p47068915
/
mindspore
forked from mindspore-Ecosystem/mindspore
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

!1921 Adapt TBE ops ApplyProximalAdagrad for GE. 

Merge pull request !1921 from liuxiao/ApplyProximalAdagrad-for-GE
This commit is contained in:
mindspore-ci-bot 2020-06-09 15:39:41 +08:00 committed by Gitee
parent db00ea71f8 6856c2ac7a
commit 42b0d49d13
5 changed files with 21 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
mindspore/ccsrc/transform/convert.cc
View File

@ -182,6 +182,7 @@ const char kNameBinaryCrossEntropy[] = "BinaryCrossEntropy";
const char kNameBinaryCrossEntropyGrad[] = "BinaryCrossEntropyGrad";
const char kNameSparseApplyAdagrad[] = "SparseApplyAdagrad";
const char kNameSparseApplyFtrlD[] = "SparseApplyFtrlD";
const char kNameApplyProximalAdagrad[] = "ApplyProximalAdagrad";
const char kNameAcosh[] = "Acosh";
const char kNameAcoshGrad[] = "AcoshGrad";
const char kNameFloorMod[] = "FloorMod";
@ -386,6 +387,7 @@ std::unordered_map<std::string, OpAdapterDescPtr> &DfGraphConvertor::get_adpt_ma
{string(kNameBinaryCrossEntropyGrad), ADPT_DESC(BinaryCrossEntropyGrad)},
{string(kNameSparseApplyAdagrad), ADPT_DESC(SparseApplyAdagradD)},
{string(kNameSparseApplyFtrlD), ADPT_DESC(SparseApplyFtrlD)},
{string(kNameApplyProximalAdagrad), ADPT_DESC(ApplyProximalAdagrad)},
{string(kNameAcosh), ADPT_DESC(Acosh)},
{string(kNameAcoshGrad), ADPT_DESC(AcoshGrad)},
{string(kNameFloorMod), ADPT_DESC(FloorMod)},

6
mindspore/ccsrc/transform/op_declare.cc
View File

@ -1155,6 +1155,12 @@ ATTR_MAP(SparseApplyAdagradD) = {{"lr", ATTR_DESC(lr, AnyTraits<float>())},
{"use_locking", ATTR_DESC(use_locking, AnyTraits<bool>())}};
OUTPUT_MAP(SparseApplyAdagradD) = {{0, OUTPUT_DESC(var)}};
// ApplyProximalAdagrad
INPUT_MAP(ApplyProximalAdagrad) = {{1, INPUT_DESC(var)}, {2, INPUT_DESC(accum)}, {3, INPUT_DESC(lr)},
{4, INPUT_DESC(l1)}, {5, INPUT_DESC(l2)}, {6, INPUT_DESC(grad)}};
ATTR_MAP(ApplyProximalAdagrad) = {{"use_locking", ATTR_DESC(use_locking, AnyTraits<bool>())}};
OUTPUT_MAP(ApplyProximalAdagrad) = {{0, OUTPUT_DESC(var)}};
// SparseApplyFtrlD
INPUT_MAP(SparseApplyFtrlD) = {{1, INPUT_DESC(var)},
{2, INPUT_DESC(accum)},

2
mindspore/ccsrc/transform/op_declare.h
View File

@ -442,6 +442,8 @@ DECLARE_OP_ADAPTER(BinaryCrossEntropyGrad)
DECLARE_OP_USE_OUTPUT(BinaryCrossEntropyGrad)
DECLARE_OP_ADAPTER(SparseApplyAdagradD)
DECLARE_OP_USE_OUTPUT(SparseApplyAdagradD)
DECLARE_OP_ADAPTER(ApplyProximalAdagrad)
DECLARE_OP_USE_OUTPUT(ApplyProximalAdagrad)
DECLARE_OP_ADAPTER(SpaceToDepth)
DECLARE_OP_USE_OUTPUT(SpaceToDepth)
DECLARE_OP_ADAPTER(DepthToSpace)

2
mindspore/ops/operations/nn_ops.py
View File

@ -3149,7 +3149,7 @@ class SparseApplyFtrl(PrimitiveWithInfer):
validator.check_value_type("l1", l1, [float], self.name)
validator.check_value_type("l2", l2, [float], self.name)
validator.check_value_type("lr_power", lr_power, [float], self.name)
self.lr = validator.check_number("lr", lr, 0.0, Rel.GT, self.name)
self.lr = validator.check_number_range("lr", lr, 0.0, float("inf"), Rel.INC_LEFT, self.name)
self.l1 = validator.check_number("l1", l1, 0.0, Rel.GE, self.name)
self.l2 = validator.check_number("l2", l2, 0.0, Rel.GE, self.name)
self.lr_power = validator.check_number("lr_power", lr_power, 0, Rel.LE, self.name)

16
tests/ut/python/ops/test_ops.py
View File

@ -244,12 +244,14 @@ class SparseApplyProximalAdagradNet(nn.Cell):
def __init__(self):
super(SparseApplyProximalAdagradNet, self).__init__()
self.sparse_apply_proximal_adagrad = P.SparseApplyProximalAdagrad()
self.var = Parameter(Tensor(np.random.rand(3, 3).astype(np.float32)), name="var")
self.accum = Parameter(Tensor(np.random.rand(3, 3).astype(np.float32)), name="accum")
self.lr = 0.01
self.l1 = 0.0
self.l2 = 0.0
def construct(self, var, accum, grad, indices):
out = self.sparse_apply_proximal_adagrad(var, accum, self.lr, self.l1, self.l2, grad, indices)
def construct(self, grad, indices):
out = self.sparse_apply_proximal_adagrad(self.var, self.accum, self.lr, self.l1, self.l2, grad, indices)
return out
@ -257,12 +259,14 @@ class ApplyProximalAdagradNet(nn.Cell):
def __init__(self):
super(ApplyProximalAdagradNet, self).__init__()
self.apply_proximal_adagrad = P.ApplyProximalAdagrad()
self.var = Parameter(Tensor(np.random.rand(3, 3).astype(np.float32)), name="var")
self.accum = Parameter(Tensor(np.random.rand(3, 3).astype(np.float32)), name="accum")
self.lr = 0.01
self.l1 = 0.0
self.l2 = 0.0
def construct(self, var, accum, grad):
out = self.apply_proximal_adagrad(var, accum, self.lr, self.l1, self.l2, grad)
def construct(self, grad):
out = self.apply_proximal_adagrad(self.var, self.accum, self.lr, self.l1, self.l2, grad)
return out
@ -1061,11 +1065,11 @@ test_case_nn_ops = [
'skip': ['backward']}),
('ApplyProximalAdagrad', {
'block': ApplyProximalAdagradNet(),
'desc_inputs': [[3, 3], [3, 3], [3, 3]],
'desc_inputs': [[3, 3]],
'skip': ['backward']}),
('SparseApplyProximalAdagrad', {
'block': SparseApplyProximalAdagradNet(),
'desc_inputs': [[3, 3], [3, 3], [3, 3], Tensor(np.ones((3,), np.int32))],
'desc_inputs': [[3, 3], Tensor(np.ones((3,), np.int32))],
'skip': ['backward']}),
('Flatten_1', {
'block': NetForFlatten(),