Module ablation.pytorch_model
pytorch_model.py About: Pytorch model and datamodule
Expand source code
"""
pytorch_model.py
About: Pytorch model and datamodule
"""
import os
from copy import copy
from typing import Optional
import numpy as np
import torch
from pytorch_lightning import (
LightningDataModule,
LightningModule,
Trainer,
seed_everything,
)
from pytorch_lightning.callbacks import ModelCheckpoint
from pytorch_lightning.callbacks.early_stopping import EarlyStopping
from torch import nn
from torch.utils.data import DataLoader, TensorDataset
from .dataset import NumpyDataset, split_dataset
from .utils.logging import logger as exp_logger
from .utils.model import _as_numpy, _torch_float
class LinearModel(nn.Module):
def __init__(self, input_size, n_classes):
super().__init__()
self.net = nn.Linear(input_size, n_classes)
def forward(self, x):
return self.net(x)
class NNModel(nn.Module):
def __init__(self, input_size, n_classes):
super().__init__()
self.net = nn.Sequential(
nn.Linear(input_size, input_size * 2),
nn.ReLU(),
nn.BatchNorm1d(input_size * 2),
nn.Dropout(p=0.25),
nn.Linear(input_size * 2, input_size),
nn.ReLU(),
nn.BatchNorm1d(input_size),
nn.Dropout(p=0.25),
nn.Linear(input_size, n_classes),
)
def forward(self, x):
return self.net(x)
class Classifier(LightningModule):
def __init__(self, input_size, n_classes, model_type="nn"):
super().__init__()
self.save_hyperparameters()
output_size = n_classes if self.hparams.n_classes > 2 else 1
self.model = (
NNModel(input_size, output_size)
if model_type == "nn"
else LinearModel(input_size, output_size)
)
self.criterion = (
nn.CrossEntropyLoss() if self.hparams.n_classes > 2 else nn.BCELoss()
)
def forward(self, x):
logits = self.model(x)
if self.hparams.n_classes > 2:
return torch.softmax(logits, -1)
return torch.sigmoid(logits)
def predict_numpy(self, x: np.ndarray):
return _as_numpy(self.predict(_torch_float(x, device=self.device)))
def _step(self, batch, batch_idx):
x, y = batch
prob = self.forward(x).squeeze(-1)
loss = self.criterion(prob, y)
return loss
def training_step(self, batch, batch_idx):
loss = self._step(batch, batch_idx)
self.log("loss", loss)
return loss
def validation_step(self, batch, batch_idx):
loss = self._step(batch, batch_idx)
self.log("val_loss", loss, on_step=False, on_epoch=True)
return loss
def test_step(self, batch, batch_idx):
loss = self._step(batch, batch_idx)
self.log("test_loss", loss, on_step=False, on_epoch=True)
return loss
def configure_optimizers(self):
return torch.optim.Adam(self.model.parameters())
class TensorDataModule(LightningDataModule):
def __init__(
self,
dataset: NumpyDataset,
batch_size: int = None,
shuffle_labels: bool = False,
):
"""Data module for training models
Args:
dataset (NumpyDataset): numpy dataset
batch_size (int): batch size. Defaults to None.
shuffle_labels (bool): corrupt y labels by permuting them. Defaults to False.
