minerva.models.nets

Submodules

Classes

`DeepLabV3`	A DeeplabV3 with a ResNet50 backbone
`MLP`	A flexible multilayer perceptron (MLP) implemented as a subclass of nn.Sequential.
`SETR_PUP`	SET-R model with PUP head for image segmentation.
`SimpleSupervisedModel`	A modular Lightning model wrapper for supervised learning tasks.
`UNet`	This class is a simple implementation of the U-Net model, which is a
`WiseNet`	A modular Lightning model wrapper for supervised learning tasks.

Package Contents

class minerva.models.nets.DeepLabV3(backbone=None, pred_head=None, loss_fn=None, learning_rate=0.001, num_classes=6, train_metrics=None, val_metrics=None, test_metrics=None, optimizer=torch.optim.Adam, optimizer_kwargs=None, lr_scheduler=None, lr_scheduler_kwargs=None, output_shape=None)[source]

Bases: minerva.models.nets.base.SimpleSupervisedModel

A DeeplabV3 with a ResNet50 backbone

References

Liang-Chieh Chen, George Papandreou, Florian Schroff, Hartwig Adam. “Rethinking Atrous Convolution for Semantic Image Segmentation”, 2017

Initializes a DeepLabV3 model.

Parameters

backbone: Optional[nn.Module]: The backbone network. Defaults to None, which will use a ResNet50 backbone.
pred_head: Optional[nn.Module]: The prediction head network. Defaults to None, which will use a DeepLabV3PredictionHead with specified number of classes.
loss_fn: Optional[nn.Module]: The loss function. Defaults to None, which will use a CrossEntropyLoss.
learning_rate: float: The learning rate for the optimizer. Defaults to 0.001.
num_classes: int: The number of classes for prediction. Defaults to 6.
train_metrics: Optional[Dict[str, Metric]]: The metrics to be computed during training. Defaults to None.
val_metrics: Optional[Dict[str, Metric]]: The metrics to be computed during validation. Defaults to None.
test_metrics: Optional[Dict[str, Metric]]: The metrics to be computed during testing. Defaults to None.
optimizer: type: Optimizer class to be instantiated. By default, it is set to torch.optim.Adam. Should be a subclass of torch.optim.Optimizer (e.g., torch.optim.SGD).
optimizer_kwargsdict, optional: Additional kwargs passed to the optimizer constructor.
lr_schedulertype, optional: Learning rate scheduler class to be instantiated. By default, it is set to None, which means no scheduler will be used. Should be a subclass of torch.optim.lr_scheduler.LRScheduler (e.g., torch.optim.lr_scheduler.StepLR).
lr_scheduler_kwargsdict, optional: Additional kwargs passed to the scheduler constructor.
output_shape: Optional[Tuple[int, …]]: The output shape of the model. If None, the output shape will be the same as the input shape. Defaults to None. This is useful for models that require a specific output shape, that is different from the input shape.

_loss_func(y_hat, y)[source]

Calculate the loss between the output and the input data.

Parameters

y_hattorch.Tensor: The output data from the forward pass.
ytorch.Tensor: The input data/label.

Returns

torch.Tensor: The loss value.

Parameters:

y_hat (torch.Tensor)
y (torch.Tensor)

Return type:

torch.Tensor

forward(x)[source]

Perform a forward pass with the input data on the backbone model.

Parameters

xtorch.Tensor: The input data.

Returns

torch.Tensor: The output data from the forward pass.

Parameters:: x (torch.Tensor)
Return type:: torch.Tensor

output_shape = None

Parameters:

backbone (Optional[torch.nn.Module])
pred_head (Optional[torch.nn.Module])
loss_fn (Optional[torch.nn.Module])
learning_rate (float)
num_classes (int)
train_metrics (Optional[Dict[str, torchmetrics.Metric]])
val_metrics (Optional[Dict[str, torchmetrics.Metric]])
test_metrics (Optional[Dict[str, torchmetrics.Metric]])
optimizer (type)
optimizer_kwargs (Optional[Dict[str, Any]])
lr_scheduler (Optional[type])
lr_scheduler_kwargs (Optional[Dict[str, Any]])
output_shape (Optional[Tuple[int, Ellipsis]])

class minerva.models.nets.MLP(layer_sizes, activation_cls=nn.ReLU, intermediate_ops=None, final_op=None, *args, **kwargs)[source]

Bases: torch.nn.Sequential

A flexible multilayer perceptron (MLP) implemented as a subclass of nn.Sequential.

