def test_head_weights_wrong_size(self):
head1 = head_lib.multi_label_head(n_classes=2, name='head1')
head2 = head_lib.multi_label_head(n_classes=3, name='head2')
with self.assertRaisesRegexp(
ValueError,
r'heads and head_weights must have the same size\. '
r'Given len\(heads\): 2. Given len\(head_weights\): 1\.'):
multi_head_lib.multi_head([head1, head2], head_weights=[1.])
def test_train_create_loss_logits_tensor_wrong_shape(self):
"""Tests create_loss with logits Tensor of the wrong shape."""
weights1 = np.array([[1.], [2.]], dtype=np.float32)
weights2 = np.array([[2.], [3.]])
head1 = head_lib.multi_label_head(n_classes=2,
name='head1',
weight_column='weights1')
head2 = head_lib.multi_label_head(n_classes=3,
name='head2',
weight_column='weights2')
multi_head = multi_head_lib.multi_head([head1, head2],
head_weights=[1., 2.])
# logits tensor is 2x6 instead of 2x5
logits = np.array([[-10., 10., 20., -20., 20., 70.],
[-15., 10., -30., 20., -20., 80.]],
dtype=np.float32)
labels = {
'head1': np.array([[1, 0], [1, 1]], dtype=np.int64),
'head2': np.array([[0, 1, 0], [1, 1, 0]], dtype=np.int64),
}
with self.assertRaisesRegexp(ValueError, r'Could not split logits'):
multi_head.create_loss(features={
'x': np.array(((42, ), ), dtype=np.int32),
'weights1': weights1,
'weights2': weights2
},
mode=model_fn.ModeKeys.TRAIN,
logits=logits,
labels=labels)
def test_train_create_loss_logits_tensor_multi_dim(self):
"""Tests create_loss with multi-dimensional logits of shape [2, 2, 5]."""
head1 = head_lib.regression_head(label_dimension=2, name='head1')
head2 = head_lib.regression_head(label_dimension=3, name='head2')
multi_head = multi_head_lib.multi_head([head1, head2])
logits = np.array(
[[[-1., 1., 2., -2., 2.], [-1., 1., 2., -2., 2.]],
[[-1.5, 1.5, -2., 2., -2.], [-1.5, 1.5, -2., 2., -2.]]],
dtype=np.float32)
labels = {
'head1': np.array([[[1., 0.], [1., 0.]],
[[1.5, 1.5], [1.5, 1.5]]], dtype=np.float32),
'head2': np.array([[[0., 1., 0.], [0., 1., 0.]],
[[2., 2., 0.], [2., 2., 0.]]], dtype=np.float32),
}
# Loss for the first head:
# loss1 = ((1+1)^2 + (0-1)^2 + (1+1)^2 + (0-1)^2 +
# (1.5+1.5)^2 + (1.5-1.5)^2 + (1.5+1.5)^2 + (1.5-1.5)^2) / 8
# = 3.5
# Loss for the second head:
# loss2 = ((0-2)^2 + (1+2)^2 + (0-2)^2 + (0-2)^2 + (1+2)^2 + (0-2)^2 +
# (2+2)^2 + (2-2)^2 + (0+2)^2 + (2+2)^2 + (2-2)^2 + (0+2)^2) / 12
# = 6.167
expected_training_loss = 3.5 + 6.167
training_loss = multi_head.create_loss(
features={},
mode=model_fn.ModeKeys.TRAIN,
logits=logits,
labels=labels)[0]
tol = 1e-3
with self.cached_session():
self.assertAllClose(
expected_training_loss, training_loss.eval(), rtol=tol, atol=tol)
def test_train_one_head(self):
head1 = head_lib.multi_label_head(n_classes=2, name='head1')
multi_head = multi_head_lib.multi_head([head1])
logits = {
'head1': np.array([[-10., 10.], [-15., 10.]], dtype=np.float32)
