Shortcuts

Self-supervised learning

These transforms are used in various self-supervised learning approaches.

Note

We rely on the community to keep these updated and working. If something doesn’t work, we’d really appreciate a contribution to fix!


CPC transforms

Transforms used for CPC

CIFAR-10 Train (c)

class pl_bolts.transforms.self_supervised.cpc_transforms.CPCTrainTransformsCIFAR10(patch_size=8, overlap=4)[source]

Bases: object

Warning

The feature CPCTrainTransformsCIFAR10 is currently marked under review. The compatibility with other Lightning projects is not guaranteed and API may change at any time. The API and functionality may change without warning in future releases. More details: https://lightning-bolts.readthedocs.io/en/latest/stability.html

Transforms used for CPC:

Transforms:

random_flip
img_jitter
col_jitter
rnd_gray
transforms.ToTensor()
normalize
Patchify(patch_size=patch_size, overlap_size=patch_size // 2)

Example:

# in a regular dataset
CIFAR10(..., transforms=CPCTrainTransformsCIFAR10())

# in a DataModule
module = CIFAR10DataModule(PATH)
train_loader = module.train_dataloader(batch_size=32, transforms=CPCTrainTransformsCIFAR10())
Parameters
  • patch_size (int) – size of patches when cutting up the image into overlapping patches

  • overlap (int) – how much to overlap patches

__call__(inp)[source]

Call self as a function.

Return type

Tensor

CIFAR-10 Eval (c)

class pl_bolts.transforms.self_supervised.cpc_transforms.CPCEvalTransformsCIFAR10(patch_size=8, overlap=4)[source]

Bases: object

Warning

The feature CPCEvalTransformsCIFAR10 is currently marked under review. The compatibility with other Lightning projects is not guaranteed and API may change at any time. The API and functionality may change without warning in future releases. More details: https://lightning-bolts.readthedocs.io/en/latest/stability.html

Transforms used for CPC:

Transforms:

random_flip
transforms.ToTensor()
normalize
Patchify(patch_size=patch_size, overlap_size=overlap)

Example:

# in a regular dataset
CIFAR10(..., transforms=CPCEvalTransformsCIFAR10())

# in a DataModule
module = CIFAR10DataModule(PATH)
train_loader = module.train_dataloader(batch_size=32, transforms=CPCEvalTransformsCIFAR10())
Parameters
  • patch_size (int) – size of patches when cutting up the image into overlapping patches

  • overlap (int) – how much to overlap patches

__call__(inp)[source]

Call self as a function.

Return type

Tensor

Imagenet Train (c)

class pl_bolts.transforms.self_supervised.cpc_transforms.CPCTrainTransformsImageNet128(patch_size=32, overlap=16)[source]

Bases: object

Warning

The feature CPCTrainTransformsImageNet128 is currently marked under review. The compatibility with other Lightning projects is not guaranteed and API may change at any time. The API and functionality may change without warning in future releases. More details: https://lightning-bolts.readthedocs.io/en/latest/stability.html

Transforms used for CPC:

Transforms:

random_flip
transforms.ToTensor()
normalize
Patchify(patch_size=patch_size, overlap_size=patch_size // 2)

Example:

# in a regular dataset
Imagenet(..., transforms=CPCTrainTransformsImageNet128())

# in a DataModule
module = ImagenetDataModule(PATH)
train_loader = module.train_dataloader(batch_size=32, transforms=CPCTrainTransformsImageNet128())
Parameters
  • patch_size (int) – size of patches when cutting up the image into overlapping patches

  • overlap (int) – how much to overlap patches

__call__(inp)[source]

Call self as a function.

