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

!2071 optimizer support loss scale for sparse situation 

Merge pull request !2071 from wangnan39/support_loss_scale_for_sparse_optimizer
This commit is contained in:
mindspore-ci-bot 2020-06-16 15:01:49 +08:00 committed by Gitee
parent 5d7b9d959e d4e3d69f37
commit 2d84011504
7 changed files with 23 additions and 62 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
mindspore/nn/optim/adam.py
View File

@ -234,8 +234,6 @@ class Adam(Optimizer):
_check_param_value(beta1, beta2, eps, weight_decay, self.cls_name)
validator.check_value_type("use_locking", use_locking, [bool], self.cls_name)
validator.check_value_type("use_nesterov", use_nesterov, [bool], self.cls_name)
validator.check_value_type("loss_scale", loss_scale, [float], self.cls_name)
validator.check_number_range("loss_scale", loss_scale, 0.0, float("inf"), Rel.INC_LEFT, self.cls_name)
self.beta1 = Tensor(beta1, mstype.float32)
self.beta2 = Tensor(beta2, mstype.float32)
@ -247,9 +245,8 @@ class Adam(Optimizer):
self.moment2 = self.parameters.clone(prefix="moment2", init='zeros')
self.hyper_map = C.HyperMap()
self.map_ = C.Map()
self.opt = P.Adam(use_locking, use_nesterov)
self.sparse_opt = P.SparseApplyAdam()
self.sparse_opt = P.SparseApplyAdam(use_locking, use_nesterov)
def construct(self, gradients):
params = self.parameters

22
mindspore/nn/optim/ftrl.py
View File

@ -41,15 +41,11 @@ def _tensor_run_opt(opt, spars_opt, learning_rate, l1, l2, lr_power, linear, gra
return success
def _check_param(initial_accum, learning_rate, lr_power, l1, l2, use_locking, loss_scale=1.0, weight_decay=0.0,
prim_name=None):
def _check_param(initial_accum, lr_power, l1, l2, use_locking, weight_decay=0.0, prim_name=None):
"""Check param."""
validator.check_value_type("initial_accum", initial_accum, [float], prim_name)
validator.check_number("initial_accum", initial_accum, 0.0, Rel.GE, prim_name)
validator.check_value_type("learning_rate", learning_rate, [float], prim_name)
validator.check_number("learning_rate", learning_rate, 0.0, Rel.GT, prim_name)
validator.check_value_type("lr_power", lr_power, [float], prim_name)
validator.check_number("lr_power", lr_power, 0.0, Rel.LE, prim_name)
@ -61,9 +57,6 @@ def _check_param(initial_accum, learning_rate, lr_power, l1, l2, use_locking, lo
validator.check_value_type("use_locking", use_locking, [bool], prim_name)
validator.check_value_type("loss_scale", loss_scale, [float], prim_name)
validator.check_number("loss_scale", loss_scale, 1.0, Rel.GE, prim_name)
validator.check_value_type("weight_decay", weight_decay, [float], prim_name)
validator.check_number("weight_decay", weight_decay, 0.0, Rel.GE, prim_name)
@ -110,21 +103,18 @@ class FTRL(Optimizer):
"""
def __init__(self, params, initial_accum=0.1, learning_rate=0.001, lr_power=-0.5, l1=0.0, l2=0.0,
use_locking=False, loss_scale=1.0, weight_decay=0.0):
super(FTRL, self).__init__(learning_rate, params)
super(FTRL, self).__init__(learning_rate, params, loss_scale=loss_scale)
if self.is_group:
raise RuntimeError(f"The {self.cls_name} optimizer cannot support group setting.")
_check_param(initial_accum, learning_rate, lr_power, l1, l2, use_locking, loss_scale, weight_decay,
self.cls_name)
_check_param(initial_accum, lr_power, l1, l2, use_locking, weight_decay, self.cls_name)
self.moments = self.parameters.clone(prefix="moments", init=initial_accum)
self.linear = self.parameters.clone(prefix="linear", init='zeros')
self.l1 = l1
self.l2 = l2
self.lr_power = lr_power
self.reciprocal_scale = 1.0 / loss_scale
self.weight_decay = weight_decay
self.decay_tf = tuple((lambda: True)() for x in self.parameters)
self.hyper_map = C.HyperMap()
self.map_ = C.Map()
self.opt = P.ApplyFtrl(use_locking=use_locking)
self.sparse_opt = P.SparseApplyFtrl(learning_rate, l1, l2, lr_power, use_locking=use_locking)
@ -132,11 +122,11 @@ class FTRL(Optimizer):
params = self.parameters
moments = self.moments
linear = self.linear
lr = self.learning_rate
if self.weight_decay > 0.0:
grads = self.hyper_map(F.partial(apply_decay, self.weight_decay), self.decay_tf, params, grads)
if self.reciprocal_scale != 1.0:
grads = self.hyper_map(F.partial(grad_scale, self.reciprocal_scale), grads)
lr = self.learning_rate
grads = self.scale_grad(grads)
success = self.map_(F.partial(ftrl_opt, self.opt, self.sparse_opt, lr, self.l1, self.l2, self.lr_power),
linear, grads, params, moments)
return success

