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
|
# Copyright 2015 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.
# ==============================================================================
"""GradientDescent for TensorFlow."""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
from tensorflow.python.framework import ops
from tensorflow.python.ops import math_ops
from tensorflow.python.ops import resource_variable_ops
from tensorflow.python.training import optimizer
from tensorflow.python.training import training_ops
from tensorflow.python.util.tf_export import tf_export
@tf_export("train.GradientDescentOptimizer")
class GradientDescentOptimizer(optimizer.Optimizer):
"""Optimizer that implements the gradient descent algorithm.
"""
def __init__(self, learning_rate, use_locking=False, name="GradientDescent"):
"""Construct a new gradient descent optimizer.
Args:
learning_rate: A Tensor or a floating point value. The learning
rate to use.
use_locking: If True use locks for update operations.
name: Optional name prefix for the operations created when applying
gradients. Defaults to "GradientDescent".
@compatibility(eager)
When eager execution is enabled, `learning_rate` can be a callable that
takes no arguments and returns the actual value to use. This can be useful
for changing these values across different invocations of optimizer
functions.
@end_compatibility
"""
super(GradientDescentOptimizer, self).__init__(use_locking, name)
self._learning_rate = learning_rate
self._learning_rate_tensor = None
def _apply_dense(self, grad, var):
return training_ops.apply_gradient_descent(
var,
math_ops.cast(self._learning_rate_tensor, var.dtype.base_dtype),
grad,
use_locking=self._use_locking).op
def _resource_apply_dense(self, grad, handle):
return training_ops.resource_apply_gradient_descent(
handle.handle, math_ops.cast(self._learning_rate_tensor,
grad.dtype.base_dtype),
grad, use_locking=self._use_locking)
def _resource_apply_sparse_duplicate_indices(self, grad, handle, indices):
return resource_variable_ops.resource_scatter_add(
handle.handle, indices, -grad * self._learning_rate)
def _apply_sparse_duplicate_indices(self, grad, var):
delta = ops.IndexedSlices(
grad.values *
math_ops.cast(self._learning_rate_tensor, var.dtype.base_dtype),
grad.indices, grad.dense_shape)
return var.scatter_sub(delta, use_locking=self._use_locking)
def _prepare(self):
learning_rate = self._call_if_callable(self._learning_rate)
self._learning_rate_tensor = ops.convert_to_tensor(
learning_rate, name="learning_rate")
|