Return type

Tensor

Imagenet Eval (c)

class pl_bolts.transforms.self_supervised.cpc_transforms.CPCEvalTransformsImageNet128(patch_size=32, overlap=16)[source]

Bases: object

Warning

The feature CPCEvalTransformsImageNet128 is currently marked under review. The compatibility with other Lightning projects is not guaranteed and API may change at any time. The API and functionality may change without warning in future releases. More details: https://lightning-bolts.readthedocs.io/en/latest/stability.html

Transforms used for CPC:

Transforms:

random_flip
transforms.ToTensor()
normalize
Patchify(patch_size=patch_size, overlap_size=patch_size // 2)

Example:

# in a regular dataset
Imagenet(..., transforms=CPCEvalTransformsImageNet128())

# in a DataModule
module = ImagenetDataModule(PATH)
train_loader = module.train_dataloader(batch_size=32, transforms=CPCEvalTransformsImageNet128())
Parameters
  • patch_size (int) – size of patches when cutting up the image into overlapping patches

  • overlap (int) – how much to overlap patches

__call__(inp)[source]

Call self as a function.

Return type

Tensor

STL-10 Train (c)

class pl_bolts.transforms.self_supervised.cpc_transforms.CPCTrainTransformsSTL10(patch_size=16, overlap=8)[source]

Bases: object

Warning

The feature CPCTrainTransformsSTL10 is currently marked under review. The compatibility with other Lightning projects is not guaranteed and API may change at any time. The API and functionality may change without warning in future releases. More details: https://lightning-bolts.readthedocs.io/en/latest/stability.html

Transforms used for CPC:

Transforms:

random_flip
img_jitter
col_jitter
rnd_gray
transforms.ToTensor()
normalize
Patchify(patch_size=patch_size, overlap_size=patch_size // 2)

Example:

# in a regular dataset
STL10(..., transforms=CPCTrainTransformsSTL10())

# in a DataModule
module = STL10DataModule(PATH)
train_loader = module.train_dataloader(batch_size=32, transforms=CPCTrainTransformsSTL10())
Parameters
  • patch_size (int) – size of patches when cutting up the image into overlapping patches

  • overlap (int) – how much to overlap patches

__call__(inp)[source]

Call self as a function.

Return type

Tensor

STL-10 Eval (c)

class pl_bolts.transforms.self_supervised.cpc_transforms.CPCEvalTransformsSTL10(patch_size=16, overlap=8)[source]

Bases: object

Warning

The feature CPCEvalTransformsSTL10 is currently marked under review. The compatibility with other Lightning projects is not guaranteed and API may change at any time. The API and functionality may change without warning in future releases. More details: https://lightning-bolts.readthedocs.io/en/latest/stability.html

Transforms used for CPC:

Transforms:

random_flip
transforms.ToTensor()
normalize
Patchify(patch_size=patch_size, overlap_size=patch_size // 2)

Example:

# in a regular dataset
STL10(..., transforms=CPCEvalTransformsSTL10())

# in a DataModule
module = STL10DataModule(PATH)
train_loader = module.train_dataloader(batch_size=32, transforms=CPCEvalTransformsSTL10())
Parameters
  • patch_size (int) – size of patches when cutting up the image into overlapping patches

  • overlap (int) – how much to overlap patches

__call__(inp)[source]

Call self as a function.

Return type

Tensor

AMDIM transforms

Transforms used for AMDIM

CIFAR-10 Train (a)

class pl_bolts.transforms.self_supervised.amdim_transforms.AMDIMTrainTransformsCIFAR10[source]

Bases: object

Warning

The feature AMDIMTrainTransformsCIFAR10 is currently marked under review. The compatibility with other Lightning projects is not guaranteed and API may change at any time. The API and functionality may change without warning in future releases. More details: https://lightning-bolts.readthedocs.io/en/latest/stability.html

Transforms applied to AMDIM.

Transforms:

img_jitter,
col_jitter,
rnd_gray,
transforms.ToTensor(),
normalize

Example:

x = torch.rand(5, 3, 32, 32)

transform = AMDIMTrainTransformsCIFAR10()
(view1, view2) = transform(x)
__call__(inp)[source]

Call self as a function.

