Update tutorial 1,3,4,9 plots

tutorials/tutorial1/tutorial.py

@@ -38,7 +38,7 @@
 # 
 # ```python
 # from pina.problem import SpatialProblem
-# from pina.geometry import CartesianProblem
+# from pina.domain import CartesianProblem
 # 
 # class SimpleODE(SpatialProblem):
 #     
@@ -233,7 +233,6 @@ trainer.train()
 
 # inspecting final loss
 trainer.logged_metrics
-print(type(problem.truth_solution))
 
 
 # By using `matplotlib` we can also do some qualitative plots of the solution. 
@@ -260,7 +259,6 @@ list_ = [
             idx for idx, s in enumerate(trainer.callbacks)
             if isinstance(s, MetricTracker)
         ]
-print(list_[0])
 trainer_metrics = trainer.callbacks[list_[0]].metrics
 
 loss = trainer_metrics['val_loss']

tutorials/tutorial3/tutorial.py

@@ -9,7 +9,7 @@
 # 
 # First of all, some useful imports.
 
-# In[12]:
+# In[1]:
 
 
 ## routine needed to run the notebook on Google Colab
@@ -50,7 +50,7 @@ from pina import Condition, LabelTensor
 
 # Now, the wave problem is written in PINA code as a class, inheriting from `SpatialProblem` and `TimeDependentProblem` since we deal with spatial, and time dependent variables. The equations are written as `conditions` that should be satisfied in the corresponding domains. `truth_solution` is the exact solution which will be compared with the predicted one.
 
-# In[13]:
+# In[2]:
 
 
 class Wave(TimeDependentProblem, SpatialProblem):
@@ -96,7 +96,7 @@ problem = Wave()
 # 
 # where $NN$ is the neural net output. This neural network takes as input the coordinates (in this case $x$, $y$ and $t$) and provides the unknown field $u$. By construction, it is zero on the boundaries. The residuals of the equations are evaluated at several sampling points (which the user can manipulate using the method `discretise_domain`) and the loss minimized by the neural network is the sum of the residuals.
 
-# In[14]:
+# In[3]:
 
 
 class HardMLP(torch.nn.Module):
@@ -120,7 +120,7 @@ class HardMLP(torch.nn.Module):
 
 # In this tutorial, the neural network is trained for 1000 epochs with a learning rate of 0.001 (default in `PINN`). Training takes approximately 3 minutes.
 
-# In[15]:
+# In[4]:
 
 
 # generate the data
@@ -136,16 +136,13 @@ trainer.train()
 
 # Notice that the loss on the boundaries of the spatial domain is exactly zero, as expected! After the training is completed one can now plot some results using the `Plotter` class of **PINA**.
 
-# In[16]:
+# In[5]:
 
 
-#plotter = Plotter()
-
+method='contourf'
 # plotting at fixed time t = 0.0
 print('Plotting at t=0')
-#plotter.plot(pinn, fixed_variables={'t': 0.0})
 fixed_variables={'t': 0.0}
-method='contourf'
 pts = pinn.problem.spatial_domain.sample(256, 'grid', variables=['x','y'])
 grids = [p_.reshape(256, 256) for p_ in pts.extract(['x','y']).T]
 fixed_pts = torch.ones(pts.shape[0], len(fixed_variables))
@@ -228,7 +225,7 @@ ax[2].title.set_text('Residual')
 # 
 # Let us build the network first
 
-# In[17]:
+# In[6]:
 
 
 class HardMLPtime(torch.nn.Module):
@@ -251,7 +248,7 @@ class HardMLPtime(torch.nn.Module):
 
 # Now let's train with the same configuration as thre previous test
 
-# In[18]:
+# In[7]:
 
 
 # generate the data
@@ -267,16 +264,12 @@ trainer.train()
 
 # We can clearly see that the loss is way lower now. Let's plot the results
 
-# In[19]:
+# In[8]:
 
 
-#plotter = Plotter()
-
 # plotting at fixed time t = 0.0
 print('Plotting at t=0')
-#plotter.plot(pinn, fixed_variables={'t': 0.0})
 fixed_variables={'t': 0.0}
-method='contourf'
 pts = pinn.problem.spatial_domain.sample(256, 'grid', variables=['x','y'])
 grids = [p_.reshape(256, 256) for p_ in pts.extract(['x','y']).T]
 fixed_pts = torch.ones(pts.shape[0], len(fixed_variables))

tutorials/tutorial4/tutorial.py

@@ -25,10 +25,10 @@ import torch
 import matplotlib.pyplot as plt 
 plt.style.use('tableau-colorblind10')
 from pina.problem import AbstractProblem
-from pina.solvers import SupervisedSolver
+from pina.solver import SupervisedSolver
 from pina.trainer import Trainer
 from pina import Condition, LabelTensor
-from pina.model.layers import ContinuousConvBlock 
+from pina.model.block import ContinuousConvBlock 
 import torchvision # for MNIST dataset
 from pina.model import FeedForward # for building AE and MNIST classification