"""
super().__init__()
self.n_classes = dataset.n_classes
dataset = self._corrupt_dataset(dataset, shuffle_labels)
X_train, y_train, X_val, y_val = split_dataset(
dataset.X_train,
dataset.y_train,
test_perc=0.1,
)
self.batch_size = (
int(np.sqrt(len(X_train))) if batch_size is None else batch_size
)
self.X_train, self.y_train = self.convert(X_train, y_train)
self.X_val, self.y_val = self.convert(X_val, y_val)
self.X_test, self.y_test = self.convert(dataset.X_test, dataset.y_test)
def _corrupt_dataset(self, dataset, shuffle_labels):
new_dataset = copy(dataset)
if shuffle_labels:
new_dataset.y_train = np.random.permutation(new_dataset.y_train)
return new_dataset
def convert(self, X, y):
X = torch.tensor(X).float()
y = torch.tensor(y)
y = y.float() if self.n_classes == 2 else y.long()
return X, y
def train_dataloader(self):
return DataLoader(
TensorDataset(self.X_train, self.y_train),
batch_size=self.batch_size,
)
def val_dataloader(self):
return DataLoader(
TensorDataset(self.X_val, self.y_val),
batch_size=self.batch_size,
)
def test_dataloader(self):
return DataLoader(
TensorDataset(self.X_test, self.y_test),
batch_size=self.batch_size,
)
def train(
data: NumpyDataset,
path,
max_epochs=100,
model_type="nn",
prefix="model",
shuffle_labels=False,
random_state=42,
log=True,
):
seed_everything(random_state)
datamodule = TensorDataModule(dataset=data, shuffle_labels=shuffle_labels)
model = Classifier(data.X_train.shape[1], data.n_classes, model_type=model_type)
if log:
trainer = Trainer(
deterministic=True,
max_epochs=max_epochs,
callbacks=[
EarlyStopping(monitor="val_loss", patience=5),
ModelCheckpoint(
monitor="val_loss",
dirpath=path,
filename=os.path.join(prefix, "checkpoint"),
save_top_k=1,
verbose=True,
mode="min",
),
],
)
else:
trainer = Trainer(
max_epochs=max_epochs,
logger=False,
enable_checkpointing=False,
deterministic=True,
)
trainer.fit(model, datamodule)
exp_logger.info(
f"{prefix} test loss: {trainer.test(model, datamodule, ckpt_path='best')[0]['test_loss']}"
)
return load_model(path, prefix)
def load_model(path, prefix="model"):
return Classifier.load_from_checkpoint(
os.path.join(path, prefix, "checkpoint.ckpt")
).eval()
Functions
def load_model(path, prefix='model')
-
Expand source code
def load_model(path, prefix="model"): return Classifier.load_from_checkpoint( os.path.join(path, prefix, "checkpoint.ckpt") ).eval()
def train(data: NumpyDataset, path, max_epochs=100, model_type='nn', prefix='model', shuffle_labels=False, random_state=42, log=True)
-
Expand source code
def train( data: NumpyDataset, path, max_epochs=100, model_type="nn", prefix="model", shuffle_labels=False, random_state=42, log=True, ): seed_everything(random_state) datamodule = TensorDataModule(dataset=data, shuffle_labels=shuffle_labels) model = Classifier(data.X_train.shape[1], data.n_classes, model_type=model_type) if log: trainer = Trainer( deterministic=True, max_epochs=max_epochs, callbacks=[ EarlyStopping(monitor="val_loss", patience=5), ModelCheckpoint( monitor="val_loss", dirpath=path, filename=os.path.join(prefix, "checkpoint"), save_top_k=1, verbose=True, mode="min", ), ], ) else: trainer = Trainer( max_epochs=max_epochs, logger=False, enable_checkpointing=False, deterministic=True, ) trainer.fit(model, datamodule) exp_logger.info( f"{prefix} test loss: {trainer.test(model, datamodule, ckpt_path='best')[0]['test_loss']}" ) return load_model(path, prefix)
Classes
class Classifier (input_size, n_classes, model_type='nn')
-
Hooks to be used in LightningModule.
Expand source code
class Classifier(LightningModule): def __init__(self, input_size, n_classes, model_type="nn"): super().__init__() self.save_hyperparameters() output_size = n_classes if self.hparams.n_classes > 2 else 1 self.model = ( NNModel(input_size, output_size) if model_type == "nn" else LinearModel(input_size, output_size) ) self.criterion = ( nn.CrossEntropyLoss() if self.hparams.n_classes > 2 else nn.BCELoss() ) def forward(self, x): logits = self.model(x) if self.hparams.n_classes > 2: return torch.softmax(logits, -1) return torch.sigmoid(logits) def predict_numpy(self, x: np.ndarray): return _as_numpy(self.predict(_torch_float(x, device=self.device))) def _step(self, batch, batch_idx): x, y = batch prob = self.forward(x).squeeze(-1) loss = self.criterion(prob, y) return loss def training_step(self, batch, batch_idx): loss = self._step(batch, batch_idx) self.log("loss", loss) return loss def validation_step(self, batch, batch_idx): loss = self._step(batch, batch_idx) self.log("val_loss", loss, on_step=False, on_epoch=True) return loss def test_step(self, batch, batch_idx): loss = self._step(batch, batch_idx) self.log("test_loss", loss, on_step=False, on_epoch=True) return loss def configure_optimizers(self): return torch.optim.Adam(self.model.parameters())
Ancestors
- pytorch_lightning.core.module.LightningModule
- lightning_lite.utilities.device_dtype_mixin._DeviceDtypeModuleMixin
- pytorch_lightning.core.mixins.hparams_mixin.HyperparametersMixin
- pytorch_lightning.core.saving.ModelIO
- pytorch_lightning.core.hooks.ModelHooks
- pytorch_lightning.core.hooks.DataHooks
- pytorch_lightning.core.hooks.CheckpointHooks
- torch.nn.modules.module.Module
Class variables
var dump_patches : bool
var training : bool
Methods
def configure_optimizers(self)
-
Choose what optimizers and learning-rate schedulers to use in your optimization. Normally you'd need one. But in the case of GANs or similar you might have multiple.
