• Home
  • Line#
  • Scopes#
  • Navigate#
  • Raw
  • Download
1# Copyright 2019 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 import Tensor
22from mindspore.nn import Dense
23from mindspore.nn import TrainOneStepCell, WithLossCell
24from mindspore.nn.optim import Momentum
25from mindspore.ops import operations as P
26
27context.set_context(mode=context.GRAPH_MODE, device_target="CPU")
28
29
30class MomentumNet(nn.Cell):
31    def __init__(self):
32        super(MomentumNet, self).__init__()
33        self.batch_size = 1
34
35        self.reshape = P.Reshape()
36        weight = Tensor(np.ones([10, 16]).astype(np.float32) * 0.01)
37        self.fc1 = Dense(16, 10, weight_init=weight)
38
39    def construct(self, input_x):
40        output = self.reshape(input_x, (self.batch_size, -1))
41        output = self.fc1(output)
42        return output
43
44
45@pytest.mark.level1
46@pytest.mark.platform_x86_cpu
47@pytest.mark.env_onecard
48def test_momentum():
49    epoch = 13
50    net = MomentumNet()
51    learning_rate = 0.1
52    momentum = 0.9
53
54    optimizer = Momentum(filter(lambda x: x.requires_grad, net.get_parameters()), learning_rate, momentum)
55    criterion = nn.SoftmaxCrossEntropyWithLogits(sparse=True, reduction='mean')
56    net_with_criterion = WithLossCell(net, criterion)
57    train_network = TrainOneStepCell(net_with_criterion, optimizer)  # optimizer
58    train_network.set_train()
59    losses = []
60    for _ in range(epoch):
61        data = Tensor(np.arange(0, 16).reshape(1, 1, 4, 4).astype(np.float32) * 0.01)
62        label = Tensor(np.array([0]).astype(np.int32))
63        loss = train_network(data, label)
64        losses.append(loss)
65
66    print("================================")
67    print(losses)
68#   expect output:
69#   [[0.04132498 0.00874167 0.00874167 0.00874167 0.00874167
70#     0.00874167 0.00874167 0.00874167 0.00874167 0.00874167]]
71
72    return losses
73