• 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"""
16@File   : test_data_parallel_dense.py
17@Desc   : test data parallel dense
18"""
19import numpy as np
20
21import mindspore.context as context
22import mindspore.nn as nn
23from mindspore import Tensor
24from mindspore.common.api import _cell_graph_executor
25from mindspore.nn import Momentum
26from mindspore.nn import TrainOneStepCell, WithLossCell
27from mindspore.ops import operations as P
28from mindspore.context import ParallelMode
29
30
31class DenseMMNet(nn.Cell):
32    """DenseMMNet definition"""
33
34    def __init__(self):
35        super(DenseMMNet, self).__init__()
36        self.fc1 = nn.Dense(128, 768, activation='relu')
37        self.fc2 = nn.Dense(128, 768, activation='relu')
38        self.fc3 = nn.Dense(128, 768, activation='relu')
39        self.fc4 = nn.Dense(768, 768, activation='relu')
40        self.relu4 = nn.ReLU()
41        self.relu5 = nn.ReLU()
42        self.transpose = P.Transpose()
43        self.matmul1 = P.MatMul()
44        self.matmul2 = P.MatMul()
45
46    def construct(self, x):
47        q = self.fc1(x)
48        k = self.fc2(x)
49        v = self.fc3(x)
50        k = self.transpose(k, (1, 0))
51        c = self.relu4(self.matmul1(q, k))
52        s = self.relu5(self.matmul2(c, v))
53        s = self.fc4(s)
54        return s
55
56
57def test_data_parallel_dense():
58    """test_data_parallel_dense"""
59    context.set_context(mode=context.GRAPH_MODE)
60    context.reset_auto_parallel_context()
61    context.set_auto_parallel_context(parallel_mode=ParallelMode.DATA_PARALLEL, gradients_mean=True, device_num=8)
62    inp = Tensor(np.ones([32, 128]).astype(np.float32) * 0.01)
63    label = Tensor(np.zeros([32, 768]).astype(np.float32))
64    net = DenseMMNet()
65    loss_fn = nn.SoftmaxCrossEntropyWithLogits()
66
67    optimizer = Momentum(filter(lambda x: x.requires_grad, net.get_parameters()),
68                         learning_rate=0.1,
69                         momentum=0.9)
70    net = WithLossCell(net, loss_fn)
71    net = TrainOneStepCell(net, optimizer)
72
73    _cell_graph_executor.compile(net, inp, label)
74    context.reset_auto_parallel_context()
75