Return
Any of these 6 options.
- Single optimizer.
- List or Tuple of optimizers.
- Two lists - The first list has multiple optimizers, and the second has multiple LR schedulers
(or multiple
lr_scheduler_config
). - Dictionary, with an
"optimizer"
key, and (optionally) a"lr_scheduler"
key whose value is a single LR scheduler orlr_scheduler_config
. - Tuple of dictionaries as described above, with an optional
"frequency"
key. - None - Fit will run without any optimizer.
The
lr_scheduler_config
is a dictionary which contains the scheduler and its associated configuration. The default configuration is shown below... code-block:: python
lr_scheduler_config = { # REQUIRED: The scheduler instance "scheduler": lr_scheduler, # The unit of the scheduler's step size, could also be 'step'. # 'epoch' updates the scheduler on epoch end whereas 'step' # updates it after a optimizer update. "interval": "epoch", # How many epochs/steps should pass between calls to # <code>scheduler.step()</code>. 1 corresponds to updating the learning # rate after every epoch/step. "frequency": 1, # Metric to to monitor for schedulers like <code>ReduceLROnPlateau</code> "monitor": "val_loss", # If set to <code>True</code>, will enforce that the value specified 'monitor' # is available when the scheduler is updated, thus stopping # training if not found. If set to <code>False</code>, it will only produce a warning "strict": True, # If using the <code>LearningRateMonitor</code> callback to monitor the # learning rate progress, this keyword can be used to specify # a custom logged name "name": None, }
When there are schedulers in which the
.step()
method is conditioned on a value, such as the :class:torch.optim.lr_scheduler.ReduceLROnPlateau
scheduler, Lightning requires that thelr_scheduler_config
contains the keyword"monitor"
set to the metric name that the scheduler should be conditioned on.Testcode
The ReduceLROnPlateau scheduler requires a monitor
def configure_optimizers(self): optimizer = Adam(…) return { "optimizer": optimizer, "lr_scheduler": { "scheduler": ReduceLROnPlateau(optimizer, …), "monitor": "metric_to_track", "frequency": "indicates how often the metric is updated" # If "monitor" references validation metrics, then "frequency" should be set to a # multiple of "trainer.check_val_every_n_epoch". }, }
In the case of two optimizers, only one using the ReduceLROnPlateau scheduler
def configure_optimizers(self): optimizer1 = Adam(…) optimizer2 = SGD(…) scheduler1 = ReduceLROnPlateau(optimizer1, …) scheduler2 = LambdaLR(optimizer2, …) return ( { "optimizer": optimizer1, "lr_scheduler": { "scheduler": scheduler1, "monitor": "metric_to_track", }, }, {"optimizer": optimizer2, "lr_scheduler": scheduler2}, )
Metrics can be made available to monitor by simply logging it using
self.log('metric_to_track', metric_val)
in your :class:~pytorch_lightning.core.module.LightningModule
.Note
The
frequency
value specified in a dict along with theoptimizer
key is an int corresponding to the number of sequential batches optimized with the specific optimizer. It should be given to none or to all of the optimizers. There is a difference between passing multiple optimizers in a list, and passing multiple optimizers in dictionaries with a frequency of 1:- In the former case, all optimizers will operate on the given batch in each optimization step. - In the latter, only one optimizer will operate on the given batch at every step.