}
labels = {'head1': np.array([[1, 0], [1, 1]], dtype=np.int64)}
# For large logits, sigmoid cross entropy loss is approximated as:
# loss = labels * (logits < 0) * (-logits) +
# (1 - labels) * (logits > 0) * logits =>
# expected_unweighted_loss = [[10., 10.], [15., 0.]]
# loss = ( (10 + 10) / 2 + (15 + 0) / 2 ) / 2 = 8.75
expected_loss = 8.75
expected_train_result = 'my_train_op'
def _train_op_fn(loss):
return string_ops.string_join([
constant_op.constant(expected_train_result),
string_ops.as_string(loss, precision=3)
])
spec = multi_head.create_estimator_spec(
features={'x': np.array(((42, ), ), dtype=np.int32)},
mode=model_fn.ModeKeys.TRAIN,
logits=logits,
labels=labels,
train_op_fn=_train_op_fn)
self.assertIsNotNone(spec.loss)
self.assertEqual({}, spec.eval_metric_ops)
self.assertIsNotNone(spec.train_op)
self.assertIsNone(spec.export_outputs)
_assert_no_hooks(self, spec)
# Assert predictions, loss, train_op, and summaries.
tol = 1e-3
with self.cached_session() as sess:
_initialize_variables(self, spec.scaffold)
self.assertIsNotNone(spec.scaffold.summary_op)
predictions = sess.run(spec.predictions)
self.assertAllClose(
logits['head1'],
predictions[('head1', prediction_keys.PredictionKeys.LOGITS)])
self.assertAllClose(
_sigmoid(logits['head1']),
predictions[('head1',
prediction_keys.PredictionKeys.PROBABILITIES)])
loss, train_result, summary_str = sess.run(
(spec.loss, spec.train_op, spec.scaffold.summary_op))
self.assertAllClose(expected_loss, loss, rtol=tol, atol=tol)
self.assertEqual(
six.b('{0:s}{1:.3f}'.format(expected_train_result,
expected_loss)), train_result)
_assert_simple_summaries(
self, {
metric_keys.MetricKeys.LOSS: expected_loss,
metric_keys.MetricKeys.LOSS + '/head1': expected_loss,
}, summary_str, tol)
def test_train_create_loss_logits_tensor(self):
"""Tests create_loss with logits Tensor."""
weights1 = np.array([[1.], [2.]], dtype=np.float32)
weights2 = np.array([[2.], [3.]])
head1 = head_lib.multi_label_head(n_classes=2,
name='head1',
weight_column='weights1')
head2 = head_lib.multi_label_head(n_classes=3,
name='head2',
weight_column='weights2')
multi_head = multi_head_lib.multi_head([head1, head2],
head_weights=[1., 2.])
logits = np.array(
[[-10., 10., 20., -20., 20.], [-15., 10., -30., 20., -20.]],
dtype=np.float32)
labels = {
'head1': np.array([[1, 0], [1, 1]], dtype=np.int64),
'head2': np.array([[0, 1, 0], [1, 1, 0]], dtype=np.int64),
}
training_loss, unreduced_losses, weights, _ = multi_head.create_loss(
features={
'x': np.array(((42, ), ), dtype=np.int32),
'weights1': weights1,
'weights2': weights2
},
mode=model_fn.ModeKeys.TRAIN,
logits=logits,
labels=labels)
tol = 1e-3
with self.cached_session():
# loss of the first head is [[(10 + 10) / 2], [(15 + 0) / 2]]
# = [10, 7.5]
# training_loss = (1 * 10 + 2 * 7.5) / 2 = 12.5
# head-weighted unreduced_loss = 1 * [10, 7.5]
self.assertAllClose([[10.], [7.5]],
unreduced_losses['head1'].eval(),
rtol=tol,
atol=tol)
# loss of the second head is [[(20 + 20 + 20) / 3], [(30 + 0 + 0) / 3]]
# = [20, 10]
# training_loss = (2 * 20 + 3 * 10) / 2 = 35
# head-weighted unreduced_loss = 2 * [20, 10]
self.assertAllClose([[40.], [20.]],
unreduced_losses['head2'].eval(),
rtol=tol,
atol=tol)
# head-weighted training_loss = 1 * 12.5 + 2 * 35 = 82.5
self.assertAllClose(82.5, training_loss.eval(), rtol=tol, atol=tol)
# head-weighted example weights
self.assertAllClose([[1.], [2.]],
weights['head1'].eval(),
rtol=tol,
atol=tol)
self.assertAllClose([[4.], [6.]],
weights['head2'].eval(),
rtol=tol,
atol=tol)
def test_predict_two_heads_logits_tensor(self):
"""Tests predict with logits as Tensor."""
