def __init__(self,
num_features,
eps=1e-5,
momentum=0.9,
affine=True,
gamma_init='ones',
beta_init='zeros',
moving_mean_init='zeros',
moving_var_init='ones',
use_batch_statistics=True):
super(_BatchNorm, self).__init__()
if num_features < 1:
raise ValueError("num_features must be at least 1")
if momentum < 0 or momentum > 1:
raise ValueError(
"momentum should be a number in range [0, 1], but got {}".
format(momentum))
self.use_batch_statistics = use_batch_statistics
self.num_features = num_features
self.eps = eps
self.moving_mean = Parameter(initializer(moving_mean_init,
num_features),
name="mean",
requires_grad=False)
self.moving_variance = Parameter(initializer(moving_var_init,
num_features),
name="variance",
requires_grad=False)
self.gamma = Parameter(initializer(gamma_init, num_features),
name="gamma",
requires_grad=affine)
self.beta = Parameter(initializer(beta_init, num_features),
name="beta",
requires_grad=affine)
if context.get_context("enable_ge"):
self.is_ge_backend = True
self.momentum = Tensor(1.0 - momentum, DT.float32)
self.bn_train = P.BatchNorm(is_training=True, epsilon=self.eps)
else:
self.is_ge_backend = False
self.momentum = 1.0 - momentum
self.bn_train = P.FusedBatchNorm(mode=1,
epsilon=self.eps,
momentum=self.momentum)
self.bn_infer = P.BatchNorm(is_training=False, epsilon=self.eps)
data_parallel_strategy = ((1, ), (1, ))
data_parallel_strategy_one = ((1, ), ())
self.sub_mean = P.Sub().set_strategy(data_parallel_strategy)
self.sub_var = P.Sub().set_strategy(data_parallel_strategy)
self.mul_mean = P.Mul().set_strategy(data_parallel_strategy_one)
self.mul_var = P.Mul().set_strategy(data_parallel_strategy_one)
self.assign_sub_mean = P.AssignSub().set_strategy(
data_parallel_strategy)
self.assign_sub_var = P.AssignSub().set_strategy(
data_parallel_strategy)
def __init__(self):
super().__init__()
self.mul = P.Mul()
self.addn = P.AddN()
self.assign = P.Assign()
self.assign_sub = P.AssignSub()
self.para = Parameter(Tensor(1.0, dtype=ms.float32), name='para')
def __init__(self):
super().__init__()
#self._save_graphs(save_graph_flag=True, save_graph_path=".")
self.relu = ReLU()
self.mean = P.ReduceMean(keep_dims=False)
self.assign_sub = P.AssignSub()
self.input_data = Parameter(initializer(1, [1, 3, 2, 2], ms.float32),
name='value')
def __init__(self,
num_features,
eps=1e-5,
momentum=0.1,
affine=True,
gamma_init='ones',
beta_init='zeros',
moving_mean_init='zeros',
moving_var_init='ones'):
super(FusedBatchNorm, self).__init__()
if num_features < 1:
raise ValueError("num_features must be at least 1")
if momentum < 0 or momentum > 1:
raise ValueError(
"momentum should be a number in range [0, 1], but got {}".
format(momentum))
self.num_features = num_features
self.eps = eps
self.momentum = Tensor(1.0 - momentum, DT.float32)
self.gamma = Parameter(initializer(gamma_init, num_features),
name="gamma",
requires_grad=affine)
self.beta = Parameter(initializer(beta_init, num_features),
name="beta",
requires_grad=affine)
self.moving_mean = Parameter(initializer(moving_mean_init,
num_features),
name="mean",
requires_grad=False)
self.moving_variance = Parameter(initializer(moving_var_init,
num_features),
name="variance",
requires_grad=False)
self.bn_train = P.BatchNorm(is_training=True, epsilon=self.eps)
self.bn_infer = P.BatchNorm(is_training=False, epsilon=self.eps)
self.sub_mean = P.Sub().shard(((1), (1)))
self.sub_var = P.Sub().shard(((1), (1)))
self.mul_mean = P.Mul().shard(((1, ), ()))
self.mul_var = P.Mul().shard(((1, ), ()))
self.assign_sub_mean = P.AssignSub().shard(((1, ), (1, )))
self.assign_sub_var = P.AssignSub().shard(((1), (1)))
self.sub_mean2 = P.Sub().shard(((1), (1)))
self.sub_var2 = P.Sub().shard(((1), (1)))
def __init__(self):
super().__init__()
self.assign_sub = P.AssignSub()
self.mul = P.Mul()
self.mul_weight = Parameter(Tensor(np.full([128, 32],
0.5, dtype=np.float32)),
name="mul_weight")
self.assignsub_weight = Parameter(Tensor(np.full([128, 32],
1.1, dtype=np.float32)),
name="assignsub_weight")
def __init__(self, channel=1, w=0.25):
super(PReLU, self).__init__()
if isinstance(w, (np.float32, float)):
tmp = np.empty((channel, ), dtype=np.float32)
tmp.fill(w)
w = Tensor(tmp)
elif isinstance(w, list):
w = Tensor(w)
if not isinstance(w, Tensor):
raise TypeError("w only support np.float32, float or Tensor type.")
