• Home
  • Line#
  • Scopes#
  • Navigate#
  • Raw
  • Download
1# Copyright 2020 Huawei Technologies Co., Ltd
2#
3# Licensed under the Apache License, Version 2.0 (the "License");
4# you may not use this file except in compliance with the License.
5# You may obtain a copy of the License at
6#
7# http://www.apache.org/licenses/LICENSE-2.0
8#
9# Unless required by applicable law or agreed to in writing, software
10# distributed under the License is distributed on an "AS IS" BASIS,
11# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12# See the License for the specific language governing permissions and
13# limitations under the License.
14# ============================================================================
15
16import numpy as np
17import pytest
18
19import mindspore.context as context
20import mindspore.nn as nn
21from mindspore.common.parameter import Parameter
22from mindspore.common.initializer import initializer
23from mindspore import Tensor
24from mindspore.ops import operations as P
25from mindspore.ops.operations import _grad_ops as G
26
27
28class Conv2dBpropInputInplace(nn.Cell):
29    def __init__(self, w1, w2):
30        super(Conv2dBpropInputInplace, self).__init__()
31        self.conv2d_1 = P.Conv2DBackpropInput(out_channel=256, kernel_size=1)
32        self.w1 = Parameter(initializer(w1, w1.shape), name='w1')
33        self.conv2d_2 = P.Conv2DBackpropInput(out_channel=256, kernel_size=1)
34        self.w2 = Parameter(initializer(w2, w2.shape), name='w2')
35        self.add = P.Add()
36        self.maxpool = P.MaxPool(kernel_size=3, strides=2, pad_mode='SAME')
37        self.maxpool_grad = G.MaxPoolGrad(kernel_size=3, strides=2, pad_mode='SAME')
38        self.shape = (32, 64, 56, 56)
39
40    def construct(self, x1, x2, x3):
41        dx1 = self.conv2d_1(x1, self.w1, self.shape)
42        dx2 = self.conv2d_2(x2, self.w2, self.shape)
43
44        dx = self.add(dx1, dx2)
45        y = self.maxpool(x3)
46        y = self.maxpool_grad(x3, y, dx)
47        return y
48
49
50@pytest.mark.level0
51@pytest.mark.platform_x86_gpu_training
52@pytest.mark.env_onecard
53def test_inplace_fusion1():
54
55    np.random.seed(42)
56    w1_np = np.random.randn(64, 64, 1, 1)
57    w2_np = np.random.randn(256, 64, 1, 1)
58    x1_np = np.random.randn(32, 64, 56, 56)
59    x2_np = np.random.randn(32, 256, 56, 56)
60    x3_np = np.random.randn(32, 64, 112, 112)
61
62    w1 = Tensor(w1_np.astype(np.float32))
63    w2 = Tensor(w2_np.astype(np.float32))
64    x1 = Tensor(x1_np.astype(np.float32))
65    x2 = Tensor(x2_np.astype(np.float32))
66    x3 = Tensor(x3_np.astype(np.float32))
67
68    context.set_context(device_target='GPU', mode=context.GRAPH_MODE)
69    net = Conv2dBpropInputInplace(w1, w2)
70    fusion_output = net(x1, x2, x3)
71
72    context.set_context(device_target='GPU', mode=context.PYNATIVE_MODE)
73    no_fusion_output = net(x1, x2, x3)
74
75    assert np.allclose(fusion_output.asnumpy(), no_fusion_output.asnumpy(), atol=2e-5)
76