This is different from the
frequency
value specified in thelr_scheduler_config
mentioned above... code-block:: python
def configure_optimizers(self): optimizer_one = torch.optim.SGD(self.model.parameters(), lr=0.01) optimizer_two = torch.optim.SGD(self.model.parameters(), lr=0.01) return [ {"optimizer": optimizer_one, "frequency": 5}, {"optimizer": optimizer_two, "frequency": 10}, ]
In this example, the first optimizer will be used for the first 5 steps, the second optimizer for the next 10 steps and that cycle will continue. If an LR scheduler is specified for an optimizer using the
lr_scheduler
key in the above dict, the scheduler will only be updated when its optimizer is being used.Examples::
# most cases. no learning rate scheduler def configure_optimizers(self): return Adam(self.parameters(), lr=1e-3) # multiple optimizer case (e.g.: GAN) def configure_optimizers(self): gen_opt = Adam(self.model_gen.parameters(), lr=0.01) dis_opt = Adam(self.model_dis.parameters(), lr=0.02) return gen_opt, dis_opt # example with learning rate schedulers def configure_optimizers(self): gen_opt = Adam(self.model_gen.parameters(), lr=0.01) dis_opt = Adam(self.model_dis.parameters(), lr=0.02) dis_sch = CosineAnnealing(dis_opt, T_max=10) return [gen_opt, dis_opt], [dis_sch] # example with step-based learning rate schedulers # each optimizer has its own scheduler def configure_optimizers(self): gen_opt = Adam(self.model_gen.parameters(), lr=0.01) dis_opt = Adam(self.model_dis.parameters(), lr=0.02) gen_sch = { 'scheduler': ExponentialLR(gen_opt, 0.99), 'interval': 'step' # called after each training step } dis_sch = CosineAnnealing(dis_opt, T_max=10) # called every epoch return [gen_opt, dis_opt], [gen_sch, dis_sch] # example with optimizer frequencies # see training procedure in <code>Improved Training of Wasserstein GANs</code>, Algorithm 1 # <https://arxiv.org/abs/1704.00028> def configure_optimizers(self): gen_opt = Adam(self.model_gen.parameters(), lr=0.01) dis_opt = Adam(self.model_dis.parameters(), lr=0.02) n_critic = 5 return ( {'optimizer': dis_opt, 'frequency': n_critic}, {'optimizer': gen_opt, 'frequency': 1} )
Note
Some things to know:
- Lightning calls
.backward()
and.step()
on each optimizer as needed. - If learning rate scheduler is specified in
configure_optimizers()
with key"interval"
(default "epoch") in the scheduler configuration, Lightning will call the scheduler's.step()
method automatically in case of automatic optimization. - If you use 16-bit precision (
precision=16
), Lightning will automatically handle the optimizers. - If you use multiple optimizers, :meth:
training_step
will have an additionaloptimizer_idx
parameter. - If you use :class:
torch.optim.LBFGS
, Lightning handles the closure function automatically for you. - If you use multiple optimizers, gradients will be calculated only for the parameters of current optimizer at each training step.
- If you need to control how often those optimizers step or override the default
.step()
schedule, override the :meth:optimizer_step
hook.
Expand source code
def configure_optimizers(self): return torch.optim.Adam(self.model.parameters())
def forward(self, x) ‑> Callable[..., Any]
-
Same as :meth:
torch.nn.Module.forward
.Args
*args
- Whatever you decide to pass into the forward method.
**kwargs
- Keyword arguments are also possible.
Return
Your model's output
Expand source code
def forward(self, x): logits = self.model(x) if self.hparams.n_classes > 2: return torch.softmax(logits, -1) return torch.sigmoid(logits)
def predict_numpy(self, x: numpy.ndarray)
-
Expand source code
def predict_numpy(self, x: np.ndarray): return _as_numpy(self.predict(_torch_float(x, device=self.device)))
def test_step(self, batch, batch_idx)
-
Operates on a single batch of data from the test set. In this step you'd normally generate examples or calculate anything of interest such as accuracy.
.. code-block:: python
# the pseudocode for these calls test_outs = [] for test_batch in test_data: out = test_step(test_batch) test_outs.append(out) test_epoch_end(test_outs)
Args
batch
- The output of your :class:
~torch.utils.data.DataLoader
. batch_idx
- The index of this batch.
dataloader_id
- The index of the dataloader that produced this batch. (only if multiple test dataloaders used).
Return
Any of.
- Any object or value
None
- Testing will skip to the next batch
.. code-block:: python
# if you have one test dataloader: def test_step(self, batch, batch_idx): ... # if you have multiple test dataloaders: def test_step(self, batch, batch_idx, dataloader_idx=0): ...