self.w = Parameter(initializer(w, [
channel,
]), name='a')
self.prelu = P.PReLU()
self.relu = P.ReLU().set_strategy(((1, ), ))
self.sub = P.Sub().set_strategy(((1, ), (1, )))
self.assign_sub = P.AssignSub().set_strategy(((1, ), (1, )))
def __init__(self,
num_features,
eps=1e-5,
momentum=0.9,
affine=True,
gamma_init='ones',
beta_init='zeros',
moving_mean_init='zeros',
moving_var_init='ones',
use_batch_statistics=True,
device_num_each_group=1):
super(_BatchNorm, self).__init__()
if num_features < 1:
raise ValueError("num_features must be at least 1")
if momentum < 0 or momentum > 1:
raise ValueError(
"momentum should be a number in range [0, 1], but got {}".
format(momentum))
self.use_batch_statistics = use_batch_statistics
self.num_features = num_features
self.eps = eps
self.moving_mean = Parameter(initializer(moving_mean_init,
num_features),
name="mean",
requires_grad=False)
self.moving_variance = Parameter(initializer(moving_var_init,
num_features),
name="variance",
requires_grad=False)
self.gamma = Parameter(initializer(gamma_init, num_features),
name="gamma",
requires_grad=affine)
self.beta = Parameter(initializer(beta_init, num_features),
name="beta",
requires_grad=affine)
self.group = check_int_positive(device_num_each_group)
self.is_global = False
if self.group != 1:
self.rank_id = get_rank()
self.rank_size = get_group_size()
self.device_list = [i for i in range(0, self.rank_size)]
self.rank_list = self.list_group(self.device_list, self.group)
self.rank_list_idx = len(self.rank_list)
for i in range(self.rank_list_idx):
if self.rank_id in self.rank_list[i] and self.group != 1:
self.is_global = True
management.create_group('group' + str(i),
self.rank_list[i])
self.all_reduce = P.AllReduce(
P.ReduceOp.SUM,
'group' + str(i)).add_prim_attr('fusion', 1)
self.shape = P.Shape()
self.reduce_mean = P.ReduceMean(keep_dims=True)
self.square = P.Square()
self.sqrt = P.Sqrt()
self.cast = P.Cast()
self.dtype = P.DType()
self.reshape = P.Reshape()
self.is_ascend = context.get_context("device_target") == "Ascend"
if context.get_context("enable_ge"):
self.is_ge_backend = True
self.momentum = Tensor(1.0 - momentum, mstype.float32)
else:
self.is_ge_backend = False
self.momentum = 1.0 - momentum
if self.is_ge_backend or self.is_ascend:
self.bn_train = P.BatchNorm(is_training=True, epsilon=self.eps)
else:
self.bn_train = P.FusedBatchNorm(mode=1,
epsilon=self.eps,
momentum=self.momentum)
self.bn_infer = P.BatchNorm(is_training=False, epsilon=self.eps)
data_parallel_strategy = ((1, ), (1, ))
data_parallel_strategy_one = ((1, ), ())
self.sub_mean = P.Sub().set_strategy(data_parallel_strategy)
self.sub_var = P.Sub().set_strategy(data_parallel_strategy)
self.mul_mean = P.Mul().set_strategy(data_parallel_strategy_one)
self.mul_var = P.Mul().set_strategy(data_parallel_strategy_one)
self.assign_sub_mean = P.AssignSub().set_strategy(
data_parallel_strategy)
self.assign_sub_var = P.AssignSub().set_strategy(
data_parallel_strategy)
def __init__(self,
num_features,
eps=1e-5,
momentum=0.9,
affine=True,
gamma_init='ones',
beta_init='zeros',
moving_mean_init='zeros',
moving_var_init='ones',
use_batch_statistics=None,
device_num_each_group=1,
input_dims='2d',
data_format='NCHW'):
super(_BatchNorm, self).__init__()
if num_features < 1:
raise ValueError("num_features must be at least 1")
if momentum < 0 or momentum > 1:
raise ValueError("momentum should be a number in range [0, 1], but got {}".format(momentum))
self.format = validator.check_string(data_format, ['NCHW', 'NHWC'], 'format', self.cls_name)
if context.get_context("device_target") != "GPU" and self.format == "NHWC":
raise ValueError("NHWC format only support in GPU target.")
