• Home
  • Line#
  • Scopes#
  • Navigate#
  • Raw
  • Download
1# Copyright 2022 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 as ms
20import mindspore.nn as nn
21
22
23class Net(nn.Cell):
24    def __init__(self):
25        super(Net, self).__init__()
26        self.pool = nn.PReLU(channel=2, w=-0.25)
27
28    def construct(self, x):
29        out = self.pool(x)
30        return out
31
32
33@pytest.mark.level2
34@pytest.mark.platform_x86_cpu
35@pytest.mark.platform_arm_cpu
36@pytest.mark.platform_x86_gpu_training
37@pytest.mark.platform_arm_ascend_training
38@pytest.mark.platform_x86_ascend_training
39@pytest.mark.env_onecard
40@pytest.mark.parametrize('mode', [ms.GRAPH_MODE, ms.PYNATIVE_MODE])
41def test_prelu_normal(mode):
42    """
43    Feature: PReLU
44    Description: Verify the result of PReLU
45    Expectation: success
46    """
47    ms.set_context(mode=mode)
48    x = ms.Tensor([[[0.9192, -0.1487],
49                    [-0.3999, -0.6840]],
50
51                   [[0.4745, -0.6271],
52                    [-0.6547, -0.5856]],
53
54                   [[-0.2572, -0.8412],
55                    [0.1918, -0.6117]]])
56    net = Net()
57    out = net(x)
58    expect_out = np.array([[[0.9192, 0.037175],
59                            [0.099975, 0.171]],
60
61                           [[0.4745, 0.156775],
62                            [0.163675, 0.1464]],
63
64                           [[0.0643, 0.2103],
65                            [0.1918, 0.152925]]])
66    assert np.allclose(out.asnumpy().astype(np.float16), expect_out.astype(np.float16))
67