Return type

Tuple[Tensor, Tensor]

CIFAR-10 Eval (a)

class pl_bolts.transforms.self_supervised.amdim_transforms.AMDIMEvalTransformsCIFAR10[source]

Bases: object

Warning

The feature AMDIMEvalTransformsCIFAR10 is currently marked under review. The compatibility with other Lightning projects is not guaranteed and API may change at any time. The API and functionality may change without warning in future releases. More details: https://lightning-bolts.readthedocs.io/en/latest/stability.html

Transforms applied to AMDIM.

Transforms:

transforms.ToTensor(),
normalize

Example:

x = torch.rand(5, 3, 32, 32)

transform = AMDIMEvalTransformsCIFAR10()
(view1, view2) = transform(x)
__call__(inp)[source]

Call self as a function.

Return type

Tensor

Imagenet Train (a)

class pl_bolts.transforms.self_supervised.amdim_transforms.AMDIMTrainTransformsImageNet128(height=128)[source]

Bases: object

Warning

The feature AMDIMTrainTransformsImageNet128 is currently marked under review. The compatibility with other Lightning projects is not guaranteed and API may change at any time. The API and functionality may change without warning in future releases. More details: https://lightning-bolts.readthedocs.io/en/latest/stability.html

Transforms applied to AMDIM.

Transforms:

img_jitter,
col_jitter,
rnd_gray,
transforms.ToTensor(),
normalize

Example:

x = torch.rand(5, 3, 128, 128)

transform = AMDIMTrainTransformsSTL10()
(view1, view2) = transform(x)
__call__(inp)[source]

Call self as a function.

Return type

Tuple[Tensor, Tensor]

Imagenet Eval (a)

class pl_bolts.transforms.self_supervised.amdim_transforms.AMDIMEvalTransformsImageNet128(height=128)[source]

Bases: object

Warning

The feature AMDIMEvalTransformsImageNet128 is currently marked under review. The compatibility with other Lightning projects is not guaranteed and API may change at any time. The API and functionality may change without warning in future releases. More details: https://lightning-bolts.readthedocs.io/en/latest/stability.html

Transforms applied to AMDIM.

Transforms:

transforms.Resize(height + 6, interpolation=InterpolationMode.BICUBIC),
transforms.CenterCrop(height),
transforms.ToTensor(),
normalize

Example:

x = torch.rand(5, 3, 128, 128)

transform = AMDIMEvalTransformsImageNet128()
view1 = transform(x)
__call__(inp)[source]

Call self as a function.

Return type

Tensor

STL-10 Train (a)

class pl_bolts.transforms.self_supervised.amdim_transforms.AMDIMTrainTransformsSTL10(height=64)[source]

Bases: object

Warning

The feature AMDIMTrainTransformsSTL10 is currently marked under review. The compatibility with other Lightning projects is not guaranteed and API may change at any time. The API and functionality may change without warning in future releases. More details: https://lightning-bolts.readthedocs.io/en/latest/stability.html

Transforms applied to AMDIM.

Transforms:

img_jitter,
col_jitter,
rnd_gray,
transforms.ToTensor(),
normalize

Example:

x = torch.rand(5, 3, 64, 64)

transform = AMDIMTrainTransformsSTL10()
(view1, view2) = transform(x)
__call__(inp)[source]

Call self as a function.

Return type

Tuple[Tensor, Tensor]

STL-10 Eval (a)

class pl_bolts.transforms.self_supervised.amdim_transforms.AMDIMEvalTransformsSTL10(height=64)[source]

Bases: object

Warning

The feature AMDIMEvalTransformsSTL10 is currently marked under review. The compatibility with other Lightning projects is not guaranteed and API may change at any time. The API and functionality may change without warning in future releases. More details: https://lightning-bolts.readthedocs.io/en/latest/stability.html

Transforms applied to AMDIM.

Transforms:

transforms.Resize(height + 6, interpolation=InterpolationMode.BICUBIC),
transforms.CenterCrop(height),
transforms.ToTensor(),
normalize

Example:

x = torch.rand(5, 3, 64, 64)

transform = AMDIMTrainTransformsSTL10()
view1 = transform(x)
__call__(inp)[source]

Call self as a function.