This class allows you to quickly build an MLP with: - Custom layer sizes - Configurable activation functions - Optional intermediate operations (e.g., BatchNorm, Dropout) after each linear layer - An optional final operation (e.g., normalization, final activation)

Parameters

layer_sizesSequence[int]: A list of integers specifying the sizes of each layer. Must contain at least two values: the input and output dimensions.
activation_clstype, optional: The activation function class (must inherit from nn.Module) to use between layers. Defaults to nn.ReLU.
intermediate_opsOptional[List[Optional[nn.Module]]], optional: A list of modules (e.g., nn.BatchNorm1d, nn.Dropout) to apply after each linear layer and before the activation. Each item corresponds to one linear layer. Use None to skip an operation for that layer. Must be the same length as the number of linear layers.
final_opOptional[nn.Module], optional: A module to apply after the last layer (e.g., a final activation or normalization).
*args, **kwargs :: Additional arguments passed to the activation function constructor.

Example

>>> from torch import nn
>>> mlp = MLP(
...     [128, 256, 64, 10],
...     activation_cls=nn.ReLU,
...     intermediate_ops=[nn.BatchNorm1d(256), nn.BatchNorm1d(64), None],
...     final_op=nn.Sigmoid()
... )
>>> print(mlp)
MLP(
    (0): Linear(in_features=128, out_features=256, bias=True)
    (1): BatchNorm1d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    (2): ReLU()
    (3): Linear(in_features=256, out_features=64, bias=True)
    (4): BatchNorm1d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    (5): ReLU()
    (6): Linear(in_features=64, out_features=10, bias=True)
    (7): Sigmoid()
)

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

Parameters:

layer_sizes (Sequence[int])
activation_cls (type)
intermediate_ops (Optional[List[Optional[torch.nn.Module]]])
final_op (Optional[torch.nn.Module])

class minerva.models.nets.SETR_PUP(image_size=512, patch_size=16, num_layers=24, num_heads=16, hidden_dim=1024, mlp_dim=4096, encoder_dropout=0.1, num_classes=1000, norm_layer=None, decoder_channels=256, num_convs=4, up_scale=2, kernel_size=3, align_corners=False, decoder_dropout=0.1, conv_norm=None, conv_act=None, interpolate_mode='bilinear', loss_fn=None, optimizer_type=None, optimizer_params=None, train_metrics=None, val_metrics=None, test_metrics=None, aux_output=True, aux_output_layers=None, aux_weights=None, load_backbone_path=None, freeze_backbone_on_load=True, learning_rate=0.001, loss_weights=None, original_resolution=None, head_lr_factor=1.0, test_engine=None)[source]

Bases: lightning.pytorch.LightningModule

SET-R model with PUP head for image segmentation.

Methods

forward(x: torch.Tensor) -> torch.Tensor: Forward pass of the model.
_compute_metrics(y_hat: torch.Tensor, y: torch.Tensor, step_name: str): Compute metrics for the given step.
_loss_func(y_hat: Union[torch.Tensor, Tuple[torch.Tensor, torch.Tensor, torch.Tensor, torch.Tensor]], y: torch.Tensor) -> torch.Tensor: Calculate the loss between the output and the input data.
_single_step(batch: torch.Tensor, batch_idx: int, step_name: str): Perform a single step of the training/validation loop.
training_step(batch: torch.Tensor, batch_idx: int): Perform a single training step.
validation_step(batch: torch.Tensor, batch_idx: int): Perform a single validation step.
test_step(batch: torch.Tensor, batch_idx: int): Perform a single test step.
predict_step(batch: torch.Tensor, batch_idx: int, dataloader_idx: Optional[int] = None): Perform a single prediction step.
load_backbone(path: str, freeze: bool = False): Load a pre-trained backbone.
configure_optimizers(): Configure the optimizer for the model.
create_from_dict(config: Dict) -> “SETR_PUP”: Create an instance of SETR_PUP from a configuration dictionary.

Initialize the SETR model with Progressive Upsampling Head.