Examples::
# CASE 1: A single test dataset def test_step(self, batch, batch_idx): x, y = batch # implement your own out = self(x) loss = self.loss(out, y) # log 6 example images # or generated text... or whatever sample_imgs = x[:6] grid = torchvision.utils.make_grid(sample_imgs) self.logger.experiment.add_image('example_images', grid, 0) # calculate acc labels_hat = torch.argmax(out, dim=1) test_acc = torch.sum(y == labels_hat).item() / (len(y) * 1.0) # log the outputs! self.log_dict({'test_loss': loss, 'test_acc': test_acc})
If you pass in multiple test dataloaders, :meth:
test_step
will have an additional argument. We recommend setting the default value of 0 so that you can quickly switch between single and multiple dataloaders... code-block:: python
# CASE 2: multiple test dataloaders def test_step(self, batch, batch_idx, dataloader_idx=0): # dataloader_idx tells you which dataset this is. ...
Note
If you don't need to test you don't need to implement this method.
Note
When the :meth:
test_step
is called, the model has been put in eval mode and PyTorch gradients have been disabled. At the end of the test epoch, the model goes back to training mode and gradients are enabled.Expand source code
def test_step(self, batch, batch_idx): loss = self._step(batch, batch_idx) self.log("test_loss", loss, on_step=False, on_epoch=True) return loss
def training_step(self, batch, batch_idx)
-
Here you compute and return the training loss and some additional metrics for e.g. the progress bar or logger.
Args
batch (:class:
~torch.Tensor
| (:class:~torch.Tensor
, …) | [:class:~torch.Tensor
, …]): The output of your :class:~torch.utils.data.DataLoader
. A tensor, tuple or list. batch_idx (int
): Integer displaying index of this batch optimizer_idx (int
): When using multiple optimizers, this argument will also be present. hiddens (Any
): Passed in if :paramref:~pytorch_lightning.core.module.LightningModule.truncated_bptt_steps
> 0.Return
Any of.
- :class:
~torch.Tensor
- The loss tensor dict
- A dictionary. Can include any keys, but must include the key'loss'
None
- Training will skip to the next batch. This is only for automatic optimization. This is not supported for multi-GPU, TPU, IPU, or DeepSpeed.
In this step you'd normally do the forward pass and calculate the loss for a batch. You can also do fancier things like multiple forward passes or something model specific.
Example::
def training_step(self, batch, batch_idx): x, y, z = batch out = self.encoder(x) loss = self.loss(out, x) return loss
If you define multiple optimizers, this step will be called with an additional
optimizer_idx
parameter... code-block:: python
# Multiple optimizers (e.g.: GANs) def training_step(self, batch, batch_idx, optimizer_idx): if optimizer_idx == 0: # do training_step with encoder ... if optimizer_idx == 1: # do training_step with decoder ...
If you add truncated back propagation through time you will also get an additional argument with the hidden states of the previous step.
.. code-block:: python
# Truncated back-propagation through time def training_step(self, batch, batch_idx, hiddens): # hiddens are the hidden states from the previous truncated backprop step out, hiddens = self.lstm(data, hiddens) loss = ... return {"loss": loss, "hiddens": hiddens}
Note
The loss value shown in the progress bar is smoothed (averaged) over the last values, so it differs from the actual loss returned in train/validation step.
Note
When
accumulate_grad_batches
> 1, the loss returned here will be automatically normalized byaccumulate_grad_batches
internally.Expand source code
def training_step(self, batch, batch_idx): loss = self._step(batch, batch_idx) self.log("loss", loss) return loss
- :class:
def validation_step(self, batch, batch_idx)
-
Operates on a single batch of data from the validation set. In this step you'd might generate examples or calculate anything of interest like accuracy.
.. code-block:: python
# the pseudocode for these calls val_outs = [] for val_batch in val_data: out = validation_step(val_batch) val_outs.append(out) validation_epoch_end(val_outs)
Args
batch
- The output of your :class:
~torch.utils.data.DataLoader
. batch_idx
- The index of this batch.
dataloader_idx
- The index of the dataloader that produced this batch. (only if multiple val dataloaders used)
Return
- Any object or value
None
- Validation will skip to the next batch
.. code-block:: python
# pseudocode of order val_outs = [] for val_batch in val_data: out = validation_step(val_batch) if defined("validation_step_end"): out = validation_step_end(out) val_outs.append(out) val_outs = validation_epoch_end(val_outs)
.. code-block:: python
# if you have one val dataloader: def validation_step(self, batch, batch_idx): ... # if you have multiple val dataloaders: def validation_step(self, batch, batch_idx, dataloader_idx=0): ...