3
mindspore/nn/optim/lazyadam.py
View File

@ -164,8 +164,6 @@ class LazyAdam(Optimizer):
_check_param_value(beta1, beta2, eps, weight_decay, self.cls_name)
validator.check_value_type("use_locking", use_locking, [bool], self.cls_name)
validator.check_value_type("use_nesterov", use_nesterov, [bool], self.cls_name)
validator.check_value_type("loss_scale", loss_scale, [float], self.cls_name)
validator.check_number_range("loss_scale", loss_scale, 1.0, float("inf"), Rel.INC_LEFT, self.cls_name)
self.beta1 = Tensor(beta1, mstype.float32)
self.beta2 = Tensor(beta2, mstype.float32)
@ -179,7 +177,6 @@ class LazyAdam(Optimizer):
self.moment2 = self.parameters.clone(prefix="moment2", init='zeros')
self.hyper_map = C.HyperMap()
self.map_ = C.Map()
self.opt = P.Adam(use_locking, use_nesterov)
self.sparse_opt = P.SparseApplyLazyAdam(use_locking, use_nesterov)

11
mindspore/nn/optim/optimizer.py
View File

@ -153,6 +153,7 @@ class Optimizer(Cell):
self.reciprocal_scale = 1.0 / loss_scale
self.exec_weight_decay = any(self.decay_flags)
self.param_length = len(self.parameters)
self.map_ = C.Map()
def decay_weight(self, gradients):
"""
@ -195,7 +196,7 @@ class Optimizer(Cell):
"""
if self.reciprocal_scale != 1.0:
gradients = self.hyper_map(F.partial(grad_scale, self.reciprocal_scale), gradients)
gradients = self.map_(F.partial(grad_scale, self.reciprocal_scale), gradients)
return gradients
@ -409,3 +410,11 @@ def tensor_grad_scale(scale, grad):
if scale == 1.0:
return grad
return grad * scale
@grad_scale.register("Number", "Tuple")
def tensor_grad_scale_with_sparse(scale, grad):
"""Get grad with scale."""
if scale == 1.0:
return grad
return grad[0], grad[1] * scale, grad[2]