Parameters

image_sizeUnion[int, Tuple[int, int]], optional: Size of the input image, by default 512.
patch_sizeint, optional: Size of the patches to be extracted from the input image, by default 16.
num_layersint, optional: Number of transformer layers, by default 24.
num_headsint, optional: Number of attention heads, by default 16.
hidden_dimint, optional: Dimension of the hidden layer, by default 1024.
mlp_dimint, optional: Dimension of the MLP layer, by default 4096.
encoder_dropoutfloat, optional: Dropout rate for the encoder, by default 0.1.
num_classesint, optional: Number of output classes, by default 1000.
norm_layerOptional[nn.Module], optional: Normalization layer, by default None.
decoder_channelsint, optional: Number of channels in the decoder, by default 256.
num_convsint, optional: Number of convolutional layers in the decoder, by default 4.
up_scaleint, optional: Upscaling factor for the decoder, by default 2.
kernel_sizeint, optional: Kernel size for the convolutional layers, by default 3.
align_cornersbool, optional: Whether to align corners when interpolating, by default False.
decoder_dropoutfloat, optional: Dropout rate for the decoder, by default 0.1.
conv_normOptional[nn.Module], optional: Normalization layer for the convolutional layers, by default None.
conv_actOptional[nn.Module], optional: Activation function for the convolutional layers, by default None.
interpolate_modestr, optional: Interpolation mode, by default “bilinear”.
loss_fnOptional[nn.Module], optional: Loss function, when None defaults to nn.CrossEntropyLoss, by default None.
optimizer_typeOptional[type], optional: Type of optimizer, by default None.
optimizer_paramsOptional[Dict], optional: Parameters for the optimizer, by default None.
train_metricsOptional[Dict[str, Metric]], optional: Metrics for training, by default None.
val_metricsOptional[Dict[str, Metric]], optional: Metrics for validation, by default None.
test_metricsOptional[Dict[str, Metric]], optional: Metrics for testing, by default None.
aux_outputbool, optional: Whether to use auxiliary outputs, by default True.
aux_output_layerslist[int], optional: Layers for auxiliary outputs, when None it defaults to [9, 14, 19].
aux_weightslist[float], optional: Weights for auxiliary outputs, when None it defaults [0.3, 0.3, 0.3].
load_backbone_pathOptional[str], optional: Path to load the backbone model, by default None.
freeze_backbone_on_loadbool, optional: Whether to freeze the backbone model on load, by default True.
learning_ratefloat, optional: Learning rate, by default 1e-3.
loss_weightsOptional[list[float]], optional: Weights for the loss function, by default None.
original_resolutionOptional[Tuple[int, int]], optional: The original resolution of the input image in the pre-training weights. When None, positional embeddings will not be interpolated. Defaults to None.
head_lr_factorfloat, optional: Learning rate factor for the head. used if you need different learning rates for backbone and prediction head, by default 1.0.
test_engineOptional[_Engine], optional: Engine used for test and validation steps. When None, behavior of all steps, training, testing and validation is the same, by default None.

_compute_metrics(y_hat, y, step_name)[source]

Parameters:

y_hat (torch.Tensor)
y (torch.Tensor)
step_name (str)

_loss_func(y_hat, y)[source]

Calculate the loss between the output and the input data.

Parameters

y_hattorch.Tensor: The output data from the forward pass.
ytorch.Tensor: The input data/label.

Returns

torch.Tensor: The loss value.

Parameters:

y_hat (Union[torch.Tensor, Tuple[torch.Tensor, torch.Tensor, torch.Tensor, torch.Tensor]])
y (torch.Tensor)

Return type:

torch.Tensor

_single_step(batch, batch_idx, step_name)[source]

Perform a single step of the training/validation loop.

Parameters

batchtorch.Tensor: The input data.
batch_idxint: The index of the batch.
step_namestr: The name of the step, either “train” or “val”.

Returns

torch.Tensor: The loss value.

Parameters:

batch (torch.Tensor)
batch_idx (int)
step_name (str)

aux_weights = None

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. Optimization with multiple optimizers only works in the manual optimization mode.

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.
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 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.

Metrics can be made available to monitor by simply logging it using self.log('metric_to_track', metric_val) in your LightningModule.

Note:

Some things to know:

Lightning calls .backward() and .step() automatically in case of automatic optimization.
If a 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 optimizer.
If you use torch.optim.LBFGS, Lightning handles the closure function automatically for you.
If you use multiple optimizers, you will have to switch to ‘manual optimization’ mode and step them yourself.
If you need to control how often the optimizer steps, override the optimizer_step() hook.

static create_from_dict(config)[source]

Parameters:: config (Dict)
Return type:: SETR_PUP

forward(x)[source]

Same as 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

Parameters:: x (torch.Tensor)
Return type:: torch.Tensor

head_lr_factor = 1.0

learning_rate = 0.001

load_backbone(path, freeze=False)[source]

Parameters:

path (str)
freeze (bool)

loss_fn = None

metrics

model

num_classes = 1000

optimizer_type = None

predict_step(batch, batch_idx, dataloader_idx=None)[source]

Step function called during predict(). By default, it calls forward(). Override to add any processing logic.

