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
|
# Copyright 2016 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.
"""Example of using Estimator with multiple GPUs to distribute one model.
This example only runs if you have multiple GPUs to assign to.
"""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import numpy as np
from sklearn import datasets
from sklearn import metrics
from sklearn import model_selection
import tensorflow as tf
X_FEATURE = 'x' # Name of the input feature.
def my_model(features, labels, mode):
"""DNN with three hidden layers, and dropout of 0.1 probability.
Note: If you want to run this example with multiple GPUs, Cuda Toolkit 7.0 and
CUDNN 6.5 V2 from NVIDIA need to be installed beforehand.
Args:
features: Dict of input `Tensor`.
labels: Label `Tensor`.
mode: One of `ModeKeys`.
Returns:
`EstimatorSpec`.
"""
# Create three fully connected layers respectively of size 10, 20, and 10 with
# each layer having a dropout probability of 0.1.
net = features[X_FEATURE]
with tf.device('/device:GPU:1'):
for units in [10, 20, 10]:
net = tf.layers.dense(net, units=units, activation=tf.nn.relu)
net = tf.layers.dropout(net, rate=0.1)
with tf.device('/device:GPU:2'):
# Compute logits (1 per class).
logits = tf.layers.dense(net, 3, activation=None)
# Compute predictions.
predicted_classes = tf.argmax(logits, 1)
if mode == tf.estimator.ModeKeys.PREDICT:
predictions = {
'class': predicted_classes,
'prob': tf.nn.softmax(logits)
}
return tf.estimator.EstimatorSpec(mode, predictions=predictions)
# Compute loss.
loss = tf.losses.sparse_softmax_cross_entropy(labels=labels, logits=logits)
# Create training op.
if mode == tf.estimator.ModeKeys.TRAIN:
optimizer = tf.train.AdagradOptimizer(learning_rate=0.1)
train_op = optimizer.minimize(
loss, global_step=tf.train.get_global_step())
return tf.estimator.EstimatorSpec(mode, loss=loss, train_op=train_op)
# Compute evaluation metrics.
eval_metric_ops = {
'accuracy': tf.metrics.accuracy(
labels=labels, predictions=predicted_classes)
}
return tf.estimator.EstimatorSpec(
mode, loss=loss, eval_metric_ops=eval_metric_ops)
def main(unused_argv):
iris = datasets.load_iris()
x_train, x_test, y_train, y_test = model_selection.train_test_split(
iris.data, iris.target, test_size=0.2, random_state=42)
classifier = tf.estimator.Estimator(model_fn=my_model)
# Train.
train_input_fn = tf.estimator.inputs.numpy_input_fn(
x={X_FEATURE: x_train}, y=y_train, num_epochs=None, shuffle=True)
classifier.train(input_fn=train_input_fn, steps=100)
# Predict.
test_input_fn = tf.estimator.inputs.numpy_input_fn(
x={X_FEATURE: x_test}, y=y_test, num_epochs=1, shuffle=False)
predictions = classifier.predict(input_fn=test_input_fn)
y_predicted = np.array(list(p['class'] for p in predictions))
y_predicted = y_predicted.reshape(np.array(y_test).shape)
# Score with sklearn.
score = metrics.accuracy_score(y_test, y_predicted)
print('Accuracy (sklearn): {0:f}'.format(score))
# Score with tensorflow.
scores = classifier.evaluate(input_fn=test_input_fn)
print('Accuracy (tensorflow): {0:f}'.format(scores['accuracy']))
if __name__ == '__main__':
tf.app.run()
|