Return type

Tensor

MOCO V2 transforms

Transforms used for MOCO V2

CIFAR-10 Train (m2)

class pl_bolts.transforms.self_supervised.moco_transforms.MoCo2TrainCIFAR10Transforms(size=32)[source]

Bases: object

Warning

The feature MoCo2TrainCIFAR10Transforms is currently marked under review. The compatibility with other Lightning projects is not guaranteed and API may change at any time. The API and functionality may change without warning in future releases. More details: https://lightning-bolts.readthedocs.io/en/latest/stability.html

MoCo v2 transforms.

Parameters

size (int, optional) – input size. Defaults to 32.

Transform:

RandomResizedCrop(size=self.input_size)

Example:

from pl_bolts.transforms.self_supervised.MoCo_transforms import MoCo2TrainCIFAR10Transforms

transform = MoCo2TrainCIFAR10Transforms(input_size=32)
x = sample()
(xi, xj) = transform(x)

MoCo 2 augmentation:

https://arxiv.org/pdf/2003.04297.pdf

__call__(x)[source]

Call self as a function.

Return type

Tuple[Tensor, Tensor]

CIFAR-10 Eval (m2)

class pl_bolts.transforms.self_supervised.moco_transforms.MoCo2EvalCIFAR10Transforms(size=32)[source]

Bases: object

Warning

The feature MoCo2EvalCIFAR10Transforms is currently marked under review. The compatibility with other Lightning projects is not guaranteed and API may change at any time. The API and functionality may change without warning in future releases. More details: https://lightning-bolts.readthedocs.io/en/latest/stability.html

MoCo 2 augmentation:

https://arxiv.org/pdf/2003.04297.pdf

__call__(x)[source]

Call self as a function.

Return type

Tuple[Tensor, Tensor]

Imagenet Train (m2)

class pl_bolts.transforms.self_supervised.moco_transforms.MoCo2TrainSTL10Transforms(size=64)[source]

Bases: object

Warning

The feature MoCo2TrainSTL10Transforms is currently marked under review. The compatibility with other Lightning projects is not guaranteed and API may change at any time. The API and functionality may change without warning in future releases. More details: https://lightning-bolts.readthedocs.io/en/latest/stability.html

MoCo 2 augmentation:

https://arxiv.org/pdf/2003.04297.pdf

__call__(x)[source]

Call self as a function.

Return type

Tuple[Tensor, Tensor]

Imagenet Eval (m2)

class pl_bolts.transforms.self_supervised.moco_transforms.MoCo2EvalSTL10Transforms(size=64)[source]

Bases: object

Warning

The feature MoCo2EvalSTL10Transforms is currently marked under review. The compatibility with other Lightning projects is not guaranteed and API may change at any time. The API and functionality may change without warning in future releases. More details: https://lightning-bolts.readthedocs.io/en/latest/stability.html

MoCo 2 augmentation:

https://arxiv.org/pdf/2003.04297.pdf

__call__(x)[source]

Call self as a function.

Return type

Tuple[Tensor, Tensor]

STL-10 Train (m2)

class pl_bolts.transforms.self_supervised.moco_transforms.MoCo2TrainImagenetTransforms(size=224)[source]

Bases: object

Warning

The feature MoCo2TrainImagenetTransforms is currently marked under review. The compatibility with other Lightning projects is not guaranteed and API may change at any time. The API and functionality may change without warning in future releases. More details: https://lightning-bolts.readthedocs.io/en/latest/stability.html

MoCo 2 augmentation:

https://arxiv.org/pdf/2003.04297.pdf

__call__(x)[source]

Call self as a function.