Examples::
# CASE 1: A single validation dataset def validation_step(self, batch, batch_idx): x, y = batch # implement your own out = self(x) loss = self.loss(out, y) # log 6 example images # or generated text... or whatever sample_imgs = x[:6] grid = torchvision.utils.make_grid(sample_imgs) self.logger.experiment.add_image('example_images', grid, 0) # calculate acc labels_hat = torch.argmax(out, dim=1) val_acc = torch.sum(y == labels_hat).item() / (len(y) * 1.0) # log the outputs! self.log_dict({'val_loss': loss, 'val_acc': val_acc})
If you pass in multiple val dataloaders, :meth:
validation_step
will have an additional argument. We recommend setting the default value of 0 so that you can quickly switch between single and multiple dataloaders... code-block:: python
# CASE 2: multiple validation dataloaders def validation_step(self, batch, batch_idx, dataloader_idx=0): # dataloader_idx tells you which dataset this is. ...
Note
If you don't need to validate you don't need to implement this method.
Note
When the :meth:
validation_step
is called, the model has been put in eval mode and PyTorch gradients have been disabled. At the end of validation, the model goes back to training mode and gradients are enabled.Expand source code
def validation_step(self, batch, batch_idx): loss = self._step(batch, batch_idx) self.log("val_loss", loss, on_step=False, on_epoch=True) return loss
class LinearModel (input_size, n_classes)
-
Base class for all neural network modules.
Your models should also subclass this class.
Modules can also contain other Modules, allowing to nest them in a tree structure. You can assign the submodules as regular attributes::
import torch.nn as nn import torch.nn.functional as F class Model(nn.Module): def __init__(self): super().__init__() self.conv1 = nn.Conv2d(1, 20, 5) self.conv2 = nn.Conv2d(20, 20, 5) def forward(self, x): x = F.relu(self.conv1(x)) return F.relu(self.conv2(x))
Submodules assigned in this way will be registered, and will have their parameters converted too when you call :meth:
to
, etc.Note
As per the example above, an
__init__()
call to the parent class must be made before assignment on the child.:ivar training: Boolean represents whether this module is in training or evaluation mode. :vartype training: bool
Initializes internal Module state, shared by both nn.Module and ScriptModule.
Expand source code
class LinearModel(nn.Module): def __init__(self, input_size, n_classes): super().__init__() self.net = nn.Linear(input_size, n_classes) def forward(self, x): return self.net(x)
Ancestors
- torch.nn.modules.module.Module
Class variables
var dump_patches : bool
var training : bool
Methods
def forward(self, x) ‑> Callable[..., Any]
-
Defines the computation performed at every call.
Should be overridden by all subclasses.
Note
Although the recipe for forward pass needs to be defined within this function, one should call the :class:
Module
instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.Expand source code
def forward(self, x): return self.net(x)
class NNModel (input_size, n_classes)
-
Base class for all neural network modules.
Your models should also subclass this class.
Modules can also contain other Modules, allowing to nest them in a tree structure. You can assign the submodules as regular attributes::
import torch.nn as nn import torch.nn.functional as F class Model(nn.Module): def __init__(self): super().__init__() self.conv1 = nn.Conv2d(1, 20, 5) self.conv2 = nn.Conv2d(20, 20, 5) def forward(self, x): x = F.relu(self.conv1(x)) return F.relu(self.conv2(x))
Submodules assigned in this way will be registered, and will have their parameters converted too when you call :meth:
to
, etc.Note
As per the example above, an
__init__()
call to the parent class must be made before assignment on the child.:ivar training: Boolean represents whether this module is in training or evaluation mode. :vartype training: bool
Initializes internal Module state, shared by both nn.Module and ScriptModule.
Expand source code
class NNModel(nn.Module): def __init__(self, input_size, n_classes): super().__init__() self.net = nn.Sequential( nn.Linear(input_size, input_size * 2), nn.ReLU(), nn.BatchNorm1d(input_size * 2), nn.Dropout(p=0.25), nn.Linear(input_size * 2, input_size), nn.ReLU(), nn.BatchNorm1d(input_size), nn.Dropout(p=0.25), nn.Linear(input_size, n_classes), ) def forward(self, x): return self.net(x)
Ancestors
- torch.nn.modules.module.Module
Class variables
var dump_patches : bool
var training : bool
Methods
def forward(self, x) ‑> Callable[..., Any]
-
Defines the computation performed at every call.