36
tests/ut/python/nn/optim/test_adam.py
View File

@ -18,7 +18,6 @@ import pytest
import mindspore.nn as nn
from mindspore import Tensor, Parameter
import mindspore.common.dtype as mstype
from mindspore.common.api import _executor
from mindspore.nn import TrainOneStepCell, WithLossCell
from mindspore.nn.optim import Adam, AdamWeightDecay, AdamWeightDecayDynamicLR
@ -100,14 +99,14 @@ def test_adam_compile():
_executor.compile(train_network, inputs, label)
def test_spares_adam_compile():
def test_sparse_adam_compile():
""" test_sparse_adam_compile """
indices = Tensor(np.array([0, 1]).astype(np.int32))
label = Tensor(np.zeros([2, 1, 2]).astype(np.float32))
net = NetWithSparseGatherV2()
net.set_train()
optimizer = Adam(net.trainable_params(), learning_rate=0.1)
optimizer = Adam(net.trainable_params(), learning_rate=0.1, loss_scale=1024.0)
train_network = TrainOneStepCell(net, optimizer)
_executor.compile(train_network, indices, label)
@ -149,34 +148,3 @@ def test_adam_mindspore_with_empty_params():
net = nn.Flatten()
with pytest.raises(ValueError, match=r"Optimizer got an empty parameter list"):
AdamWeightDecay(net.get_parameters())
class TestSparseOps(nn.Cell):
"""Define sparse operator"""
def __init__(self, sparse_opt):
super(TestSparseOps, self).__init__()
self.sparse_apply_adam = sparse_opt
self.var = Parameter(Tensor(np.ones([3, 3, 3]).astype(np.float32)), name="var")
self.m = Parameter(Tensor(np.ones([3, 3, 3]).astype(np.float32)), name="m")
self.v = Parameter(Tensor(np.ones([3, 3, 3]).astype(np.float32)), name="v")
def construct(self, beta1_power, beta2_power, lr, beta1, beta2, epsilon, grad, indices):
out = self.sparse_apply_adam(self.var, self.m, self.v, beta1_power, beta2_power, lr, beta1, beta2, epsilon,
grad, indices)
return out
def test_sparse_adam():
"""test sparse operator"""
gradient = Tensor(np.random.rand(3, 3, 3).astype(np.float32))
indices = Tensor([0, 1, 2], mstype.int32)
net = TestSparseOps(P.SparseApplyAdam())
_executor.compile(net, 0.9, 0.999, 0.001, 0.9, 0.999, 1e-8, gradient, indices)
def test_sparse_lazy_adam():
"""test sparse operator"""
gradient = Tensor(np.random.rand(3, 3, 3).astype(np.float32))
indices = Tensor([0, 1, 2], mstype.int32)
net = TestSparseOps(P.SparseApplyLazyAdam())
_executor.compile(net, 0.9, 0.999, 0.001, 0.9, 0.999, 1e-8, gradient, indices)

4
tests/ut/python/nn/optim/test_ftrl.py
View File

@ -57,7 +57,7 @@ def test_ftrl():
net = Net()
net.set_train()
loss = nn.SoftmaxCrossEntropyWithLogits()
optimizer = FTRL(net.trainable_params())
optimizer = FTRL(net.trainable_params(), weight_decay=0.9, loss_scale=2.0)
net_with_loss = WithLossCell(net, loss)
train_network = TrainOneStepCell(net_with_loss, optimizer)
_executor.compile(train_network, inputs, label)
@ -70,6 +70,6 @@ def test_spares_ftrl_compile():
net = NetWithSparseGatherV2()
net.set_train()
optimizer = FTRL(net.trainable_params())
optimizer = FTRL(net.trainable_params(), loss_scale=2.0)
train_network = TrainOneStepCell(net, optimizer)
_executor.compile(train_network, indices, label)

4
tests/ut/python/nn/optim/test_lazyadam.py
View File

@ -60,7 +60,7 @@ def test_lazy_adam_compile():
net.set_train()
loss = nn.SoftmaxCrossEntropyWithLogits()
optimizer = LazyAdam(net.trainable_params(), learning_rate=0.1, weight_decay=0.9)
optimizer = LazyAdam(net.trainable_params(), learning_rate=0.1, weight_decay=0.9, loss_scale=2.0)
net_with_loss = WithLossCell(net, loss)
train_network = TrainOneStepCell(net_with_loss, optimizer)
@ -74,7 +74,7 @@ def test_spares_lazy_adam_compile():
net = NetWithSparseGatherV2()
net.set_train()
optimizer = LazyAdam(net.trainable_params(), learning_rate=0.1)
optimizer = LazyAdam(net.trainable_params(), learning_rate=0.1, loss_scale=2.0)
train_network = TrainOneStepCell(net, optimizer)
_executor.compile(train_network, indices, label)