head1 = head_lib.multi_label_head(n_classes=2, name='head1')
head2 = head_lib.multi_label_head(n_classes=3, name='head2')
multi_head = multi_head_lib.multi_head([head1, head2])
logits = np.array([[-1., 1., 2., -2., 2.], [-1.5, 1., -3., 2., -2.]],
dtype=np.float32)
expected_logits1 = np.array([[-1., 1.], [-1.5, 1.]], dtype=np.float32)
expected_logits2 = np.array([[2., -2., 2.], [-3., 2., -2.]],
dtype=np.float32)
expected_probabilities = {
'head1': _sigmoid(expected_logits1),
'head2': _sigmoid(expected_logits2),
}
spec = multi_head.create_estimator_spec(
features={'x': np.array(((42, ), ), dtype=np.int32)},
mode=model_fn.ModeKeys.PREDICT,
logits=logits)
self.assertItemsEqual(
(_DEFAULT_SERVING_KEY, 'predict', 'head1', 'head1/classification',
'head1/predict', 'head2', 'head2/classification',
'head2/predict'), spec.export_outputs.keys())
# Assert predictions and export_outputs.
with self.cached_session() as sess:
_initialize_variables(self, spec.scaffold)
self.assertIsNone(spec.scaffold.summary_op)
predictions = sess.run(spec.predictions)
self.assertAllClose(
expected_logits1,
predictions[('head1', prediction_keys.PredictionKeys.LOGITS)])
self.assertAllClose(
expected_logits2,
predictions[('head2', prediction_keys.PredictionKeys.LOGITS)])
self.assertAllClose(
expected_probabilities['head1'],
predictions[('head1',
prediction_keys.PredictionKeys.PROBABILITIES)])
self.assertAllClose(
expected_probabilities['head2'],
predictions[('head2',
prediction_keys.PredictionKeys.PROBABILITIES)])
self.assertAllClose(
expected_probabilities['head1'],
sess.run(spec.export_outputs[_DEFAULT_SERVING_KEY].scores))
self.assertAllClose(expected_probabilities['head1'],
sess.run(spec.export_outputs['head1'].scores))
self.assertAllClose(expected_probabilities['head2'],
sess.run(spec.export_outputs['head2'].scores))
def test_predict_two_heads_logits_tensor_multi_dim(self):
"""Tests predict with multi-dimensional logits of shape [2, 2, 5]."""
head1 = head_lib.regression_head(label_dimension=2, name='head1')
head2 = head_lib.regression_head(label_dimension=3, name='head2')
multi_head = multi_head_lib.multi_head([head1, head2])
logits = np.array(
[[[-1., 1., 2., -2., 2.], [-1., 1., 2., -2., 2.]],
[[-1.5, 1., -3., 2., -2.], [-1.5, 1., -3., 2., -2.]]],
dtype=np.float32)
expected_logits1 = np.array(
[[[-1., 1.], [-1., 1.]],
[[-1.5, 1.], [-1.5, 1.]]],
dtype=np.float32)
expected_logits2 = np.array(
[[[2., -2., 2.], [2., -2., 2.]],
[[-3., 2., -2.], [-3., 2., -2.]]],
dtype=np.float32)
spec = multi_head.create_estimator_spec(
features={'x': np.array(((42,),), dtype=np.int32)},
mode=model_fn.ModeKeys.PREDICT,
logits=logits)
self.assertItemsEqual(
(_DEFAULT_SERVING_KEY, 'predict', 'head1', 'head1/regression',
'head1/predict', 'head2', 'head2/regression', 'head2/predict'),
spec.export_outputs.keys())