Should be overridden by all subclasses.
Note
Although the recipe for forward pass needs to be defined within this function, one should call the :class:
Module
instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.Expand source code
def forward(self, x): return self.net(x)
class TensorDataModule (dataset: NumpyDataset, batch_size: int = None, shuffle_labels: bool = False)
-
A DataModule standardizes the training, val, test splits, data preparation and transforms. The main advantage is consistent data splits, data preparation and transforms across models.
Example::
class MyDataModule(LightningDataModule): def __init__(self): super().__init__() def prepare_data(self): # download, split, etc... # only called on 1 GPU/TPU in distributed def setup(self, stage): # make assignments here (val/train/test split) # called on every process in DDP def train_dataloader(self): train_split = Dataset(...) return DataLoader(train_split) def val_dataloader(self): val_split = Dataset(...) return DataLoader(val_split) def test_dataloader(self): test_split = Dataset(...) return DataLoader(test_split) def teardown(self): # clean up after fit or test # called on every process in DDP
Data module for training models
Args
dataset
:NumpyDataset
- numpy dataset
batch_size
:int
- batch size. Defaults to None.
shuffle_labels
:bool
- corrupt y labels by permuting them. Defaults to False.
Expand source code
class TensorDataModule(LightningDataModule): def __init__( self, dataset: NumpyDataset, batch_size: int = None, shuffle_labels: bool = False, ): """Data module for training models Args: dataset (NumpyDataset): numpy dataset batch_size (int): batch size. Defaults to None. shuffle_labels (bool): corrupt y labels by permuting them. Defaults to False. """ super().__init__() self.n_classes = dataset.n_classes dataset = self._corrupt_dataset(dataset, shuffle_labels) X_train, y_train, X_val, y_val = split_dataset( dataset.X_train, dataset.y_train, test_perc=0.1, ) self.batch_size = ( int(np.sqrt(len(X_train))) if batch_size is None else batch_size ) self.X_train, self.y_train = self.convert(X_train, y_train) self.X_val, self.y_val = self.convert(X_val, y_val) self.X_test, self.y_test = self.convert(dataset.X_test, dataset.y_test) def _corrupt_dataset(self, dataset, shuffle_labels): new_dataset = copy(dataset) if shuffle_labels: new_dataset.y_train = np.random.permutation(new_dataset.y_train) return new_dataset def convert(self, X, y): X = torch.tensor(X).float() y = torch.tensor(y) y = y.float() if self.n_classes == 2 else y.long() return X, y def train_dataloader(self): return DataLoader( TensorDataset(self.X_train, self.y_train), batch_size=self.batch_size, ) def val_dataloader(self): return DataLoader( TensorDataset(self.X_val, self.y_val), batch_size=self.batch_size, ) def test_dataloader(self): return DataLoader( TensorDataset(self.X_test, self.y_test), batch_size=self.batch_size, )
Ancestors
- pytorch_lightning.core.datamodule.LightningDataModule
- pytorch_lightning.core.hooks.DataHooks
- pytorch_lightning.core.mixins.hparams_mixin.HyperparametersMixin
Class variables
var name : Optional[str]
Methods
def convert(self, X, y)
-
Expand source code
def convert(self, X, y): X = torch.tensor(X).float() y = torch.tensor(y) y = y.float() if self.n_classes == 2 else y.long() return X, y
def test_dataloader(self)
-
Implement one or multiple PyTorch DataLoaders for testing.
For data processing use the following pattern:
- download in :meth:<code>prepare\_data</code> - process and split in :meth:<code>setup</code>
However, the above are only necessary for distributed processing.
Warning: do not assign state in prepare_data
- :meth:
~pytorch_lightning.trainer.trainer.Trainer.test
- :meth:
prepare_data
- :meth:
setup
Note
Lightning adds the correct sampler for distributed and arbitrary hardware. There is no need to set it yourself.
