File size: 9,746 Bytes
3bbb319
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
# Copyright (c) OpenMMLab. All rights reserved.
import numpy as np
import pytest
import torch
import torch.nn as nn
from mmcv.runner import auto_fp16, force_fp32
from mmcv.runner.fp16_utils import cast_tensor_type


def test_cast_tensor_type():
    inputs = torch.FloatTensor([5.])
    src_type = torch.float32
    dst_type = torch.int32
    outputs = cast_tensor_type(inputs, src_type, dst_type)
    assert isinstance(outputs, torch.Tensor)
    assert outputs.dtype == dst_type

    inputs = 'tensor'
    src_type = str
    dst_type = str
    outputs = cast_tensor_type(inputs, src_type, dst_type)
    assert isinstance(outputs, str)

    inputs = np.array([5.])
    src_type = np.ndarray
    dst_type = np.ndarray
    outputs = cast_tensor_type(inputs, src_type, dst_type)
    assert isinstance(outputs, np.ndarray)

    inputs = dict(
        tensor_a=torch.FloatTensor([1.]), tensor_b=torch.FloatTensor([2.]))
    src_type = torch.float32
    dst_type = torch.int32
    outputs = cast_tensor_type(inputs, src_type, dst_type)
    assert isinstance(outputs, dict)
    assert outputs['tensor_a'].dtype == dst_type
    assert outputs['tensor_b'].dtype == dst_type

    inputs = [torch.FloatTensor([1.]), torch.FloatTensor([2.])]
    src_type = torch.float32
    dst_type = torch.int32
    outputs = cast_tensor_type(inputs, src_type, dst_type)
    assert isinstance(outputs, list)
    assert outputs[0].dtype == dst_type
    assert outputs[1].dtype == dst_type

    inputs = 5
    outputs = cast_tensor_type(inputs, None, None)
    assert isinstance(outputs, int)


def test_auto_fp16():

    with pytest.raises(TypeError):
        # ExampleObject is not a subclass of nn.Module

        class ExampleObject:

            @auto_fp16()
            def __call__(self, x):
                return x

        model = ExampleObject()
        input_x = torch.ones(1, dtype=torch.float32)
        model(input_x)

    # apply to all input args
    class ExampleModule(nn.Module):

        @auto_fp16()
        def forward(self, x, y):
            return x, y

    model = ExampleModule()
    input_x = torch.ones(1, dtype=torch.float32)
    input_y = torch.ones(1, dtype=torch.float32)
    output_x, output_y = model(input_x, input_y)
    assert output_x.dtype == torch.float32
    assert output_y.dtype == torch.float32

    model.fp16_enabled = True
    output_x, output_y = model(input_x, input_y)
    assert output_x.dtype == torch.half
    assert output_y.dtype == torch.half

    if torch.cuda.is_available():
        model.cuda()
        output_x, output_y = model(input_x.cuda(), input_y.cuda())
        assert output_x.dtype == torch.half
        assert output_y.dtype == torch.half

    # apply to specified input args
    class ExampleModule(nn.Module):

        @auto_fp16(apply_to=('x', ))
        def forward(self, x, y):
            return x, y

    model = ExampleModule()
    input_x = torch.ones(1, dtype=torch.float32)
    input_y = torch.ones(1, dtype=torch.float32)
    output_x, output_y = model(input_x, input_y)
    assert output_x.dtype == torch.float32
    assert output_y.dtype == torch.float32

    model.fp16_enabled = True
    output_x, output_y = model(input_x, input_y)
    assert output_x.dtype == torch.half
    assert output_y.dtype == torch.float32

    if torch.cuda.is_available():
        model.cuda()
        output_x, output_y = model(input_x.cuda(), input_y.cuda())
        assert output_x.dtype == torch.half
        assert output_y.dtype == torch.float32

    # apply to optional input args
    class ExampleModule(nn.Module):

        @auto_fp16(apply_to=('x', 'y'))
        def forward(self, x, y=None, z=None):
            return x, y, z

    model = ExampleModule()
    input_x = torch.ones(1, dtype=torch.float32)
    input_y = torch.ones(1, dtype=torch.float32)
    input_z = torch.ones(1, dtype=torch.float32)
    output_x, output_y, output_z = model(input_x, y=input_y, z=input_z)
    assert output_x.dtype == torch.float32
    assert output_y.dtype == torch.float32
    assert output_z.dtype == torch.float32

    model.fp16_enabled = True
    output_x, output_y, output_z = model(input_x, y=input_y, z=input_z)
    assert output_x.dtype == torch.half
    assert output_y.dtype == torch.half
    assert output_z.dtype == torch.float32

    if torch.cuda.is_available():
        model.cuda()
        output_x, output_y, output_z = model(
            input_x.cuda(), y=input_y.cuda(), z=input_z.cuda())
        assert output_x.dtype == torch.half
        assert output_y.dtype == torch.half
        assert output_z.dtype == torch.float32