# Assert predictions and export_outputs.
with self.cached_session() as sess:
_initialize_variables(self, spec.scaffold)
self.assertIsNone(spec.scaffold.summary_op)
predictions = sess.run(spec.predictions)
self.assertAllClose(
expected_logits1,
predictions[('head1', prediction_keys.PredictionKeys.PREDICTIONS)])
self.assertAllClose(
expected_logits2,
predictions[('head2', prediction_keys.PredictionKeys.PREDICTIONS)])
self.assertAllClose(
expected_logits1,
sess.run(spec.export_outputs[_DEFAULT_SERVING_KEY].value))
self.assertAllClose(
expected_logits1,
sess.run(spec.export_outputs['head1'].value))
self.assertAllClose(
expected_logits2,
sess.run(spec.export_outputs['head2'].value))
def test_train_create_loss_one_head(self):
head1 = head_lib.multi_label_head(n_classes=2, name='head1')
multi_head = multi_head_lib.multi_head([head1])
logits = {'head1': np.array([[-10., 10.], [-15., 10.]], dtype=np.float32)}
labels = {'head1': np.array([[1, 0], [1, 1]], dtype=np.int64)}
loss = multi_head.create_loss(
features={'x': np.array(((42,),), dtype=np.int32)},
mode=model_fn.ModeKeys.TRAIN,
logits=logits,
labels=labels)[0]
tol = 1e-3
with self.cached_session():
# Unreduced loss of the head is [[(10 + 10) / 2], (15 + 0) / 2]
# (averaged over classes, averaged over examples).
self.assertAllClose(8.75, loss.eval(), rtol=tol, atol=tol)
def test_train_one_head_with_optimizer(self):
head1 = head_lib.multi_label_head(n_classes=2, name='head1')
multi_head = multi_head_lib.multi_head([head1])
logits = {
'head1': np.array([[-10., 10.], [-15., 10.]], dtype=np.float32)
}
labels = {'head1': np.array([[1, 0], [1, 1]], dtype=np.int64)}
# For large logits, sigmoid cross entropy loss is approximated as:
# loss = labels * (logits < 0) * (-logits) +
# (1 - labels) * (logits > 0) * logits =>
# expected_unweighted_loss = [[10., 10.], [15., 0.]]
# loss = ( (10 + 10) / 2 + (15 + 0) / 2 ) / 2 = 8.75
expected_loss = 8.75
expected_train_result = 'my_train_op'
class _Optimizer(object):
def minimize(self, loss, global_step):
del global_step
return string_ops.string_join([
constant_op.constant(expected_train_result),
string_ops.as_string(loss, precision=3)
])
spec = multi_head.create_estimator_spec(
features={'x': np.array(((42, ), ), dtype=np.int32)},
mode=model_fn.ModeKeys.TRAIN,
logits=logits,
labels=labels,
optimizer=_Optimizer())
tol = 1e-3
with self.cached_session() as sess:
_initialize_variables(self, spec.scaffold)
predictions = sess.run(spec.predictions)
self.assertAllClose(
logits['head1'],
predictions[('head1', prediction_keys.PredictionKeys.LOGITS)])
self.assertAllClose(
_sigmoid(logits['head1']),
predictions[('head1',
prediction_keys.PredictionKeys.PROBABILITIES)])
loss, train_result = sess.run((spec.loss, spec.train_op))
self.assertAllClose(expected_loss, loss, rtol=tol, atol=tol)
self.assertEqual(
six.b('{0:s}{1:.3f}'.format(expected_train_result,
expected_loss)), train_result)
def test_train_create_loss_logits_tensor_multi_dim_wrong_shape(self):
"""Tests create_loss with a multi-dimensional logits tensor of wrong shape."""
