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
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
|
# 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.
# ==============================================================================
"""Tests for convolution related functionality in tensorflow.ops.nn."""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import numpy as np
from six.moves import xrange # pylint: disable=redefined-builtin
import tensorflow as tf
from tensorflow.python.client import device_lib
class Conv2DTransposeTest(tf.test.TestCase):
def testConv2DTransposeSingleStride(self):
with self.test_session():
strides = [1, 1, 1, 1]
# Input, output: [batch, height, width, depth]
x_shape = [2, 6, 4, 3]
y_shape = [2, 6, 4, 2]
# Filter: [kernel_height, kernel_width, output_depth, input_depth]
f_shape = [3, 3, 2, 3]
x = tf.constant(1.0, shape=x_shape, name="x", dtype=tf.float32)
f = tf.constant(1.0, shape=f_shape, name="filter", dtype=tf.float32)
output = tf.nn.conv2d_transpose(x, f, y_shape, strides=strides,
padding="SAME")
value = output.eval()
# We count the number of cells being added at the locations in the output.
# At the center, #cells=kernel_height * kernel_width
# At the corners, #cells=ceil(kernel_height/2) * ceil(kernel_width/2)
# At the borders, #cells=ceil(kernel_height/2)*kernel_width or
# kernel_height * ceil(kernel_width/2)
for n in xrange(x_shape[0]):
for k in xrange(f_shape[2]):
for w in xrange(y_shape[2]):
for h in xrange(y_shape[1]):
target = 4 * 3.0
h_in = h > 0 and h < y_shape[1] - 1
w_in = w > 0 and w < y_shape[2] - 1
if h_in and w_in:
target += 5 * 3.0
elif h_in or w_in:
target += 2 * 3.0
self.assertAllClose(target, value[n, h, w, k])
def testConv2DTransposeSame(self):
with self.test_session():
strides = [1, 2, 2, 1]
# Input, output: [batch, height, width, depth]
x_shape = [2, 6, 4, 3]
y_shape = [2, 12, 8, 2]
# Filter: [kernel_height, kernel_width, output_depth, input_depth]
f_shape = [3, 3, 2, 3]
x = tf.constant(1.0, shape=x_shape, name="x", dtype=tf.float32)
f = tf.constant(1.0, shape=f_shape, name="filter", dtype=tf.float32)
output = tf.nn.conv2d_transpose(x, f, y_shape, strides=strides,
padding="SAME")
value = output.eval()
for n in xrange(x_shape[0]):
for k in xrange(f_shape[2]):
for w in xrange(y_shape[2]):
for h in xrange(y_shape[1]):
target = 3.0
# We add a case for locations divisible by the stride.
h_in = h % strides[1] == 0 and h > 0 and h < y_shape[1] - 1
w_in = w % strides[2] == 0 and w > 0 and w < y_shape[2] - 1
if h_in and w_in:
target += 9.0
elif h_in or w_in:
target += 3.0
self.assertAllClose(target, value[n, h, w, k])
def testConv2DTransposeValid(self):
with self.test_session():
strides = [1, 2, 2, 1]
# Input, output: [batch, height, width, depth]
x_shape = [2, 6, 4, 3]
y_shape = [2, 13, 9, 2]
# Filter: [kernel_height, kernel_width, output_depth, input_depth]
f_shape = [3, 3, 2, 3]
x = tf.constant(1.0, shape=x_shape, name="x", dtype=tf.float32)
f = tf.constant(1.0, shape=f_shape, name="filter", dtype=tf.float32)
output = tf.nn.conv2d_transpose(x, f, y_shape, strides=strides,
padding="VALID")
value = output.eval()
cache_values = np.zeros(y_shape, dtype=np.float32)
# The amount of padding added
pad = 1
for n in xrange(x_shape[0]):
for k in xrange(f_shape[2]):
for w in xrange(pad, y_shape[2] - pad):
for h in xrange(pad, y_shape[1] - pad):
target = 3.0
# We add a case for locations divisible by the stride.
h_in = h % strides[
1] == 0 and h > pad and h < y_shape[1] - 1 - pad
w_in = w % strides[
2] == 0 and w > pad and w < y_shape[2] - 1 - pad
if h_in and w_in:
target += 9.0
elif h_in or w_in:
target += 3.0
cache_values[n, h, w, k] = target
# copy values in the border
cache_values[n, :, 0, k] = cache_values[n, :, 1, k]
cache_values[n, :, -1, k] = cache_values[n, :, -2, k]
cache_values[n, 0, :, k] = cache_values[n, 1, :, k]
cache_values[n, -1, :, k] = cache_values[n, -2, :, k]
self.assertAllClose(cache_values, value)
def testGradient(self):
x_shape = [2, 6, 4, 3]
f_shape = [3, 3, 2, 3]
y_shape = [2, 12, 8, 2]
strides = [1, 2, 2, 1]
np.random.seed(1) # Make it reproducible.