    # out_fp32=True
    class ExampleModule(nn.Module):

        @auto_fp16(apply_to=('x', 'y'), out_fp32=True)
        def forward(self, x, y=None, z=None):
            return x, y, z

    model = ExampleModule()
    input_x = torch.ones(1, dtype=torch.half)
    input_y = torch.ones(1, dtype=torch.float32)
    input_z = torch.ones(1, dtype=torch.float32)
    output_x, output_y, output_z = model(input_x, y=input_y, z=input_z)
    assert output_x.dtype == torch.half
    assert output_y.dtype == torch.float32
    assert output_z.dtype == torch.float32

    model.fp16_enabled = True
    output_x, output_y, output_z = model(input_x, y=input_y, z=input_z)
    assert output_x.dtype == torch.float32
    assert output_y.dtype == torch.float32
    assert output_z.dtype == torch.float32

    if torch.cuda.is_available():
        model.cuda()
        output_x, output_y, output_z = model(
            input_x.cuda(), y=input_y.cuda(), z=input_z.cuda())
        assert output_x.dtype == torch.float32
        assert output_y.dtype == torch.float32
        assert output_z.dtype == torch.float32


def test_force_fp32():

    with pytest.raises(TypeError):
        # ExampleObject is not a subclass of nn.Module

        class ExampleObject:

            @force_fp32()
            def __call__(self, x):
                return x

        model = ExampleObject()
        input_x = torch.ones(1, dtype=torch.float32)
        model(input_x)

    # apply to all input args
    class ExampleModule(nn.Module):

        @force_fp32()
        def forward(self, x, y):
            return x, y

    model = ExampleModule()
    input_x = torch.ones(1, dtype=torch.half)
    input_y = torch.ones(1, dtype=torch.half)
    output_x, output_y = model(input_x, input_y)
    assert output_x.dtype == torch.half
    assert output_y.dtype == torch.half

    model.fp16_enabled = True
    output_x, output_y = model(input_x, input_y)
    assert output_x.dtype == torch.float32
    assert output_y.dtype == torch.float32

    if torch.cuda.is_available():
        model.cuda()
        output_x, output_y = model(input_x.cuda(), input_y.cuda())
        assert output_x.dtype == torch.float32
        assert output_y.dtype == torch.float32

    # apply to specified input args
    class ExampleModule(nn.Module):

        @force_fp32(apply_to=('x', ))
        def forward(self, x, y):
            return x, y

    model = ExampleModule()
    input_x = torch.ones(1, dtype=torch.half)
    input_y = torch.ones(1, dtype=torch.half)
    output_x, output_y = model(input_x, input_y)
    assert output_x.dtype == torch.half
    assert output_y.dtype == torch.half

    model.fp16_enabled = True
    output_x, output_y = model(input_x, input_y)
    assert output_x.dtype == torch.float32
    assert output_y.dtype == torch.half

    if torch.cuda.is_available():
        model.cuda()
        output_x, output_y = model(input_x.cuda(), input_y.cuda())
        assert output_x.dtype == torch.float32
        assert output_y.dtype == torch.half

    # apply to optional input args
    class ExampleModule(nn.Module):

        @force_fp32(apply_to=('x', 'y'))
        def forward(self, x, y=None, z=None):
            return x, y, z

    model = ExampleModule()
    input_x = torch.ones(1, dtype=torch.half)
    input_y = torch.ones(1, dtype=torch.half)
    input_z = torch.ones(1, dtype=torch.half)
    output_x, output_y, output_z = model(input_x, y=input_y, z=input_z)
    assert output_x.dtype == torch.half
    assert output_y.dtype == torch.half
    assert output_z.dtype == torch.half

    model.fp16_enabled = True
    output_x, output_y, output_z = model(input_x, y=input_y, z=input_z)
    assert output_x.dtype == torch.float32
    assert output_y.dtype == torch.float32
    assert output_z.dtype == torch.half

    if torch.cuda.is_available():
        model.cuda()
        output_x, output_y, output_z = model(
            input_x.cuda(), y=input_y.cuda(), z=input_z.cuda())
        assert output_x.dtype == torch.float32
        assert output_y.dtype == torch.float32
        assert output_z.dtype == torch.half

    # out_fp16=True
    class ExampleModule(nn.Module):

        @force_fp32(apply_to=('x', 'y'), out_fp16=True)
        def forward(self, x, y=None, z=None):
            return x, y, z

    model = ExampleModule()
    input_x = torch.ones(1, dtype=torch.float32)
    input_y = torch.ones(1, dtype=torch.half)
    input_z = torch.ones(1, dtype=torch.half)
    output_x, output_y, output_z = model(input_x, y=input_y, z=input_z)
    assert output_x.dtype == torch.float32
    assert output_y.dtype == torch.half
    assert output_z.dtype == torch.half

    model.fp16_enabled = True
    output_x, output_y, output_z = model(input_x, y=input_y, z=input_z)
    assert output_x.dtype == torch.half
    assert output_y.dtype == torch.half
    assert output_z.dtype == torch.half

    if torch.cuda.is_available():
        model.cuda()
        output_x, output_y, output_z = model(
            input_x.cuda(), y=input_y.cuda(), z=input_z.cuda())
        assert output_x.dtype == torch.half
        assert output_y.dtype == torch.half
        assert output_z.dtype == torch.half