Skip to content
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

Jump to bottom

[neural-networks] restructured training of neural networks #1274

Merged
merged 7 commits into from Apr 22, 2021
Merged

[neural-networks] restructured training of neural networks #1274

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
1d2cb34
[neural-networks] moved training routine out of reductor
HenKlei Mar 17, 2021
eb6bd18
[neural-networks] layers_sizes -> layer_sizes
HenKlei Mar 26, 2021
cea5abd
[neural-networks] use dimension of parameters instead of length
HenKlei Mar 29, 2021
c8a06af
[neural-networks] extended documentation of training functions
HenKlei Apr 9, 2021
3d1642c
[neural-networks] allow numpy arrays as training data
HenKlei Apr 13, 2021
1890752
[neural-networks] allow pyMOR structures as training data
HenKlei Apr 21, 2021
01a9c28
[neural-networks] adjusted documentation of training routine
HenKlei Apr 21, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
18 changes: 9 additions & 9 deletions src/pymor/models/neural_network.py
View file
Open in desktop
Expand Up @@ -67,7 +67,7 @@ def __init__(self, neural_network, parameters={}, output_functional=None,
def _compute_solution(self, mu=None, **kwargs):

# convert the parameter `mu` into a form that is usable in PyTorch
converted_input = torch.from_numpy(mu.to_numpy()).double()
converted_input = torch.DoubleTensor(mu.to_numpy())
# obtain (reduced) coordinates by forward pass of the parameter values
# through the neural network
U = self.neural_network(converted_input).data.numpy()
Expand Down Expand Up @@ -141,7 +141,7 @@ def _compute_solution(self, mu=None, **kwargs):
for i in range(self.nt):
mu = mu.with_(t=t)
# convert the parameter `mu` into a form that is usable in PyTorch
converted_input = torch.from_numpy(mu.to_numpy()).double()
converted_input = torch.DoubleTensor(mu.to_numpy())
# obtain (reduced) coordinates by forward pass of the parameter values
# through the neural network
result_neural_network = self.neural_network(converted_input).data.numpy()
Expand All @@ -160,24 +160,24 @@ class FullyConnectedNN(nn.Module, BasicObject):

Parameters
----------
layers_sizes
layer_sizes
List of sizes (i.e. number of neurons) for the layers of the neural network.
activation_function
Function to use as activation function between the single layers.
"""

def __init__(self, layers_sizes, activation_function=torch.tanh):
def __init__(self, layer_sizes, activation_function=torch.tanh):
super().__init__()

if layers_sizes is None or not len(layers_sizes) > 1 or not all(size >= 1 for size in layers_sizes):
if layer_sizes is None or not len(layer_sizes) > 1 or not all(size >= 1 for size in layer_sizes):
raise ValueError

self.input_dimension = layers_sizes[0]
self.output_dimension = layers_sizes[-1]
self.input_dimension = layer_sizes[0]
self.output_dimension = layer_sizes[-1]

self.layers = nn.ModuleList()
self.layers.extend([nn.Linear(int(layers_sizes[i]), int(layers_sizes[i+1]))
for i in range(len(layers_sizes) - 1)])
self.layers.extend([nn.Linear(int(layer_sizes[i]), int(layer_sizes[i+1]))
for i in range(len(layer_sizes) - 1)])

self.activation_function = activation_function

Expand Down