1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
|
# Copyright 2017 The TensorFlow Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ==============================================================================
"""Deep Neural Network estimators."""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
from tensorflow.python.estimator import estimator
from tensorflow.python.estimator.canned import dnn as dnn_lib
from tensorflow.python.ops import nn
class DNNEstimator(estimator.Estimator):
"""An estimator for TensorFlow DNN models with user-specified head.
Example:
```python
sparse_feature_a = sparse_column_with_hash_bucket(...)
sparse_feature_b = sparse_column_with_hash_bucket(...)
sparse_feature_a_emb = embedding_column(sparse_id_column=sparse_feature_a,
...)
sparse_feature_b_emb = embedding_column(sparse_id_column=sparse_feature_b,
...)
estimator = DNNEstimator(
head=tf.contrib.estimator.multi_label_head(n_classes=3),
feature_columns=[sparse_feature_a_emb, sparse_feature_b_emb],
hidden_units=[1024, 512, 256])
# Or estimator using the ProximalAdagradOptimizer optimizer with
# regularization.
estimator = DNNEstimator(
head=tf.contrib.estimator.multi_label_head(n_classes=3),
feature_columns=[sparse_feature_a_emb, sparse_feature_b_emb],
hidden_units=[1024, 512, 256],
optimizer=tf.train.ProximalAdagradOptimizer(
learning_rate=0.1,
l1_regularization_strength=0.001
))
# Or estimator using an optimizer with a learning rate decay.
estimator = DNNEstimator(
head=tf.contrib.estimator.multi_label_head(n_classes=3),
feature_columns=[sparse_feature_a_emb, sparse_feature_b_emb],
hidden_units=[1024, 512, 256],
optimizer=lambda: tf.AdamOptimizer(
learning_rate=tf.exponential_decay(
learning_rate=0.1,
global_step=tf.get_global_step(),
decay_steps=10000,
decay_rate=0.96))
# Or estimator with warm-starting from a previous checkpoint.
estimator = DNNEstimator(
head=tf.contrib.estimator.multi_label_head(n_classes=3),
feature_columns=[sparse_feature_a_emb, sparse_feature_b_emb],
hidden_units=[1024, 512, 256],
warm_start_from="/path/to/checkpoint/dir")
# Input builders
def input_fn_train: # returns x, y
pass
estimator.train(input_fn=input_fn_train, steps=100)
def input_fn_eval: # returns x, y
pass
metrics = estimator.evaluate(input_fn=input_fn_eval, steps=10)
def input_fn_predict: # returns x, None
pass
predictions = estimator.predict(input_fn=input_fn_predict)
```
Input of `train` and `evaluate` should have following features,
otherwise there will be a `KeyError`:
* if `weight_column` is not `None`, a feature with
`key=weight_column` whose value is a `Tensor`.
* for each `column` in `feature_columns`:
- if `column` is a `_CategoricalColumn`, a feature with `key=column.name`
whose `value` is a `SparseTensor`.
- if `column` is a `_WeightedCategoricalColumn`, two features: the first
with `key` the id column name, the second with `key` the weight column
name. Both features' `value` must be a `SparseTensor`.
- if `column` is a `_DenseColumn`, a feature with `key=column.name`
whose `value` is a `Tensor`.
Loss and predicted output are determined by the specified head.
"""
def __init__(self,
head,
hidden_units,
feature_columns,
model_dir=None,
optimizer='Adagrad',
activation_fn=nn.relu,
dropout=None,
input_layer_partitioner=None,
config=None,
warm_start_from=None):
"""Initializes a `DNNEstimator` instance.
Args:
head: A `_Head` instance constructed with a method such as
`tf.contrib.estimator.multi_label_head`.
hidden_units: Iterable of number hidden units per layer. All layers are
fully connected. Ex. `[64, 32]` means first layer has 64 nodes and
second one has 32.
feature_columns: An iterable containing all the feature columns used by
the model. All items in the set should be instances of classes derived
from `_FeatureColumn`.
model_dir: Directory to save model parameters, graph and etc. This can
also be used to load checkpoints from the directory into a estimator to
continue training a previously saved model.
optimizer: An instance of `tf.Optimizer` used to train the model. Can also
be a string (one of 'Adagrad', 'Adam', 'Ftrl', 'RMSProp', 'SGD'), or
callable. Defaults to Adagrad optimizer.
activation_fn: Activation function applied to each layer. If `None`, will
use `tf.nn.relu`.
dropout: When not `None`, the probability we will drop out a given
coordinate.
input_layer_partitioner: Optional. Partitioner for input layer. Defaults
to `min_max_variable_partitioner` with `min_slice_size` 64 << 20.
config: `RunConfig` object to configure the runtime settings.
warm_start_from: A string filepath to a checkpoint to warm-start from, or
a `WarmStartSettings` object to fully configure warm-starting. If the
string filepath is provided instead of a `WarmStartSettings`, then all
weights are warm-started, and it is assumed that vocabularies and Tensor
names are unchanged.
"""
def _model_fn(features, labels, mode, config):
return dnn_lib._dnn_model_fn( # pylint: disable=protected-access
features=features,
labels=labels,
mode=mode,
head=head,
hidden_units=hidden_units,
feature_columns=tuple(feature_columns or []),
optimizer=optimizer,
activation_fn=activation_fn,
dropout=dropout,
input_layer_partitioner=input_layer_partitioner,
config=config)
super(DNNEstimator, self).__init__(
model_fn=_model_fn, model_dir=model_dir, config=config,
warm_start_from=warm_start_from)
|
