pytorch_model.py About: Pytorch model and datamodule

"""
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 or lr_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 the lr_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 the optimizer 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 the lr_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 additional optimizer_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 by accumulate_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

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 argument dataloader_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,
    )

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,
    )

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 argument dataloader_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,
    )