1# Copyright 2021 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 15import numpy as np 16 17import mindspore as ms 18from mindspore import context, Tensor, Parameter 19from mindspore.common.api import _cell_graph_executor 20from mindspore.nn import Cell, TrainOneStepCell, Momentum 21from mindspore.ops import operations as P 22 23 24class Net(Cell): 25 def __init__(self, mul_weight, strategy1=None, strategy2=None): 26 super().__init__() 27 self.mul = P.Mul().shard(strategy1) 28 self.dropout1 = P.Dropout(keep_prob=0.5).shard(strategy2) 29 self.relu = P.ReLU().shard(strategy2) 30 self.dropout2 = P.Dropout(keep_prob=0.5).shard(strategy2) 31 self.relu2 = P.ReLU().shard(strategy2) 32 self.mul_weight = Parameter(mul_weight, "w1") 33 34 def construct(self, x, b): 35 out = self.mul(x, self.mul_weight) 36 out, _ = self.dropout1(out) 37 out = self.relu(out) 38 out, _ = self.dropout2(out) 39 out = self.relu2(out) 40 return out 41 42 43_x = Tensor(np.ones([128, 64]), dtype=ms.float32) 44_w1 = Tensor(np.ones([128, 64]), dtype=ms.float32) 45_b = Tensor(np.ones([128, 64]), dtype=ms.float32) 46 47 48def compile_net(net): 49 optimizer = Momentum(net.trainable_params(), learning_rate=0.1, momentum=0.9) 50 train_net = TrainOneStepCell(net, optimizer) 51 train_net.set_auto_parallel() 52 train_net.set_train() 53 _cell_graph_executor.compile(train_net, _x, _b) 54 context.reset_auto_parallel_context() 55 56 57def test_dropout_data_parallel(): 58 context.set_auto_parallel_context(parallel_mode="semi_auto_parallel", device_num=16, global_rank=0) 59 strategy1 = ((16, 1), (16, 1)) 60 strategy2 = ((16, 1),) 61 net = Net(_w1, strategy1, strategy2) 62 compile_net(net) 63 64 65def test_dropout_model_parallel(): 66 context.set_auto_parallel_context(parallel_mode="semi_auto_parallel", device_num=16, global_rank=0) 67 strategy1 = ((1, 16), (1, 16)) 68 strategy2 = ((1, 16),) 69 net = Net(_w1, strategy1, strategy2) 70 compile_net(net) 71 72 73def test_dropout_mixed_parallel(): 74 context.set_auto_parallel_context(parallel_mode="semi_auto_parallel", device_num=16, global_rank=0) 75 strategy1 = ((4, 4), (4, 4)) 76 strategy2 = ((4, 4),) 77 net = Net(_w1, strategy1, strategy2) 78 compile_net(net) 79 80 81def test_dropout_auto_parallel(): 82 context.set_auto_parallel_context(parallel_mode="auto_parallel", device_num=16, global_rank=0) 83 net = Net(_w1) 84 compile_net(net) 85 86 87def test_dropout_repeat_calc(): 88 context.set_auto_parallel_context(parallel_mode="semi_auto_parallel", device_num=16, global_rank=0) 89 strategy1 = ((4, 4), (4, 4)) 90 strategy2 = ((2, 4),) 91 net = Net(_w1, strategy1, strategy2) 92 compile_net(net) 93