Return type

Tuple[Tensor, Tensor]

STL-10 Eval (m2)

class pl_bolts.transforms.self_supervised.moco_transforms.MoCo2EvalImagenetTransforms(size=128)[source]

Bases: object

Warning

The feature MoCo2EvalImagenetTransforms is currently marked under review. The compatibility with other Lightning projects is not guaranteed and API may change at any time. The API and functionality may change without warning in future releases. More details: https://lightning-bolts.readthedocs.io/en/latest/stability.html

Transforms for MoCo during training step.

https://arxiv.org/pdf/2003.04297.pdf

__call__(x)[source]

Call self as a function.

Return type

Tuple[Tensor, Tensor]

SimCLR transforms

Transforms used for SimCLR

Train (sc)

class pl_bolts.transforms.self_supervised.simclr_transforms.SimCLRTrainDataTransform(input_height=224, gaussian_blur=True, jitter_strength=1.0, normalize=None)[source]

Bases: object

Transforms for SimCLR during training step of the pre-training stage.

Parameters
  • input_height (int, optional) – expected output size of image. Defaults to 224.

  • gaussian_blur (bool, optional) – applies Gaussian blur if True. Defaults to True.

  • jitter_strength (float, optional) – color jitter multiplier. Defaults to 1.0.

  • normalize (Callable, optional) – optional transform to normalize. Defaults to None.

Transform:

RandomResizedCrop(size=self.input_height)
RandomHorizontalFlip()
RandomApply([color_jitter], p=0.8)
RandomGrayscale(p=0.2)
RandomApply([GaussianBlur(kernel_size=int(0.1 * self.input_height))], p=0.5)
transforms.ToTensor()

Example:

from pl_bolts.transforms.self_supervised.simclr_transforms import SimCLRTrainDataTransform

transform = SimCLRTrainDataTransform(input_height=32)
x = sample()
(xi, xj, xk) = transform(x) # xk is only for the online evaluator if used
__call__(sample)[source]

Call self as a function.

Return type

Tuple[Tensor, Tensor, Tensor]

Eval (sc)

class pl_bolts.transforms.self_supervised.simclr_transforms.SimCLREvalDataTransform(input_height=224, gaussian_blur=True, jitter_strength=1.0, normalize=None)[source]

Bases: pl_bolts.transforms.self_supervised.simclr_transforms.SimCLRTrainDataTransform

Transforms for SimCLR during the validation step of the pre-training stage.

Parameters
  • input_height (int, optional) – expected output size of image. Defaults to 224.

  • gaussian_blur (bool, optional) – applies Gaussian blur if True. Defaults to True.

  • jitter_strength (float, optional) – color jitter multiplier. Defaults to 1.0.

  • normalize (Callable, optional) – optional transform to normalize. Defaults to None.

Transform:

Resize(input_height + 10, interpolation=3)
transforms.CenterCrop(input_height),
transforms.ToTensor()

Example:

from pl_bolts.transforms.self_supervised.simclr_transforms import SimCLREvalDataTransform

transform = SimCLREvalDataTransform(input_height=32)
x = sample()
(xi, xj, xk) = transform(x) # xk is only for the online evaluator if used

Identity class

Example:

from pl_bolts.utils import Identity
class pl_bolts.utils.self_supervised.Identity[source]

Bases: torch.nn.modules.module.Module

Warning

The feature Identity is currently marked under review. The compatibility with other Lightning projects is not guaranteed and API may change at any time. The API and functionality may change without warning in future releases. More details: https://lightning-bolts.readthedocs.io/en/latest/stability.html

An identity class to replace arbitrary layers in pretrained models.

Example:

from pl_bolts.utils import Identity

model = resnet18()
model.fc = Identity()

Initializes internal Module state, shared by both nn.Module and ScriptModule.

forward(x)[source]

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 Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

Return type

Tensor


SSL-ready resnets

Torchvision resnets with the fc layers removed and with the ability to return all feature maps instead of just the last one.

