Update tutorials (#463)
--------- Co-authored-by: Dario Coscia <93731561+dario-coscia@users.noreply.github.com>
This commit is contained in:
Matteo Bertocchi
committed by
FilippoOlivo
FilippoOlivo
parent
8b797d589a
commit
bd9b49530a
58
tutorials/tutorial11/tutorial.py
vendored
58
tutorials/tutorial11/tutorial.py
vendored
@@ -13,7 +13,7 @@
|
||||
#
|
||||
# Let's start by importing useful modules, define the `SimpleODE` problem and the `PINN` solver.
|
||||
|
||||
# In[18]:
|
||||
# In[1]:
|
||||
|
||||
|
||||
## routine needed to run the notebook on Google Colab
|
||||
@@ -26,15 +26,18 @@ if IN_COLAB:
|
||||
get_ipython().system('pip install "pina-mathlab"')
|
||||
|
||||
import torch
|
||||
import warnings
|
||||
|
||||
from pina import Condition, Trainer
|
||||
from pina.solvers import PINN
|
||||
from pina.solver import PINN
|
||||
from pina.model import FeedForward
|
||||
from pina.problem import SpatialProblem
|
||||
from pina.operators import grad
|
||||
from pina.operator import grad
|
||||
from pina.domain import CartesianDomain
|
||||
from pina.equation import Equation, FixedValue
|
||||
|
||||
warnings.filterwarnings('ignore')
|
||||
|
||||
class SimpleODE(SpatialProblem):
|
||||
|
||||
output_variables = ['u']
|
||||
@@ -77,7 +80,7 @@ pinn = PINN(problem, model)
|
||||
# Till now we just followed the extact step of the previous tutorials. The `Trainer` object
|
||||
# can be initialized by simiply passing the `PINN` solver
|
||||
|
||||
# In[3]:
|
||||
# In[2]:
|
||||
|
||||
|
||||
trainer = Trainer(solver=pinn)
|
||||
@@ -96,7 +99,7 @@ trainer = Trainer(solver=pinn)
|
||||
#
|
||||
# * `accelerator = {'gpu', 'cpu', 'hpu', 'mps', 'cpu', 'ipu'}` sets the accelerator to a specific one
|
||||
|
||||
# In[5]:
|
||||
# In[3]:
|
||||
|
||||
|
||||
trainer = Trainer(solver=pinn,
|
||||
@@ -114,7 +117,7 @@ trainer = Trainer(solver=pinn,
|
||||
# We will now import `TensorBoardLogger`, do three runs of training and then visualize the results. Notice we set `enable_model_summary=False` to avoid model summary specifications (e.g. number of parameters), set it to true if needed.
|
||||
#
|
||||
|
||||
# In[7]:
|
||||
# In[4]:
|
||||
|
||||
|
||||
from pytorch_lightning.loggers import TensorBoardLogger
|
||||
@@ -131,8 +134,11 @@ for _ in range(3):
|
||||
pinn = PINN(problem, model)
|
||||
trainer = Trainer(solver=pinn,
|
||||
accelerator='cpu',
|
||||
logger=TensorBoardLogger(save_dir='simpleode'),
|
||||
enable_model_summary=False)
|
||||
logger=TensorBoardLogger(save_dir='training_log'),
|
||||
enable_model_summary=False,
|
||||
train_size=1.0,
|
||||
val_size=0.0,
|
||||
test_size=0.0)
|
||||
trainer.train()
|
||||
|
||||
|
||||
@@ -161,10 +167,11 @@ for _ in range(3):
|
||||
#
|
||||
# <!-- Suppose we want to log the accuracy on some validation poit -->
|
||||
|
||||
# In[8]:
|
||||
# In[5]:
|
||||
|
||||
|
||||
from pytorch_lightning.callbacks import Callback
|
||||
from lightning.pytorch.callbacks import Callback
|
||||
from lightning.pytorch.callbacks import EarlyStopping
|
||||
import torch
|
||||
|
||||
# define a simple callback
|
||||
@@ -180,7 +187,7 @@ class NaiveMetricTracker(Callback):
|
||||
|
||||
# Let's see the results when applyed to the `SimpleODE` problem. You can define callbacks when initializing the `Trainer` by the `callbacks` argument, which expects a list of callbacks.
