p60975123
/
mindspore
forked from mindspore-Ecosystem/mindspore
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

!7497 change composite.random_ops.get_seed to internal interface 

Merge pull request !7497 from yihuaijie/random
This commit is contained in:
mindspore-ci-bot 2020-10-20 14:50:55 +08:00 committed by Gitee
parent d0a1a9b73c 626c7f8906
commit 4ef0163963
2 changed files with 35 additions and 35 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

58
mindspore/common/seed.py
View File

@ -57,73 +57,73 @@ def set_seed(seed):
TypeError: If seed isn't a int.
Examples:
1. If global seed is not set, numpy.random and initializer will choose a random seed:
>>> # 1. If global seed is not set, numpy.random and initializer will choose a random seed:
>>> np_1 = np.random.normal(0, 1, [1]).astype(np.float32) # A1
>>> np_1 = np.random.normal(0, 1, [1]).astype(np.float32) # A2
>>> w1 = Parameter(initializer("uniform", [2, 2], ms.float32), name="w1") # W1
>>> w1 = Parameter(initializer("uniform", [2, 2], ms.float32), name="w1") # W2
Rerun the program will get diferent results:
>>> # Rerun the program will get diferent results:
>>> np_1 = np.random.normal(0, 1, [1]).astype(np.float32) # A3
>>> np_1 = np.random.normal(0, 1, [1]).astype(np.float32) # A4
>>> w1 = Parameter(initializer("uniform", [2, 2], ms.float32), name="w1") # W3
>>> w1 = Parameter(initializer("uniform", [2, 2], ms.float32), name="w1") # W4
2. If global seed is set, numpy.random and initializer will use it:
>>>
>>> 2. If global seed is set, numpy.random and initializer will use it:
>>> set_seed(1234)
>>> np_1 = np.random.normal(0, 1, [1]).astype(np.float32) # A1
>>> np_1 = np.random.normal(0, 1, [1]).astype(np.float32) # A2
>>> w1 = Parameter(initializer("uniform", [2, 2], ms.float32), name="w1") # W1
>>> w1 = Parameter(initializer("uniform", [2, 2], ms.float32), name="w1") # W2
Rerun the program will get the same results:
>>> # Rerun the program will get the same results:
>>> set_seed(1234)
>>> np_1 = np.random.normal(0, 1, [1]).astype(np.float32) # A1
>>> np_1 = np.random.normal(0, 1, [1]).astype(np.float32) # A2
>>> w1 = Parameter(initializer("uniform", [2, 2], ms.float32), name="w1") # W1
>>> w1 = Parameter(initializer("uniform", [2, 2], ms.float32), name="w1") # W2
3. If neither global seed nor op seed is set, mindspore.ops.composite.random_ops and
mindspore.nn.probability.distribution will choose a random seed:
>>>
>>> # 3. If neither global seed nor op seed is set, mindspore.ops.composite.random_ops and
>>> # mindspore.nn.probability.distribution will choose a random seed:
>>> c1 = C.uniform((1, 4)) # C1
>>> c2 = C.uniform((1, 4)) # C2
Rerun the program will get different results:
>>> Rerun the program will get different results:
>>> c1 = C.uniform((1, 4)) # C3
>>> c2 = C.uniform((1, 4)) # C4
4. If global seed is set, but op seed is not set, mindspore.ops.composite.random_ops and
mindspore.nn.probability.distribution will caculate a seed according to global seed and
default op seed. Each call will change the default op seed, thus each call get different
results.
>>>
>>> # 4. If global seed is set, but op seed is not set, mindspore.ops.composite.random_ops and
>>> # mindspore.nn.probability.distribution will caculate a seed according to global seed and
>>> # default op seed. Each call will change the default op seed, thus each call get different
>>> # results.
>>> set_seed(1234)
>>> c1 = C.uniform((1, 4)) # C1
>>> c2 = C.uniform((1, 4)) # C2
Rerun the program will get the same results:
>>> # Rerun the program will get the same results:
>>> set_seed(1234)
>>> c1 = C.uniform((1, 4)) # C1
>>> c2 = C.uniform((1, 4)) # C2
5. If both global seed and op seed are set, mindspore.ops.composite.random_ops and
mindspore.nn.probability.distribution will caculate a seed according to global seed and
op seed counter. Each call will change the op seed counter, thus each call get different
results.
>>>
>>> # 5. If both global seed and op seed are set, mindspore.ops.composite.random_ops and
>>> # mindspore.nn.probability.distribution will caculate a seed according to global seed and
>>> # op seed counter. Each call will change the op seed counter, thus each call get different
>>> # results.
>>> set_seed(1234)
>>> c1 = C.uniform((1, 4), seed=2) # C1
>>> c2 = C.uniform((1, 4), seed=2) # C2
Rerun the program will get the same results:
>>> Rerun the program will get the same results:
>>> set_seed(1234)
>>> c1 = C.uniform((1, 4), seed=2) # C1
>>> c2 = C.uniform((1, 4), seed=2) # C2
6. If op seed is set but global seed is not set, 0 will be used as global seed. Then
mindspore.ops.composite.random_ops and mindspore.nn.probability.distribution act as in
condition 5.
>>>
>>> # 6. If op seed is set but global seed is not set, 0 will be used as global seed. Then
>>> # mindspore.ops.composite.random_ops and mindspore.nn.probability.distribution act as in
>>> # condition 5.
>>> c1 = C.uniform((1, 4), seed=2) # C1
>>> c2 = C.uniform((1, 4), seed=2) # C2
Rerun the program will get the same results:
>>> #Rerun the program will get the same results:
>>> c1 = C.uniform((1, 4), seed=2) # C1
>>> c2 = C.uniform((1, 4), seed=2) # C2
7. Recall set_seed() in the program will reset numpy seed and op seed counter of
mindspore.ops.composite.random_ops and mindspore.nn.probability.distribution.
>>>
>>> # 7. Recall set_seed() in the program will reset numpy seed and op seed counter of
>>> # mindspore.ops.composite.random_ops and mindspore.nn.probability.distribution.
>>> set_seed(1234)
>>> np_1 = np.random.normal(0, 1, [1]).astype(np.float32) # A1
>>> c1 = C.uniform((1, 4), seed=2) # C1