Example:

from pl_bolts.utils.self_supervised import torchvision_ssl_encoder

resnet = torchvision_ssl_encoder('resnet18', pretrained=False, return_all_feature_maps=True)
x = torch.rand(3, 3, 32, 32)

feat_maps = resnet(x)
pl_bolts.utils.self_supervised.torchvision_ssl_encoder(name, pretrained=False, return_all_feature_maps=False)[source]

Warning

The feature torchvision_ssl_encoder is currently marked under review. The compatibility with other Lightning projects is not guaranteed and API may change at any time. The API and functionality may change without warning in future releases. More details: https://lightning-bolts.readthedocs.io/en/latest/stability.html

Return type

Module


SSL backbone finetuner

class pl_bolts.models.self_supervised.ssl_finetuner.SSLFineTuner(backbone, in_features=2048, num_classes=1000, epochs=100, hidden_dim=None, dropout=0.0, learning_rate=0.1, weight_decay=1e-06, nesterov=False, scheduler_type='cosine', decay_epochs=(60, 80), gamma=0.1, final_lr=0.0)[source]

Bases: pytorch_lightning.core.module.LightningModule

Finetunes a self-supervised learning backbone using the standard evaluation protocol of a singler layer MLP with 1024 units.

Example:

from pl_bolts.utils.self_supervised import SSLFineTuner
from pl_bolts.models.self_supervised import CPC_v2
from pl_bolts.datamodules import CIFAR10DataModule
from pl_bolts.models.self_supervised.cpc.transforms import CPCEvalTransformsCIFAR10,
                                                            CPCTrainTransformsCIFAR10

# pretrained model
backbone = CPC_v2.load_from_checkpoint(PATH, strict=False)

# dataset + transforms
dm = CIFAR10DataModule(data_dir='.')
dm.train_transforms = CPCTrainTransformsCIFAR10()
dm.val_transforms = CPCEvalTransformsCIFAR10()

# finetuner
finetuner = SSLFineTuner(backbone, in_features=backbone.z_dim, num_classes=backbone.num_classes)

# train
trainer = pl.Trainer()
trainer.fit(finetuner, dm)

# test
trainer.test(datamodule=dm)
Parameters
  • backbone (Module) – a pretrained model

  • in_features (int) – feature dim of backbone outputs

  • num_classes (int) – classes of the dataset

  • hidden_dim (Optional[int]) – dim of the MLP (1024 default used in self-supervised literature)

configure_optimizers()[source]

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.

Returns

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.

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
    # `scheduler.step()`. 1 corresponds to updating the learning
    # rate after every epoch/step.
    "frequency": 1,
    # Metric to to monitor for schedulers like `ReduceLROnPlateau`
    "monitor": "val_loss",
    # If set to `True`, will enforce that the value specified 'monitor'
    # is available when the scheduler is updated, thus stopping
    # training if not found. If set to `False`, it will only produce a warning
    "strict": True,
    # If using the `LearningRateMonitor` 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 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.

# 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 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.

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 `Improved Training of Wasserstein GANs`, 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, training_step() will have an additional optimizer_idx parameter.

  • If you use 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 optimizer_step() hook.

on_train_epoch_start()[source]

Called in the training loop at the very beginning of the epoch.

Return type

None

test_step(batch, batch_idx)[source]

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.

# 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)
Parameters
  • batch – The output of your 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).

Returns

Any of.

  • Any object or value

  • None - Testing will skip to the next batch

# 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, 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.

# 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 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.

training_step(batch, batch_idx)[source]

Here you compute and return the training loss and some additional metrics for e.g. the progress bar or logger.

Parameters
  • batch (Tensor | (Tensor, …) | [Tensor, …]) – The output of your 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 truncated_bptt_steps > 0.

Returns

Any of.

  • 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.

# 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.

# 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.

validation_step(batch, batch_idx)[source]

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.

# 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)
Parameters
  • batch – The output of your 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)

Returns

  • Any object or value

  • None - Validation will skip to the next batch

# 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)
# 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, 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.

# 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 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.

Read the Docs v: latest
Versions
latest
stable
Downloads
pdf
html
On Read the Docs
Project Home
Builds

Free document hosting provided by Read the Docs.