x_val = np.random.random_sample(x_shape).astype(np.float64)
f_val = np.random.random_sample(f_shape).astype(np.float64)
with self.test_session():
x = tf.constant(x_val, name="x", dtype=tf.float32)
f = tf.constant(f_val, name="f", dtype=tf.float32)
output = tf.nn.conv2d_transpose(x, f, y_shape, strides=strides,
padding="SAME")
err = tf.test.compute_gradient_error(
[x, f], [x_shape, f_shape], output, y_shape)
print("conv2d_transpose gradient err = %g " % err)
err_tolerance = 0.0005
self.assertLess(err, err_tolerance)
def testConv2DTransposeSingleStrideNCHW(self):
# `NCHW` data fomat is only supported for `GPU` device.
if tf.test.is_gpu_available():
with self.test_session(use_gpu=True):
strides = [1, 1, 1, 1]
# Input, output: [batch, depth, height, width, depth]
x_shape = [2, 3, 6, 4]
y_shape = [2, 2, 6, 4]
# Filter: [kernel_height, kernel_width, output_depth, input_depth]
f_shape = [3, 3, 2, 3]
x = tf.constant(1.0, shape=x_shape, name="x", dtype=tf.float32)
f = tf.constant(1.0, shape=f_shape, name="filter", dtype=tf.float32)
output = tf.nn.conv2d_transpose(x, f, y_shape, strides=strides,
padding="SAME", data_format='NCHW')
value = output.eval()
for n in xrange(x_shape[0]):
for k in xrange(f_shape[2]):
for w in xrange(y_shape[3]):
for h in xrange(y_shape[2]):
target = 4 * 3.0
h_in = h > 0 and h < y_shape[2] - 1
w_in = w > 0 and w < y_shape[3] - 1
if h_in and w_in:
target += 5 * 3.0
elif h_in or w_in:
target += 2 * 3.0
self.assertAllClose(target, value[n, k, h, w])
def testConv2DTransposeSameNCHW(self):
# `NCHW` data fomat is only supported for `GPU` device.
if tf.test.is_gpu_available():
with self.test_session(use_gpu=True):
strides = [1, 1, 2, 2]
# Input, output: [batch, depth, height, width]
x_shape = [2, 3, 6, 4]
y_shape = [2, 2, 12, 8]
# Filter: [kernel_height, kernel_width, output_depth, input_depth]
f_shape = [3, 3, 2, 3]
x = tf.constant(1.0, shape=x_shape, name="x", dtype=tf.float32)
f = tf.constant(1.0, shape=f_shape, name="filter", dtype=tf.float32)
output = tf.nn.conv2d_transpose(x, f, y_shape, strides=strides,
padding="SAME", data_format='NCHW')
value = output.eval()
for n in xrange(x_shape[0]):
for k in xrange(f_shape[2]):
for w in xrange(y_shape[3]):
for h in xrange(y_shape[2]):
target = 3.0
# We add a case for locations divisible by the stride.
h_in = h % strides[2] == 0 and h > 0 and h < y_shape[2] - 1
w_in = w % strides[3] == 0 and w > 0 and w < y_shape[3] - 1
if h_in and w_in:
target += 9.0
elif h_in or w_in:
target += 3.0
self.assertAllClose(target, value[n, k, h, w])
def testConv2DTransposeValidNCHW(self):
# `NCHW` data fomat is only supported for `GPU` device.
if tf.test.is_gpu_available():
with self.test_session(use_gpu=True):
strides = [1, 1, 2, 2]
# Input, output: [batch, depth, height, width]
x_shape = [2, 3, 6, 4]
y_shape = [2, 2, 13, 9]
# Filter: [kernel_height, kernel_width, output_depth, input_depth]
f_shape = [3, 3, 2, 3]
x = tf.constant(1.0, shape=x_shape, name="x", dtype=tf.float32)
f = tf.constant(1.0, shape=f_shape, name="filter", dtype=tf.float32)
output = tf.nn.conv2d_transpose(x, f, y_shape, strides=strides,
padding="VALID", data_format='NCHW')
value = output.eval()
cache_values = np.zeros(y_shape, dtype=np.float32)
# The amount of padding added
pad = 1
for n in xrange(x_shape[0]):
for k in xrange(f_shape[2]):
for w in xrange(pad, y_shape[3] - pad):
for h in xrange(pad, y_shape[2] - pad):
target = 3.0
# We add a case for locations divisible by the stride.
h_in = h % strides[
2] == 0 and h > pad and h < y_shape[2] - 1 - pad
w_in = w % strides[
3] == 0 and w > pad and w < y_shape[3] - 1 - pad
if h_in and w_in:
target += 9.0
elif h_in or w_in:
target += 3.0
cache_values[n, k, h, w] = target
# copy values in the border
cache_values[n, k, :, 0] = cache_values[n, k, :, 1]
cache_values[n, k, :, -1] = cache_values[n, k, :, -2]
cache_values[n, k, 0, :] = cache_values[n, k, 1, :]
cache_values[n, k, -1, :] = cache_values[n, k, -2, :]
self.assertAllClose(cache_values, value)
if __name__ == "__main__":
tf.test.main()
|
