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
|
import unittest
import hypothesis.strategies as st
from hypothesis import given, settings
import numpy as np
from caffe2.proto import caffe2_pb2
from caffe2.python import core, workspace
from caffe2.python.transformations import optimizeForMKLDNN
import caffe2.python.hypothesis_test_util as hu
import caffe2.python.ideep_test_util as mu
@unittest.skipIf(not workspace.C.use_mkldnn, "No MKLDNN support.")
class ConvTest(hu.HypothesisTestCase):
@given(stride=st.integers(1, 3),
pad=st.integers(0, 3),
kernel=st.integers(3, 5),
size=st.integers(8, 10),
input_channels=st.integers(1, 3),
output_channels=st.integers(1, 5),
batch_size=st.integers(1, 3),
use_bias=st.booleans(),
training_mode=st.booleans(),
group=st.integers(1, 2),
**mu.gcs)
@settings(max_examples=10, deadline=None)
def test_convolution(self, stride, pad, kernel, size,
input_channels, output_channels,
batch_size, use_bias, training_mode, group, gc, dc):
training = 1 if training_mode else 0
op = core.CreateOperator(
"Conv",
["X", "w", "b"] if use_bias else ["X", "w"],
["Y"],
stride=stride,
pad=pad,
kernel=kernel,
group=group,
training_mode=training,
)
X = np.random.rand(
batch_size, input_channels * group, size, size).astype(np.float32) - 0.5
w = np.random.rand(output_channels * group, input_channels, kernel, kernel) \
.astype(np.float32) - 0.5
b = np.random.rand(output_channels * group).astype(np.float32) - 0.5
inputs = [X, w, b] if use_bias else [X, w]
self.assertDeviceChecks(dc, op, inputs, [0])
if training_mode:
for i in range(len(inputs)):
self.assertGradientChecks(gc, op, inputs, i, [0], threshold=0.01)
@settings(max_examples=10, deadline=None)
@given(stride=st.integers(1, 3),
pad=st.integers(0, 3),
size=st.integers(8, 10),
input_channels=st.integers(16, 32),
output_channels=st.integers(16, 32),
batch_size=st.integers(1, 3),
use_bias=st.booleans(),
training_mode=st.booleans(),
**mu.gcs)
def test_winograd_convolution(self, stride, pad, size,
input_channels, output_channels,
batch_size, use_bias, training_mode, gc, dc):
training = 1 if training_mode else 0
conv3x3_winograd_algorithm = 1
kernel = 3
op = core.CreateOperator(
"Conv",
["X", "w", "b"] if use_bias else ["X", "w"],
["Y"],
stride=stride,
pad=pad,
kernel=kernel,
training_mode=training,
algorithm=conv3x3_winograd_algorithm
)
X = np.random.rand(
batch_size, input_channels, size, size).astype(np.float32) - 0.5
w = np.random.rand(
output_channels, input_channels, kernel, kernel) \
.astype(np.float32) - 0.5
b = np.random.rand(output_channels).astype(np.float32) - 0.5
inputs = [X, w, b] if use_bias else [X, w]
self.assertDeviceChecks(dc, op, inputs, [0])
if training_mode:
for i in range(len(inputs)):
self.assertGradientChecks(gc, op, inputs, i, [0], threshold=0.01)
@given(batch_size=st.integers(1, 3), **mu.gcs)
def test_depthwise_convolution(self, batch_size, gc, dc):
op = core.CreateOperator(
"Conv",
["X", "w", "b"],
["Y"],
stride=1,
pad=0,
kernel=1,
group=4,
device_option=dc[0]
)
op1 = core.CreateOperator(
"Conv",
["X", "w", "b"],
["Y"],
stride=1,
pad=0,
kernel=1,
group=4,
device_option=dc[1]
)
X = np.random.rand(batch_size, 544, 14, 14).astype(np.float32)
w = np.random.rand(544, 136, 1, 1).astype(np.float32)
b = np.random.rand(544).astype(np.float32)
workspace.SwitchWorkspace("_device_check_", True)
workspace.FeedBlob('X', X, dc[0])
workspace.FeedBlob('w', w, dc[0])
workspace.FeedBlob('b', b, dc[0])
workspace.RunOperatorOnce(op)
Y0 = workspace.FetchBlob('Y')
workspace.ResetWorkspace()
workspace.FeedBlob('X', X, dc[1])
workspace.FeedBlob('w', w, dc[1])
workspace.FeedBlob('b', b, dc[1])
net = core.Net("net")
old_net = caffe2_pb2.NetDef()
old_net.op.extend([op1])
net.Proto().CopyFrom(old_net)
optimizeForMKLDNN(net)
workspace.RunOperatorOnce(net.Proto().op[0])
Y1 = workspace.FetchBlob('Y')
if not np.allclose(Y0, Y1, atol=0.01, rtol=0.01):
print(Y1.flatten())
print(Y0.flatten())
print(np.max(np.abs(Y1 - Y0)))
self.assertTrue(False)
workspace.ResetWorkspace()
workspace.FeedBlob('X', X, dc[1])
workspace.FeedBlob('w', w, dc[1])
workspace.FeedBlob('b', b, dc[1])
workspace.RunOperatorOnce(op1)
Y2 = workspace.FetchBlob('Y')
if not np.allclose(Y0, Y2, atol=0.01, rtol=0.01):
print(Y2.flatten())
print(Y0.flatten())
print(np.max(np.abs(Y2 - Y0)))
self.assertTrue(False)
if __name__ == "__main__":
unittest.main()
|