head1 = head_lib.regression_head(label_dimension=2, name='head1')
head2 = head_lib.regression_head(label_dimension=3, name='head2')
multi_head = multi_head_lib.multi_head([head1, head2])
# logits tensor is 2x2x4 instead of 2x2x5
logits = np.array([[[-1., 1., 2., -2.], [-1., 1., 2., -2.]],
[[-1.5, 1.5, -2., 2.], [-1.5, 1.5, -2., 2.]]],
dtype=np.float32)
labels = {
'head1':
np.array([[[1., 0.], [1., 0.]], [[1.5, 1.5], [1.5, 1.5]]],
dtype=np.float32),
'head2':
np.array(
[[[0., 1., 0.], [0., 1., 0.]], [[2., 2., 0.], [2., 2., 0.]]],
dtype=np.float32),
}
with self.assertRaisesRegexp(ValueError, r'Could not split logits'):
multi_head.create_loss(features={},
mode=model_fn.ModeKeys.TRAIN,
logits=logits,
labels=labels)
def test_head_name_missing(self):
head1 = head_lib.multi_label_head(n_classes=2, name='head1')
head2 = head_lib.multi_label_head(n_classes=3)
with self.assertRaisesRegexp(
ValueError, r'All given heads must have name specified\.'):
multi_head_lib.multi_head([head1, head2])
def test_no_heads(self):
with self.assertRaisesRegexp(ValueError,
r'Must specify heads\. Given: \[\]'):
multi_head_lib.multi_head(heads=[])
def test_train_two_heads_with_weights(self):
head1 = head_lib.multi_label_head(n_classes=2, name='head1')
head2 = head_lib.multi_label_head(n_classes=3, name='head2')
multi_head = multi_head_lib.multi_head([head1, head2],
head_weights=[1., 2.])
logits = {
'head1':
np.array([[-10., 10.], [-15., 10.]], dtype=np.float32),
'head2':
np.array([[20., -20., 20.], [-30., 20., -20.]], dtype=np.float32),
}
labels = {
'head1': np.array([[1, 0], [1, 1]], dtype=np.int64),
'head2': np.array([[0, 1, 0], [1, 1, 0]], dtype=np.int64),
}
# For large logits, sigmoid cross entropy loss is approximated as:
# loss = labels * (logits < 0) * (-logits) +
# (1 - labels) * (logits > 0) * logits =>
# head1: expected_unweighted_loss = [[10., 10.], [15., 0.]]
# loss = ( (10 + 10) / 2 + (15 + 0) / 2 ) / 2 = 8.75
# head2: expected_unweighted_loss = [[20., 20., 20.], [30., 0., 0]]
# loss = ( (20 + 20 + 20) / 3 + (30 + 0 + 0) / 3 ) / 2 = 15
# Average over classes, weighted sum over batch and heads.
expected_loss_head1 = 8.75
expected_loss_head2 = 15.0
expected_loss = 1. * expected_loss_head1 + 2. * expected_loss_head2
expected_train_result = 'my_train_op'
def _train_op_fn(loss):
return string_ops.string_join([
constant_op.constant(expected_train_result),
string_ops.as_string(loss, precision=3)
])
spec = multi_head.create_estimator_spec(
features={'x': np.array(((42, ), ), dtype=np.int32)},
mode=model_fn.ModeKeys.TRAIN,
logits=logits,
labels=labels,
train_op_fn=_train_op_fn)
self.assertIsNotNone(spec.loss)
self.assertEqual({}, spec.eval_metric_ops)
self.assertIsNotNone(spec.train_op)
self.assertIsNone(spec.export_outputs)
_assert_no_hooks(self, spec)