self.use_batch_statistics = use_batch_statistics
self.num_features = num_features
self.eps = eps
self.input_dims = input_dims
self.moving_mean = Parameter(initializer(
moving_mean_init, num_features), name="mean", requires_grad=False)
self.moving_variance = Parameter(initializer(
moving_var_init, num_features), name="variance", requires_grad=False)
self.gamma = Parameter(initializer(
gamma_init, num_features), name="gamma", requires_grad=affine)
self.beta = Parameter(initializer(
beta_init, num_features), name="beta", requires_grad=affine)
self.group = validator.check_positive_int(device_num_each_group)
self.is_global = False
if self.group != 1:
self.rank_id = get_rank()
self.rank_size = get_group_size()
self.device_list = [i for i in range(0, self.rank_size)]
self.rank_list = self.list_group(self.device_list, self.group)
self.rank_list_idx = len(self.rank_list)
for i in range(self.rank_list_idx):
if self.rank_id in self.rank_list[i] and self.group != 1:
self.is_global = True
management.create_group('group' + str(i), self.rank_list[i])
self.all_reduce = P.AllReduce(P.ReduceOp.SUM, 'group' + str(i)).add_prim_attr('fusion', 1)
self.shape = P.Shape()
self.reduce_mean = P.ReduceMean(keep_dims=True)
self.square = P.Square()
self.sqrt = P.Sqrt()
self.cast = P.Cast()
self.dtype = P.DType()
self.reshape = P.Reshape()
self.is_ascend = context.get_context("device_target") == "Ascend"
self.is_gpu = context.get_context("device_target") == "GPU"
self.is_graph_mode = context.get_context("mode") == context.GRAPH_MODE
self.momentum = 1.0 - momentum
if context.get_context("enable_ge"):
self.is_ge_backend = True
else:
self.is_ge_backend = False
if self.is_graph_mode and (self.is_ge_backend or self.is_ascend):
self.bn_train = P.BatchNorm(is_training=True,
epsilon=self.eps)
elif self.is_gpu:
self.bn_train = P.FusedBatchNormEx(mode=1,
epsilon=self.eps,
momentum=self.momentum,
data_format=self.format)
else:
self.bn_train = P.FusedBatchNorm(mode=1,
epsilon=self.eps,
momentum=self.momentum)
self.bn_infer = P.BatchNorm(is_training=False, epsilon=self.eps, data_format=self.format)
self.enable_global_sync = self.is_global and (self.is_ge_backend or (self.is_graph_mode and self.is_ascend))
self.enable_default_train = self.is_graph_mode and not self.is_global and \
(self.is_ge_backend or self.is_ascend)
data_parallel_strategy = ((1,), (1,))
data_parallel_strategy_one = ((1,), ())
self.sub_mean = P.Sub().shard(data_parallel_strategy)
self.sub_var = P.Sub().shard(data_parallel_strategy)
self.mul_mean = P.Mul().shard(data_parallel_strategy_one)
self.mul_var = P.Mul().shard(data_parallel_strategy_one)
self.assign_sub_mean = P.AssignSub().shard(data_parallel_strategy)
self.assign_sub_var = P.AssignSub().shard(data_parallel_strategy)
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ============================================================================
from mindspore.ops import operations as P
from mindspore.ops import Primitive
import mindspore.common.dtype as mstype
from mindspore.common.tensor import Tensor
AssignSub = P.AssignSub()
Mul = P.Mul()
Sub = P.Sub()
make_tuple = Primitive('make_tuple')
tuple_getitem = Primitive('tuple_getitem')
depend = Primitive('depend')
BatchNorm = P.BatchNorm()
BNTrainingReduce = Primitive('BNTrainingReduce')
BNTrainingUpdate = Primitive('BNTrainingUpdate')
constant0 = Tensor(0.1, mstype.float32)
constant1 = Tensor(0.1, mstype.float32)
class FnDict:
def __init__(self):
self.fnDict = {}
def __init__(self):
super(Net, self).__init__()
self.b = Parameter(initializer('ones', [5]), name='b')
self.sub = P.AssignSub()
def __init__(self, para):
super(AssignSubNet, self).__init__()
self.para = Parameter(para, name="para")
self.assign_sub = P.AssignSub()
def __init__(self):
super(Net, self).__init__()
self.AssignSub = P.AssignSub()
self.inputdata = Parameter(initializer('normal', [1]),
name="global_step")
print("inputdata: ", self.inputdata)
def __init__(self,):
super(AssignSubNet, self).__init__()
self.op = P.AssignSub()
self.inputdata = Parameter(Tensor(np.zeros([1]).astype(np.bool_), mstype.bool_), name="assign_sub1")
