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
|
# Copyright 2018 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.
# ==============================================================================
"""Basic tests for TF-TensorRT integration."""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import numpy as np
from tensorflow.python.framework import constant_op
from tensorflow.python.framework import dtypes
from tensorflow.python.framework import ops
from tensorflow.python.ops import array_ops
from tensorflow.python.ops import nn
from tensorflow.python.ops import nn_ops
from tensorflow.python.platform import test
from tensorflow.contrib.tensorrt.test import tf_trt_integration_test_base as trt_test
# TODO(aaroey): test graph with different dtypes.
def _GetSingleEngineGraphDef(dtype=dtypes.float32):
"""Create a graph containing single segment."""
input_dims = [100, 24, 24, 2]
g = ops.Graph()
with g.as_default():
inp = array_ops.placeholder(
dtype=dtype, shape=[None] + input_dims[1:], name=trt_test.INPUT_NAME)
with g.device("/GPU:0"):
conv_filter = constant_op.constant(
[[[[1., 0.5, 4., 6., 0.5, 1.], [1., 0.5, 1., 1., 0.5, 1.]]]],
name="weights",
dtype=dtype)
conv = nn.conv2d(
input=inp,
filter=conv_filter,
strides=[1, 2, 2, 1],
padding="SAME",
name="conv")
bias = constant_op.constant(
[4., 1.5, 2., 3., 5., 7.], name="bias", dtype=dtype)
added = nn.bias_add(conv, bias, name="bias_add")
relu = nn.relu(added, "relu")
identity = array_ops.identity(relu, "identity")
pool = nn_ops.max_pool(
identity, [1, 2, 2, 1], [1, 2, 2, 1], "VALID", name="max_pool")
array_ops.squeeze(pool, name=trt_test.OUTPUT_NAME)
return trt_test.TfTrtIntegrationTestParams(
graph_name="SimpleSingleEngine",
gdef=g.as_graph_def(),
input_dims=input_dims,
num_expected_engines=1,
expected_output_dims=(100, 6, 6, 6),
allclose_atol=1.e-03,
allclose_rtol=1.e-03)
# TODO(aaroey): test graph with different dtypes.
def _GetMultiEngineGraphDef(dtype=dtypes.float32):
"""Create a graph containing multiple segment."""
input_dims = [100, 24, 24, 2]
g = ops.Graph()
with g.as_default():
inp = array_ops.placeholder(
dtype=dtype, shape=[None] + input_dims[1:], name=trt_test.INPUT_NAME)
with g.device("/GPU:0"):
conv_filter = constant_op.constant(
[[[[1., 0.5, 4., 6., 0.5, 1.], [1., 0.5, 1., 1., 0.5, 1.]]]],
name="weights",
dtype=dtype)
conv = nn.conv2d(
input=inp,
filter=conv_filter,
strides=[1, 2, 2, 1],
padding="SAME",
name="conv")
c1 = constant_op.constant(
np.random.randn(input_dims[0], 12, 12, 6), dtype=dtype)
p = conv * c1
c2 = constant_op.constant(
np.random.randn(input_dims[0], 12, 12, 6), dtype=dtype)
q = conv / c2
edge = trt_test.TRT_INCOMPATIBLE_OP(q)
edge /= edge
r = edge + edge
p -= edge
q *= edge
s = p + q
s -= r
array_ops.squeeze(s, name=trt_test.OUTPUT_NAME)
return trt_test.TfTrtIntegrationTestParams(
graph_name="SimpleMultipleEngines",
gdef=g.as_graph_def(),
input_dims=input_dims,
num_expected_engines=2,
expected_output_dims=(100, 12, 12, 6),
allclose_atol=1.e-03,
allclose_rtol=1.e-03)
class BaseTest(trt_test.TfTrtIntegrationTestBase):
"""Class to test Tensorflow-TensorRT integration."""
pass
if __name__ == "__main__":
# TODO(aaroey): add a large complex graph to test.
trt_test.AddTests(BaseTest,
[_GetSingleEngineGraphDef(),
_GetMultiEngineGraphDef()])
test.main()
|