# Assert predictions, loss, train_op, and summaries.
tol = 1e-3
with self.cached_session() as sess:
_initialize_variables(self, spec.scaffold)
self.assertIsNotNone(spec.scaffold.summary_op)
loss, train_result, summary_str = sess.run(
(spec.loss, spec.train_op, spec.scaffold.summary_op))
self.assertAllClose(expected_loss, loss, rtol=tol, atol=tol)
self.assertEqual(
six.b('{0:s}{1:.3f}'.format(expected_train_result,
expected_loss)), train_result)
_assert_simple_summaries(
self, {
metric_keys.MetricKeys.LOSS: expected_loss,
metric_keys.MetricKeys.LOSS + '/head1':
expected_loss_head1,
metric_keys.MetricKeys.LOSS + '/head2':
expected_loss_head2,
}, summary_str, tol)
def test_eval_two_heads_with_weights(self):
head1 = head_lib.multi_label_head(n_classes=2, name='head1')
head2 = head_lib.multi_label_head(n_classes=3, name='head2')
multi_head = multi_head_lib.multi_head([head1, head2],
head_weights=[1., 2.])
logits = {
'head1':
np.array([[-10., 10.], [-15., 10.]], dtype=np.float32),
'head2':
np.array([[20., -20., 20.], [-30., 20., -20.]], dtype=np.float32),
}
labels = {
'head1': np.array([[1, 0], [1, 1]], dtype=np.int64),
'head2': np.array([[0, 1, 0], [1, 1, 0]], dtype=np.int64),
}
# For large logits, sigmoid cross entropy loss is approximated as:
# loss = labels * (logits < 0) * (-logits) +
# (1 - labels) * (logits > 0) * logits =>
# head1: expected_unweighted_loss = [[10., 10.], [15., 0.]]
# loss = ( (10 + 10) / 2 + (15 + 0) / 2 ) / 2 = 8.75
# head2: expected_unweighted_loss = [[20., 20., 20.], [30., 0., 0]]
# loss = ( (20 + 20 + 20) / 3 + (30 + 0 + 0) / 3 ) / 2 = 15
expected_loss_head1 = 8.75
expected_loss_head2 = 15.
expected_loss = 1. * expected_loss_head1 + 2. * expected_loss_head2
spec = multi_head.create_estimator_spec(
features={'x': np.array(((42, ), ), dtype=np.int32)},
mode=model_fn.ModeKeys.EVAL,
logits=logits,
labels=labels)
keys = metric_keys.MetricKeys
expected_metrics = {
keys.LOSS + '/head1':
expected_loss_head1,
keys.LOSS + '/head2':
expected_loss_head2,
# Average loss over examples.
keys.LOSS_MEAN + '/head1':
expected_loss_head1,
keys.LOSS_MEAN + '/head2':
expected_loss_head2,
# auc and auc_pr cannot be reliably calculated for only 4-6 samples, but
# this assert tests that the algorithm remains consistent.
keys.AUC + '/head1':
0.1667,
keys.AUC + '/head2':
0.3333,
keys.AUC_PR + '/head1':
0.6667,
keys.AUC_PR + '/head2':
0.5000,
}
# Assert spec contains expected tensors.
self.assertIsNotNone(spec.loss)
self.assertItemsEqual(expected_metrics.keys(),
spec.eval_metric_ops.keys())
self.assertIsNone(spec.train_op)
self.assertIsNone(spec.export_outputs)
_assert_no_hooks(self, spec)
# Assert predictions, loss, and metrics.
tol = 1e-3
with self.cached_session() as sess:
_initialize_variables(self, spec.scaffold)
self.assertIsNone(spec.scaffold.summary_op)
value_ops = {
k: spec.eval_metric_ops[k][0]
for k in spec.eval_metric_ops
}
update_ops = {
k: spec.eval_metric_ops[k][1]
for k in spec.eval_metric_ops
}
loss, metrics = sess.run((spec.loss, update_ops))
self.assertAllClose(expected_loss, loss, rtol=tol, atol=tol)
