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(),
experimental_run_tf_function=testing_utils.
should_run_tf_function())
dnn_model.compile(optimizer='adam',
loss='mse',
metrics=[],
run_eagerly=testing_utils.should_run_eagerly(),
experimental_run_tf_function=testing_utils.
should_run_tf_function())
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(),
experimental_run_tf_function=testing_utils.
should_run_tf_function())
wide_deep_model.fit(inputs, output, epochs=50)
def test_wide_deep_model_with_multi_outputs(self):
with context.eager_mode():
inp = input_layer.Input(shape=(1, ), name='linear')
l = linear.LinearModel(units=2, use_bias=False)(inp)
l1, l2 = array_ops.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 = array_ops.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_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(),
experimental_run_tf_function=testing_utils.
should_run_tf_function())
model.fit([linear_input_np, dnn_input_np, input_b_np],
output_np,
epochs=5)
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 = fc.categorical_column_with_vocabulary_list(
key='symbol', vocabulary_list=vocab_list)
ind_column = fc.indicator_column(cat_column)
emb_column = fc.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(),
experimental_run_tf_function=testing_utils.
should_run_tf_function())
wide_deep_model.fit(x={'symbol': data}, y=y, batch_size=32, epochs=10)
self.assertEqual(3, linear_model.inputs[0].shape[1])
self.assertEqual(5, dnn_model.inputs[0].shape[1])
def test_linear_model_with_feature_column(self):
with context.eager_mode():
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 = fc.categorical_column_with_vocabulary_list(
key='symbol', vocabulary_list=vocab_list)
ind_column = fc.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_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(),
experimental_run_tf_function=testing_utils.
should_run_tf_function())
self.evaluate(variables.global_variables_initializer())
wide_deep_model.fit(inputs, output, epochs=1)
self.assertAllClose(
[[0.3]],
self.evaluate(
wide_deep_model.linear_model.dense_layers[0].kernel))
self.assertAllClose(
[[0.9]],
self.evaluate(wide_deep_model.dnn_model.layers[0].kernel))
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_linear_model_with_multi_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([input_a, input_b], output, epochs=5)
def test_train_premade_widedeep_model_with_feature_layers(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)
# TODO(tanzheny): use emb column for dense part once b/139667019 is fixed.
# emb_column = feature_column.embedding_column(cat_column, dimension=5)
keras_input = keras.layers.Input(name='symbol',
shape=3,
dtype=tf.dtypes.string)
# build linear part with feature layer.
linear_feature_layer = dense_features.DenseFeatures([ind_column])
linear_model = linear.LinearModel(units=1,
name='Linear',
kernel_initializer='zeros')
combined_linear = keras.Sequential(
[linear_feature_layer, linear_model])
# build dnn part with feature layer.
dnn_feature_layer = dense_features.DenseFeatures([ind_column])
dense_layer = keras.layers.Dense(units=1,
name='DNNDense',
kernel_initializer='zeros')
combined_dnn = keras.Sequential([dnn_feature_layer, dense_layer])
# build and compile wide deep.
wide_deep_model = wide_deep.WideDeepModel(combined_linear,
combined_dnn)
wide_deep_model._set_inputs({'symbol': keras_input})
sgd_opt = gradient_descent.SGD(0.1)
adam_opt = adam.Adam(0.1)
wide_deep_model.compile([sgd_opt, adam_opt], 'mse', ['mse'])
