(inputs, output, epochs=5)
self.assertTrue(wide_deep_model.built)
def test_wide_deep_model(self, distribution, data_fn):
with distribution.scope():
linear_model = linear.LinearModel(units=1)
dnn_model = sequential.Sequential([core.Dense(units=1)])
wide_deep_model = wide_deep.WideDeepModel(linear_model, dnn_model)
linear_opt = gradient_descent.SGD(learning_rate=0.05)
dnn_opt = adagrad.Adagrad(learning_rate=0.1)
wide_deep_model.compile(optimizer=[linear_opt, dnn_opt],
loss='mse')
if data_fn == 'numpy':
inputs, output = get_numpy()
hist = wide_deep_model.fit(inputs, output, epochs=5)
else:
hist = wide_deep_model.fit(get_dataset(), epochs=5)
self.assertLess(hist.history['loss'][4], 0.2)
def test_wide_deep_model_as_layer(self):
linear_model = linear.LinearModel(units=1)
dnn_model = sequential.Sequential([core.Dense(units=1)])
linear_input = input_layer.Input(shape=(3,), name='linear')
dnn_input = input_layer.Input(shape=(5,), name='dnn')
wide_deep_model = wide_deep.WideDeepModel(linear_model, dnn_model)
wide_deep_output = wide_deep_model((linear_input, dnn_input))
input_b = input_layer.Input(shape=(1,), name='b')
output_b = core.Dense(units=1)(input_b)
model = training.Model(
inputs=[linear_input, dnn_input, input_b],
outputs=[wide_deep_output + output_b])
linear_input_np = np.random.uniform(low=-5, high=5, size=(64, 3))
dnn_input_np = np.random.uniform(low=-5, high=5, size=(64, 5))
input_b_np = np.random.uniform(low=-5, high=5, size=(64,))
output_np = linear_input_np[:, 0] + .2 * dnn_input_np[:, 1] + input_b_np
model.compile(
optimizer='sgd',
loss='mse',
metrics=[],
run_eagerly=testing_utils.should_run_eagerly())
model.fit([linear_input_np, dnn_input_np, input_b_np], output_np, epochs=5)
def test_linear_model_with_feature_column(self):
vocab_list = ['alpha', 'beta', 'gamma']
vocab_val = [0.4, 0.6, 0.9]
data = np.random.choice(vocab_list, size=256)
y = np.zeros_like(data, dtype=np.float32)
for vocab, val in zip(vocab_list, vocab_val):
indices = np.where(data == vocab)
y[indices] = val + np.random.uniform(
low=-0.01, high=0.01, size=indices[0].shape)
cat_column = tf.feature_column.categorical_column_with_vocabulary_list(
key='symbol', vocabulary_list=vocab_list)
ind_column = tf.feature_column.indicator_column(cat_column)
dense_feature_layer = dense_features_v2.DenseFeatures([ind_column])
linear_model = linear.LinearModel(use_bias=False,
kernel_initializer='zeros')
combined = sequential.Sequential([dense_feature_layer, linear_model])
opt = gradient_descent.SGD(learning_rate=0.1)
combined.compile(opt, 'mse', [])
combined.fit(x={'symbol': data}, y=y, batch_size=32, epochs=10)
self.assertAllClose([[0.4], [0.6], [0.9]],
combined.layers[1].dense_layers[0].kernel.numpy(),
atol=0.01)
def test_linear_model_with_sparse_input_and_custom_training(self):
batch_size = 64
indices = []
values = []
target = np.zeros((batch_size, 1))
for i in range(64):
rand_int = np.random.randint(3)
if rand_int == 0:
indices.append((i, 0))
val = np.random.uniform(low=-5, high=5)
values.append(val)
target[i] = 0.3 * val
elif rand_int == 1:
indices.append((i, 1))
val = np.random.uniform(low=-5, high=5)
values.append(val)
target[i] = 0.2 * val
else:
indices.append((i, 0))
indices.append((i, 1))
val_1 = np.random.uniform(low=-5, high=5)
val_2 = np.random.uniform(low=-5, high=5)
values.append(val_1)
values.append(val_2)
target[i] = 0.3 * val_1 + 0.2 * val_2
indices = np.asarray(indices)
values = np.asarray(values)
shape = tf.constant([batch_size, 2], dtype=tf.int64)
inp = tf.SparseTensor(indices, values, shape)
model = linear.LinearModel(use_bias=False)
opt = gradient_descent.SGD()
for _ in range(20):
with tf.GradientTape() as t:
output = model(inp)
loss = backend.mean(losses.mean_squared_error(target, output))
grads = t.gradient(loss, model.trainable_variables)
grads_and_vars = zip(grads, model.trainable_variables)
opt.apply_gradients(grads_and_vars)
def test_wide_deep_model_with_multi_outputs(self):
inp = input_layer.Input(shape=(1,), name='linear')
l = linear.LinearModel(units=2, use_bias=False)(inp)
l1, l2 = tf.split(l, num_or_size_splits=2, axis=1)
linear_model = training.Model(inp, [l1, l2])
linear_model.set_weights([np.asarray([[0.5, 0.3]])])
h = core.Dense(units=2, use_bias=False)(inp)
h1, h2 = tf.split(h, num_or_size_splits=2, axis=1)
dnn_model = training.Model(inp, [h1, h2])
dnn_model.set_weights([np.asarray([[0.1, -0.5]])])
wide_deep_model = wide_deep.WideDeepModel(linear_model, dnn_model)
inp_np = np.asarray([[1.]])
out1, out2 = wide_deep_model(inp_np)
# output should be (0.5 + 0.1), and (0.3 - 0.5)
self.assertAllClose([[0.6]], out1)
self.assertAllClose([[-0.2]], out2)
wide_deep_model = wide_deep.WideDeepModel(
linear_model, dnn_model, activation='relu')
out1, out2 = wide_deep_model(inp_np)
# output should be relu((0.5 + 0.1)), and relu((0.3 - 0.5))
self.assertAllClose([[0.6]], out1)
self.assertAllClose([[0.]], out2)
def test_config(self):
linear_model = linear.LinearModel(units=3, use_bias=True)
config = linear_model.get_config()
cloned_linear_model = linear.LinearModel.from_config(config)
self.assertEqual(linear_model.units, cloned_linear_model.units)