# Check results of both update (in `metrics`) and value ops.
self.assertAllClose(expected_metrics, metrics, rtol=tol, atol=tol)
self.assertAllClose(expected_metrics,
{k: value_ops[k].eval()
for k in value_ops},
rtol=tol,
atol=tol)
def test_name(self):
head1 = head_lib.multi_label_head(n_classes=2, name='head1')
head2 = head_lib.multi_label_head(n_classes=3, name='head2')
multi_head = multi_head_lib.multi_head([head1, head2])
self.assertEqual('head1_head2', multi_head.name)
def simple_multi_head(export_path, eval_export_path):
"""Trains and exports a simple multi-headed model."""
def eval_input_receiver_fn():
"""Eval input receiver function."""
serialized_tf_example = tf.compat.v1.placeholder(
dtype=tf.string, shape=[None], name='input_example_tensor')
language = tf.feature_column.categorical_column_with_vocabulary_list(
'language', ['english', 'chinese', 'other'])
age = tf.feature_column.numeric_column('age')
english_label = tf.feature_column.numeric_column('english_label')
chinese_label = tf.feature_column.numeric_column('chinese_label')
other_label = tf.feature_column.numeric_column('other_label')
all_features = [age, language, english_label, chinese_label, other_label]
feature_spec = tf.feature_column.make_parse_example_spec(all_features)
receiver_tensors = {'examples': serialized_tf_example}
features = tf.io.parse_example(
serialized=serialized_tf_example, features=feature_spec)
labels = {
'english_head': features['english_label'],
'chinese_head': features['chinese_label'],
'other_head': features['other_label'],
}
return export.EvalInputReceiver(
features=features, receiver_tensors=receiver_tensors, labels=labels)
def input_fn():
"""Train input function."""
labels = {
'english_head': tf.constant([[1], [1], [0], [0], [0], [0]]),
'chinese_head': tf.constant([[0], [0], [1], [1], [0], [0]]),
'other_head': tf.constant([[0], [0], [0], [0], [1], [1]])
}
features = {
'age':
tf.constant([[1], [2], [3], [4], [5], [6]]),
'language':
tf.SparseTensor(
values=[
'english', 'english', 'chinese', 'chinese', 'other', 'other'
],
indices=[[0, 0], [1, 0], [2, 0], [3, 0], [4, 0], [5, 0]],
dense_shape=[6, 1]),
}
return features, labels
language = tf.feature_column.categorical_column_with_vocabulary_list(
'language', ['english', 'chinese', 'other'])
age = tf.feature_column.numeric_column('age')
all_features = [age, language]
feature_spec = tf.feature_column.make_parse_example_spec(all_features)
# TODO(b/130299739): Update with tf.estimator.BinaryClassHead and
# tf.estimator.MultiHead
english_head = head.binary_classification_head(name='english_head')
chinese_head = head.binary_classification_head(name='chinese_head')
other_head = head.binary_classification_head(name='other_head')
combined_head = multi_head.multi_head(
[english_head, chinese_head, other_head])
estimator = tf.estimator.DNNLinearCombinedEstimator(
head=combined_head,
dnn_feature_columns=[],
dnn_optimizer=tf.compat.v1.train.AdagradOptimizer(learning_rate=0.01),
dnn_hidden_units=[],
linear_feature_columns=[language, age],
linear_optimizer=tf.compat.v1.train.FtrlOptimizer(learning_rate=0.05))
estimator.train(input_fn=input_fn, steps=1000)
return util.export_model_and_eval_model(
estimator=estimator,
serving_input_receiver_fn=(
tf.estimator.export.build_parsing_serving_input_receiver_fn(
feature_spec)),
eval_input_receiver_fn=eval_input_receiver_fn,
export_path=export_path,
eval_export_path=eval_export_path)