# build estimator.
train_input_fn = numpy_io.numpy_input_fn(x={'symbol': data},
y=y,
num_epochs=20,
shuffle=False)
eval_input_fn = numpy_io.numpy_input_fn(x={'symbol': data},
y=y,
num_epochs=20,
shuffle=False)
est = keras_lib.model_to_estimator(keras_model=wide_deep_model,
config=self._config,
checkpoint_format='saver')
before_eval_results = est.evaluate(input_fn=eval_input_fn, steps=1)
est.train(input_fn=train_input_fn, steps=20)
after_eval_results = est.evaluate(input_fn=eval_input_fn, steps=1)
self.assertLess(after_eval_results['loss'],
before_eval_results['loss'])
self.assertLess(after_eval_results['loss'], 0.1)
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_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': tensor_shape.TensorShape([None, 1]),
'b': tensor_shape.TensorShape([None, 1])})
with self.assertRaisesRegex(ValueError, 'Missing keys'):
model.fit({'c': input_a, 'b': input_b}, 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 == get_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_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_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_wide_deep_model(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', 'adam'],
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_linear_model_with_sparse_input(self):
indices = constant_op.constant([[0, 0], [0, 2], [1, 0], [1, 1]],
dtype=dtypes.int64)
values = constant_op.constant([.4, .6, .8, .5])
shape = constant_op.constant([2, 3], dtype=dtypes.int64)
model = linear.LinearModel()
inp = sparse_tensor.SparseTensor(indices, values, shape)
output = model(inp)
self.evaluate(variables.global_variables_initializer())
if context.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_train_premade_linear_model(self):
(x_train, y_train
), _, train_inp_fn, eval_inp_fn = get_resource_for_simple_model()
linear_model = linear.LinearModel(units=1)
opt = gradient_descent.SGD(0.1)
linear_model.compile(opt, 'mse', ['mse'])
linear_model.fit(x_train, y_train, epochs=10)
est = keras_lib.model_to_estimator(keras_model=linear_model,
config=self._config,
checkpoint_format='saver')
before_eval_results = est.evaluate(input_fn=eval_inp_fn, steps=1)
est.train(input_fn=train_inp_fn, steps=500)
after_eval_results = est.evaluate(input_fn=eval_inp_fn, steps=1)
self.assertLess(after_eval_results['loss'],
before_eval_results['loss'])
self.assertLess(after_eval_results['loss'], 0.1)
def test_linear_model_with_sparse_input_and_custom_training(self):
batch_size = 64
indices = []
values = []
target = np.zeros((batch_size, 1))
with context.eager_mode():
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 = constant_op.constant([batch_size, 2], dtype=dtypes.int64)
inp = sparse_tensor.SparseTensor(indices, values, shape)
model = linear.LinearModel(use_bias=False)
opt = gradient_descent.SGD()
for _ in range(20):
with backprop.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_train_premade_linear_model_with_dense_features(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)
keras_input = keras.layers.Input(name='symbol',
shape=3,
dtype=tf.dtypes.string)
feature_layer = dense_features.DenseFeatures([ind_column])
h = feature_layer({'symbol': keras_input})
linear_model = linear.LinearModel(units=1)
h = linear_model(h)
model = keras.Model(inputs=keras_input, outputs=h)
opt = gradient_descent.SGD(0.1)
model.compile(opt, 'mse', ['mse'])
train_input_fn = numpy_io.numpy_input_fn(x={'symbol': data},
y=y,
num_epochs=20,
shuffle=False)
eval_input_fn = numpy_io.numpy_input_fn(x={'symbol': data},
y=y,
num_epochs=20,
shuffle=False)
est = keras_lib.model_to_estimator(keras_model=model,
config=self._config,
checkpoint_format='saver')
before_eval_results = est.evaluate(input_fn=eval_input_fn, steps=1)
est.train(input_fn=train_input_fn, steps=30)
after_eval_results = est.evaluate(input_fn=eval_input_fn, steps=1)
self.assertLess(after_eval_results['loss'],
before_eval_results['loss'])
self.assertLess(after_eval_results['loss'], 0.05)
def test_wide_deep_model_with_single_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 = feature_column_v2.categorical_column_with_vocabulary_list(
key='symbol', vocabulary_list=vocab_list)
ind_column = feature_column_v2.indicator_column(cat_column)
dense_feature_layer = dense_features_v2.DenseFeatures([ind_column])
linear_model = linear.LinearModel(use_bias=False,
kernel_initializer='zeros')
dnn_model = keras.Sequential([keras.layers.Dense(units=1)])
wide_deep_model = wide_deep.WideDeepModel(linear_model, dnn_model)
combined = keras.Sequential([dense_feature_layer, wide_deep_model])
opt = gradient_descent.SGD(learning_rate=0.1)
combined.compile(opt,
'mse', [],
run_eagerly=testing_utils.should_run_eagerly())
combined.fit(x={'symbol': data}, y=y, batch_size=32, epochs=10)
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)
def test_linear_model_with_int_input(self):
inp = input_layer.Input(shape=(1, ), dtype=dtypes.int32)
with self.assertRaisesRegexp(TypeError, 'Unable to build'):
linear.LinearModel()(inp)