12
mindspore/ops/composite/random_ops.py
View File

@ -22,7 +22,7 @@ from ...common import dtype as mstype
from ...common.seed import _get_graph_seed
@constexpr
def get_seed(op_seed, kernel_name):
def _get_seed(op_seed, kernel_name):
"Get the graph-level seed."
return _get_graph_seed(op_seed, kernel_name)
@ -57,7 +57,7 @@ def normal(shape, mean, stddev, seed=None):
stddev_dtype = F.dtype(stddev)
const_utils.check_valid_type(mean_dtype, mstype.int_type + (mstype.float16, mstype.float32), 'normal')
const_utils.check_valid_type(stddev_dtype, mstype.int_type + (mstype.float16, mstype.float32), 'normal')
seed1, seed2 = get_seed(seed, "normal")
seed1, seed2 = _get_seed(seed, "normal")
stdnormal = P.StandardNormal(seed1, seed2)
random_normal = stdnormal(shape)
value = random_normal * stddev + mean
@ -94,7 +94,7 @@ def laplace(shape, mean, lambda_param, seed=None):
lambda_param_dtype = F.dtype(lambda_param)
const_utils.check_tensors_dtype_same(mean_dtype, mstype.float32, "laplace")
const_utils.check_tensors_dtype_same(lambda_param_dtype, mstype.float32, "laplace")
seed1, seed2 = get_seed(seed, "laplace")
seed1, seed2 = _get_seed(seed, "laplace")
stdlaplace = P.StandardLaplace(seed1, seed2)
rnd = stdlaplace(shape)
value = rnd * lambda_param + mean
@ -144,7 +144,7 @@ def uniform(shape, minval, maxval, seed=None, dtype=mstype.float32):
const_utils.check_valid_type(dtype, [mstype.int32, mstype.float32], 'uniform')
const_utils.check_tensors_dtype_same(minval_dtype, dtype, "uniform")
const_utils.check_tensors_dtype_same(maxval_dtype, dtype, "uniform")
seed1, seed2 = get_seed(seed, "uniform")
seed1, seed2 = _get_seed(seed, "uniform")
if const_utils.is_same_type(dtype, mstype.int32):
random_uniform = P.UniformInt(seed1, seed2)
value = random_uniform(shape, minval, maxval)
@ -176,7 +176,7 @@ def gamma(shape, alpha, beta, seed=None):
>>> beta = Tensor(1.0, mstype.float32)
>>> output = C.gamma(shape, alpha, beta, seed=5)
"""
seed1, seed2 = get_seed(seed, "gamma")
seed1, seed2 = _get_seed(seed, "gamma")
random_gamma = P.Gamma(seed1, seed2)
value = random_gamma(shape, alpha, beta)
return value
@ -200,7 +200,7 @@ def poisson(shape, mean, seed=None):
>>> mean = Tensor(1.0, mstype.float32)
>>> output = C.poisson(shape, mean, seed=5)
"""
seed1, seed2 = get_seed(seed, "poisson")
seed1, seed2 = _get_seed(seed, "poisson")
random_poisson = P.Poisson(seed1, seed2)
value = random_poisson(shape, mean)
return value