Return
A :class:
torch.utils.data.DataLoader
or a sequence of them specifying testing samples.Example::
def test_dataloader(self): transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5,), (1.0,))]) dataset = MNIST(root='/path/to/mnist/', train=False, transform=transform, download=True) loader = torch.utils.data.DataLoader( dataset=dataset, batch_size=self.batch_size, shuffle=False ) return loader # can also return multiple dataloaders def test_dataloader(self): return [loader_a, loader_b, ..., loader_n]
Note
If you don't need a test dataset and a :meth:
test_step
, you don't need to implement this method.Note
In the case where you return multiple test dataloaders, the :meth:
test_step
will have an argumentdataloader_idx
which matches the order here.Expand source code
def test_dataloader(self): return DataLoader( TensorDataset(self.X_test, self.y_test), batch_size=self.batch_size, )
- :meth:
def train_dataloader(self)
-
Implement one or more PyTorch DataLoaders for training.
Return
A collection of :class:
torch.utils.data.DataLoader
specifying training samples. In the case of multiple dataloaders, please see this :ref:section <multiple-dataloaders>
.The dataloader you return will not be reloaded unless you set :paramref:
~pytorch_lightning.trainer.Trainer.reload_dataloaders_every_n_epochs
to a positive integer.For data processing use the following pattern:
- download in :meth:<code>prepare\_data</code> - process and split in :meth:<code>setup</code>
However, the above are only necessary for distributed processing.
Warning: do not assign state in prepare_data
- :meth:
~pytorch_lightning.trainer.trainer.Trainer.fit
- :meth:
prepare_data
- :meth:
setup
Note
Lightning adds the correct sampler for distributed and arbitrary hardware. There is no need to set it yourself.
Example::
# single dataloader def train_dataloader(self): transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5,), (1.0,))]) dataset = MNIST(root='/path/to/mnist/', train=True, transform=transform, download=True) loader = torch.utils.data.DataLoader( dataset=dataset, batch_size=self.batch_size, shuffle=True ) return loader # multiple dataloaders, return as list def train_dataloader(self): mnist = MNIST(...) cifar = CIFAR(...) mnist_loader = torch.utils.data.DataLoader( dataset=mnist, batch_size=self.batch_size, shuffle=True ) cifar_loader = torch.utils.data.DataLoader( dataset=cifar, batch_size=self.batch_size, shuffle=True ) # each batch will be a list of tensors: [batch_mnist, batch_cifar] return [mnist_loader, cifar_loader] # multiple dataloader, return as dict def train_dataloader(self): mnist = MNIST(...) cifar = CIFAR(...) mnist_loader = torch.utils.data.DataLoader( dataset=mnist, batch_size=self.batch_size, shuffle=True ) cifar_loader = torch.utils.data.DataLoader( dataset=cifar, batch_size=self.batch_size, shuffle=True ) # each batch will be a dict of tensors: {'mnist': batch_mnist, 'cifar': batch_cifar} return {'mnist': mnist_loader, 'cifar': cifar_loader}
Expand source code
def train_dataloader(self): return DataLoader( TensorDataset(self.X_train, self.y_train), batch_size=self.batch_size, )
- :meth:
def val_dataloader(self)
-
Implement one or multiple PyTorch DataLoaders for validation.
The dataloader you return will not be reloaded unless you set :paramref:
~pytorch_lightning.trainer.Trainer.reload_dataloaders_every_n_epochs
to a positive integer.It's recommended that all data downloads and preparation happen in :meth:
prepare_data
.- :meth:
~pytorch_lightning.trainer.trainer.Trainer.fit
- :meth:
~pytorch_lightning.trainer.trainer.Trainer.validate
- :meth:
prepare_data
- :meth:
setup
Note
Lightning adds the correct sampler for distributed and arbitrary hardware There is no need to set it yourself.
Return
A :class:
torch.utils.data.DataLoader
or a sequence of them specifying validation samples.Examples::
def val_dataloader(self): transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5,), (1.0,))]) dataset = MNIST(root='/path/to/mnist/', train=False, transform=transform, download=True) loader = torch.utils.data.DataLoader( dataset=dataset, batch_size=self.batch_size, shuffle=False ) return loader # can also return multiple dataloaders def val_dataloader(self): return [loader_a, loader_b, ..., loader_n]
Note
If you don't need a validation dataset and a :meth:
validation_step
, you don't need to implement this method.Note
In the case where you return multiple validation dataloaders, the :meth:
validation_step
will have an argumentdataloader_idx
which matches the order here.Expand source code
def val_dataloader(self): return DataLoader( TensorDataset(self.X_val, self.y_val), batch_size=self.batch_size, )
- :meth: