folivo/PINA
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

tut10

Browse Source
This commit is contained in:
Dario Coscia
2024-03-14 19:16:48 +01:00
committed by Nicola Demo
parent ada9643c11
commit 98f7694d6f
11 changed files with 1171 additions and 78 deletions
Download Patch File Download Diff File Expand all files Collapse all files

160
tests/test_model/test_avno.py
View File

@@ -1,62 +1,146 @@
import torch
from pina.model import AveragingNeuralOperator
from pina import LabelTensor
import pytest
output_numb_fields = 5
batch_size = 15
n_layers = 4
embedding_dim = 24
func = torch.nn.Tanh
coordinates_indices = ['p']
field_indices = ['v']
def test_constructor():
input_numb_fields = 1
output_numb_fields = 1
#minimuum constructor
AveragingNeuralOperator(input_numb_fields,
output_numb_fields,
coordinates_indices=['p'],
field_indices=['v'])
# working constructor
lifting_net = torch.nn.Linear(len(coordinates_indices) + len(field_indices),
embedding_dim)
projecting_net = torch.nn.Linear(embedding_dim + len(field_indices),
len(field_indices))
AveragingNeuralOperator(
lifting_net=lifting_net,
projecting_net=projecting_net,
coordinates_indices=coordinates_indices,
field_indices=field_indices,
n_layers=n_layers,
func=func)
#all constructor
AveragingNeuralOperator(input_numb_fields,
output_numb_fields,
inner_size=5,
n_layers=5,
func=torch.nn.ReLU,
coordinates_indices=['p'],
field_indices=['v'])
# not working constructor
with pytest.raises(ValueError):
AveragingNeuralOperator(
lifting_net=lifting_net,
projecting_net=projecting_net,
coordinates_indices=coordinates_indices,
field_indices=field_indices,
n_layers=3.2, # wrong
func=func)
AveragingNeuralOperator(
lifting_net=lifting_net,
projecting_net=projecting_net,
coordinates_indices=coordinates_indices,
field_indices=field_indices,
n_layers=n_layers,
func=1) # wrong
AveragingNeuralOperator(
lifting_net=[0], # wrong
projecting_net=projecting_net,
coordinates_indices=coordinates_indices,
field_indices=field_indices,
n_layers=n_layers,
func=func)
AveragingNeuralOperator(
lifting_net=lifting_net,
projecting_net=[0], # wront
coordinates_indices=coordinates_indices,
field_indices=field_indices,
n_layers=n_layers,
func=func)
AveragingNeuralOperator(
lifting_net=lifting_net,
projecting_net=projecting_net,
coordinates_indices=[0], #wrong
field_indices=field_indices,
n_layers=n_layers,
func=func)
AveragingNeuralOperator(
lifting_net=lifting_net,
projecting_net=projecting_net,
coordinates_indices=coordinates_indices,
field_indices=[0], #wrong
n_layers=n_layers,
func=func)
lifting_net = torch.nn.Linear(len(coordinates_indices),
embedding_dim)
AveragingNeuralOperator(
lifting_net=lifting_net,
projecting_net=projecting_net,
coordinates_indices=coordinates_indices,
field_indices=field_indices,
n_layers=n_layers,
func=func)
lifting_net = torch.nn.Linear(len(coordinates_indices) + len(field_indices),
embedding_dim)
projecting_net = torch.nn.Linear(embedding_dim,
len(field_indices))
AveragingNeuralOperator(
lifting_net=lifting_net,
projecting_net=projecting_net,
coordinates_indices=coordinates_indices,
field_indices=field_indices,
n_layers=n_layers,
func=func)
def test_forward():
input_numb_fields = 1
output_numb_fields = 1
dimension = 1
lifting_net = torch.nn.Linear(len(coordinates_indices) + len(field_indices),
embedding_dim)
projecting_net = torch.nn.Linear(embedding_dim + len(field_indices),
len(field_indices))
avno=AveragingNeuralOperator(
lifting_net=lifting_net,
projecting_net=projecting_net,
coordinates_indices=coordinates_indices,
field_indices=field_indices,
n_layers=n_layers,
func=func)
input_ = LabelTensor(
torch.rand(batch_size, 1000, input_numb_fields + dimension), ['p', 'v'])
ano = AveragingNeuralOperator(input_numb_fields,
output_numb_fields,
dimension=dimension,
coordinates_indices=['p'],
field_indices=['v'])
out = ano(input_)
torch.rand(batch_size, 100,
len(coordinates_indices) + len(field_indices)), ['p', 'v'])
out = avno(input_)
assert out.shape == torch.Size(
[batch_size, input_.shape[1], output_numb_fields])
[batch_size, input_.shape[1], len(field_indices)])
def test_backward():
input_numb_fields = 1
dimension = 1
output_numb_fields = 1
lifting_net = torch.nn.Linear(len(coordinates_indices) + len(field_indices),
embedding_dim)
projecting_net = torch.nn.Linear(embedding_dim + len(field_indices),
len(field_indices))
avno=AveragingNeuralOperator(
lifting_net=lifting_net,
projecting_net=projecting_net,
coordinates_indices=coordinates_indices,
field_indices=field_indices,
n_layers=n_layers,
func=func)
input_ = LabelTensor(
torch.rand(batch_size, 1000, dimension + input_numb_fields),
['p', 'v'])
torch.rand(batch_size, 100,
len(coordinates_indices) + len(field_indices)), ['p', 'v'])
input_ = input_.requires_grad_()
avno = AveragingNeuralOperator(input_numb_fields,
output_numb_fields,
dimension=dimension,
coordinates_indices=['p'],
field_indices=['v'])
out = avno(input_)
tmp = torch.linalg.norm(out)
tmp.backward()
grad = input_.grad
assert grad.shape == torch.Size(
[batch_size, input_.shape[1], dimension + input_numb_fields])
[batch_size, input_.shape[1],
len(coordinates_indices) + len(field_indices)])