Skip to content

Backend paddle: modify fnn #1922

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 3 commits into from
Dec 18, 2024
Merged

Backend paddle: modify fnn #1922

Changes from 2 commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
ee1e39f
Backend paddle: modify fnn
lijialin03 Dec 18, 2024
d8ebf78
update dropout layers and add regularization parameter for pfnn (only…
lijialin03 Dec 18, 2024
fd3efb0
update code 1
lijialin03 Dec 18, 2024
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
52 changes: 37 additions & 15 deletions deepxde/nn/paddle/fnn.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,12 +3,20 @@
from .nn import NN
from .. import activations
from .. import initializers
from .. import regularizers


class FNN(NN):
"""Fully-connected neural network."""

def __init__(self, layer_sizes, activation, kernel_initializer):
def __init__(
self,
layer_sizes,
activation,
kernel_initializer,
regularization=None,
dropout_rate=0.0,
):
super().__init__()
if isinstance(activation, list):
if not (len(layer_sizes) - 1) == len(activation):
Expand All @@ -20,6 +28,13 @@ def __init__(self, layer_sizes, activation, kernel_initializer):
self.activation = activations.get(activation)
initializer = initializers.get(kernel_initializer)
initializer_zero = initializers.get("zeros")
self.regularizer = regularizers.get(regularization)
self.dropout_rate = dropout_rate
self.dropouts = [
paddle.nn.Dropout(p=dropout_rate)
for _ in range(1, len(layer_sizes) - 1)
if dropout_rate > 0.0
]

self.linears = paddle.nn.LayerList()
for i in range(1, len(layer_sizes)):
Expand All @@ -37,6 +52,8 @@ def forward(self, inputs):
if isinstance(self.activation, list)
else self.activation(linear(x))
)
if self.dropout_rate > 0.0:
x = self.dropouts[j](x)
x = self.linears[-1](x)
if self._output_transform is not None:
x = self._output_transform(inputs, x)
Expand All @@ -58,11 +75,14 @@ class PFNN(NN):
kernel_initializer: Initializer for the kernel weights matrix.
"""

def __init__(self, layer_sizes, activation, kernel_initializer):
def __init__(
self, layer_sizes, activation, kernel_initializer, regularization=None
):
super().__init__()
self.activation = activations.get(activation)
initializer = initializers.get(kernel_initializer)
initializer_zero = initializers.get("zeros")
self.regularizer = regularizers.get(regularization)

if len(layer_sizes) <= 1:
raise ValueError("must specify input and output sizes")
Expand All @@ -73,7 +93,6 @@ def __init__(self, layer_sizes, activation, kernel_initializer):

n_output = layer_sizes[-1]


def make_linear(n_input, n_output):
linear = paddle.nn.Linear(n_input, n_output)
initializer(linear.weight)
Expand All @@ -92,18 +111,22 @@ def make_linear(n_input, n_output):
if isinstance(prev_layer_size, (list, tuple)):
# e.g. [8, 8, 8] -> [16, 16, 16]
self.layers.append(
paddle.nn.LayerList([
make_linear(prev_layer_size[j], curr_layer_size[j])
for j in range(n_output)
])
paddle.nn.LayerList(
[
make_linear(prev_layer_size[j], curr_layer_size[j])
for j in range(n_output)
]
)
)
else:
# e.g. 64 -> [8, 8, 8]
self.layers.append(
paddle.nn.LayerList([
make_linear(prev_layer_size, curr_layer_size[j])
for j in range(n_output)
])
paddle.nn.LayerList(
[
make_linear(prev_layer_size, curr_layer_size[j])
for j in range(n_output)
]
)
)
else: # e.g. 64 -> 64
if not isinstance(prev_layer_size, int):
Expand All @@ -115,10 +138,9 @@ def make_linear(n_input, n_output):
# output layers
if isinstance(layer_sizes[-2], (list, tuple)): # e.g. [3, 3, 3] -> 3
self.layers.append(
paddle.nn.LayerList([
make_linear(layer_sizes[-2][j], 1)
for j in range(n_output)
])
paddle.nn.LayerList(
[make_linear(layer_sizes[-2][j], 1) for j in range(n_output)]
)
)
else:
self.layers.append(make_linear(layer_sizes[-2], n_output))
Expand Down
Loading