|
||||
|
||||
# In[10]:
|
||||
# In[6]:
|
||||
|
||||
|
||||
model = FeedForward(
|
||||
@@ -192,14 +199,18 @@ model = FeedForward(
|
||||
pinn = PINN(problem, model)
|
||||
trainer = Trainer(solver=pinn,
|
||||
accelerator='cpu',
|
||||
logger=True,
|
||||
callbacks=[NaiveMetricTracker()], # adding a callbacks
|
||||
enable_model_summary=False,
|
||||
callbacks=[NaiveMetricTracker()]) # adding a callbacks
|
||||
train_size=1.0,
|
||||
val_size=0.0,
|
||||
test_size=0.0)
|
||||
trainer.train()
|
||||
|
||||
|
||||
# We can easily access the data by calling `trainer.callbacks[0].saved_metrics` (notice the zero representing the first callback in the list given at initialization).
|
||||
|
||||
# In[9]:
|
||||
# In[7]:
|
||||
|
||||
|
||||
trainer.callbacks[0].saved_metrics[:3] # only the first three epochs
|
||||
@@ -207,13 +218,12 @@ trainer.callbacks[0].saved_metrics[:3] # only the first three epochs
|
||||
|
||||
# PyTorch Lightning also has some built in `Callbacks` which can be used in **PINA**, [here an extensive list](https://lightning.ai/docs/pytorch/stable/extensions/callbacks.html#built-in-callbacks).
|
||||
#
|
||||
# We can for example try the `EarlyStopping` routine, which automatically stops the training when a specific metric converged (here the `mean_loss`). In order to let the training keep going forever set `max_epochs=-1`.
|
||||
# We can for example try the `EarlyStopping` routine, which automatically stops the training when a specific metric converged (here the `train_loss`). In order to let the training keep going forever set `max_epochs=-1`.
|
||||
|
||||
# In[7]:
|
||||
# In[8]:
|
||||
|
||||
|
||||
# ~2 mins
|
||||
from pytorch_lightning.callbacks import EarlyStopping
|
||||
# ~5 mins
|
||||
|
||||
model = FeedForward(
|
||||
layers=[10, 10],
|
||||
@@ -226,7 +236,7 @@ trainer = Trainer(solver=pinn,
|
||||
accelerator='cpu',
|
||||
max_epochs = -1,
|
||||
enable_model_summary=False,
|
||||
callbacks=[EarlyStopping('mean_loss')]) # adding a callbacks
|
||||
callbacks=[EarlyStopping('train_loss')]) # adding a callbacks
|
||||
trainer.train()
|
||||
|
||||
|
||||
@@ -248,11 +258,11 @@ trainer.train()
|
||||
# We will just demonstrate how to use the first two, and see the results compared to a standard training.
|
||||
# We use the [`Timer`](https://lightning.ai/docs/pytorch/stable/api/lightning.pytorch.callbacks.Timer.html#lightning.pytorch.callbacks.Timer) callback from `pytorch_lightning.callbacks` to take the times. Let's start by training a simple model without any optimization (train for 2000 epochs).
|
||||
|
||||
# In[19]:
|
||||
# In[9]:
|
||||
|
||||
|
||||
from pytorch_lightning.callbacks import Timer
|
||||
from pytorch_lightning import seed_everything
|
||||
from lightning.pytorch.callbacks import Timer
|
||||
from lightning.pytorch import seed_everything
|
||||
|
||||
# setting the seed for reproducibility
|
||||
seed_everything(42, workers=True)
|
||||
@@ -277,10 +287,10 @@ print(f'Total training time {trainer.callbacks[0].time_elapsed("train"):.5f} s')
|
||||
|
||||
# Now we do the same but with StochasticWeightAveraging
|
||||
|
||||
# In[36]:
|
||||
# In[10]:
|
||||
|
||||
|
||||
from pytorch_lightning.callbacks import StochasticWeightAveraging
|
||||
from lightning.pytorch.callbacks import StochasticWeightAveraging
|
||||
|
||||
# setting the seed for reproducibility
|
||||
seed_everything(42, workers=True)
|
||||
@@ -309,7 +319,7 @@ print(f'Total training time {trainer.callbacks[0].time_elapsed("train"):.5f} s')
|
||||
#
|
||||
# We will now now do the same but clippling the gradient to be relatively small.
|
||||
|
||||
# In[35]:
|
||||
# In[11]:
|
||||
|
||||
|
||||
# setting the seed for reproducibility
|
||||
|
||||
Reference in New Issue
Block a user