Skip to content

fix rmsprop_ yaml bug #49026

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Dec 13, 2022
+45 −26
Merged

fix rmsprop_ yaml bug #49026

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
98a89f8
fix rmsprop_ yaml bug
wanghuancoder Dec 12, 2022
0d0a170
refine
wanghuancoder Dec 12, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion paddle/phi/api/yaml/legacy_ops.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1685,7 +1685,7 @@
kernel :
func : rmsprop {dense, dense, dense, dense, dense, dense -> dense, dense, dense, dense}
rmsprop_dense_param_sparse_grad {dense, dense, selected_rows, dense, dense, dense -> dense, dense, dense, dense}
optional : mean_grad
optional : mean_grad
inplace : (param -> param_out), (moment -> moment_out), (mean_square -> mean_square_out), (mean_grad -> mean_grad_out)

- op : rnn
Expand Down
69 changes: 44 additions & 25 deletions python/paddle/optimizer/rmsprop.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,7 +12,10 @@
# See the License for the specific language governing permissions and
# limitations under the License.

from paddle import _C_ops

from ..fluid import framework
from ..fluid.framework import in_dygraph_mode
from .optimizer import Optimizer

__all__ = []
Expand Down Expand Up @@ -216,32 +219,48 @@ def _append_optimize_op(self, block, param_and_grad):
mean_grad_acc = self._get_accumulator(
self._mean_grad_acc_str, param_and_grad[0]
)
rmsprop_op = block.append_op(
type=self.type,
inputs={
"Param": param_and_grad[0],
"Grad": param_and_grad[1],
"Moment": momentum_acc,
"MeanSquare": mean_square_acc,
"MeanGrad": mean_grad_acc,
"LearningRate": self._create_param_lr(param_and_grad),
},
outputs={
"ParamOut": param_and_grad[0],
"MomentOut": momentum_acc,
"MeanSquareOut": mean_square_acc,
"MeanGradOut": mean_grad_acc,
},
attrs={
"epsilon": self._epsilon,
"decay": self._rho,
"momentum": self._momentum,
"centered": self._centered,
},
stop_gradient=True,
)

return rmsprop_op
if in_dygraph_mode():
_C_ops.rmsprop_(
param_and_grad[0],
mean_square_acc,
param_and_grad[1],
momentum_acc,
self._create_param_lr(param_and_grad),
mean_grad_acc,
self._epsilon,
self._rho,
self._momentum,
self._centered,
)
return None
else:
rmsprop_op = block.append_op(
type=self.type,
inputs={
"Param": param_and_grad[0],
"Grad": param_and_grad[1],
"Moment": momentum_acc,
"MeanSquare": mean_square_acc,
"MeanGrad": mean_grad_acc,
"LearningRate": self._create_param_lr(param_and_grad),
},
outputs={
"ParamOut": param_and_grad[0],
"MomentOut": momentum_acc,
"MeanSquareOut": mean_square_acc,
"MeanGradOut": mean_grad_acc,
},
attrs={
"epsilon": self._epsilon,
"decay": self._rho,
"momentum": self._momentum,
"centered": self._centered,
},
stop_gradient=True,
)

return rmsprop_op

def _update_param_group(self, parameters):
self._epsilon = parameters.get('epsilon', self._default_dict['epsilon'])
Expand Down