The predict_step() is used to scale inference on multi-devices.

To prevent an OOM error, it is possible to use BasePredictionWriter callback to write the predictions to disk or database after each batch or on epoch end.

The BasePredictionWriter should be used while using a spawn based accelerator. This happens for Trainer(strategy="ddp_spawn") or training on 8 TPU cores with Trainer(accelerator="tpu", devices=8) as predictions won’t be returned.

Args:: batch: The output of your data iterable, normally a DataLoader. batch_idx: The index of this batch. dataloader_idx: The index of the dataloader that produced this batch.

(only if multiple dataloaders used)
Return:: Predicted output (optional).

Example

class MyModel(LightningModule):

    def predict_step(self, batch, batch_idx, dataloader_idx=0):
        return self(batch)

dm = ...
model = MyModel()
trainer = Trainer(accelerator="gpu", devices=2)
predictions = trainer.predict(model, dm)

Parameters:

batch (torch.Tensor)
batch_idx (int)
dataloader_idx (Optional[int])

test_engine = 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.

Args:

batch: The output of your data iterable, normally a DataLoader. batch_idx: The index of this batch. dataloader_idx: The index of the dataloader that produced this batch.

(only if multiple dataloaders used)

Return:

Tensor - The loss tensor
dict - A dictionary. Can include any keys, but must include the key 'loss'.
None - 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.

Parameters:

batch (torch.Tensor)
batch_idx (int)

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.

Args:

batch: The output of your data iterable, normally a DataLoader. batch_idx: The index of this batch. dataloader_idx: The index of the dataloader that produced this batch.

(only if multiple dataloaders used)

Return:

Tensor - The loss tensor
dict - A dictionary which can include any keys, but must include the key 'loss' in the case of automatic optimization.
None - In automatic optimization, this will skip to the next batch (but is not supported for multi-GPU, TPU, or DeepSpeed). For manual optimization, this has no special meaning, as returning the loss is not required.

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

To use multiple optimizers, you can switch to ‘manual optimization’ and control their stepping:

def __init__(self):
    super().__init__()
    self.automatic_optimization = False


# Multiple optimizers (e.g.: GANs)
def training_step(self, batch, batch_idx):
    opt1, opt2 = self.optimizers()

    # do training_step with encoder
    ...
    opt1.step()
    # do training_step with decoder
    ...
    opt2.step()

Note:: When accumulate_grad_batches > 1, the loss returned here will be automatically normalized by accumulate_grad_batches internally.

Parameters:

batch (torch.Tensor)
batch_idx (int)

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.

Args:

batch: The output of your data iterable, normally a DataLoader. batch_idx: The index of this batch. dataloader_idx: The index of the dataloader that produced this batch.

(only if multiple dataloaders used)

Return:

Tensor - The loss tensor
dict - A dictionary. Can include any keys, but must include the key 'loss'.
None - Skip to the next batch.

# 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.

Parameters:

batch (torch.Tensor)
batch_idx (int)

Parameters:

image_size (Union[int, Tuple[int, int]])
patch_size (int)
num_layers (int)
num_heads (int)
hidden_dim (int)
mlp_dim (int)
encoder_dropout (float)
num_classes (int)
norm_layer (Optional[torch.nn.Module])
decoder_channels (int)
num_convs (int)
up_scale (int)
kernel_size (int)
align_corners (bool)
decoder_dropout (float)
conv_norm (Optional[torch.nn.Module])
conv_act (Optional[torch.nn.Module])
interpolate_mode (str)
loss_fn (Optional[torch.nn.Module])
optimizer_type (Optional[type])
optimizer_params (Optional[Dict])
train_metrics (Optional[Dict[str, torchmetrics.Metric]])
val_metrics (Optional[Dict[str, torchmetrics.Metric]])
test_metrics (Optional[Dict[str, torchmetrics.Metric]])
aux_output (bool)
aux_output_layers (Optional[list[int]])
aux_weights (Optional[list[float]])
load_backbone_path (Optional[str])
freeze_backbone_on_load (bool)
learning_rate (float)
loss_weights (Optional[list[float]])
original_resolution (Optional[Tuple[int, int]])
head_lr_factor (float)
test_engine (Optional[minerva.engines.engine._Engine])

class minerva.models.nets.SimpleSupervisedModel(backbone, fc, loss_fn, adapter=None, learning_rate=0.001, flatten=True, train_metrics=None, val_metrics=None, test_metrics=None, freeze_backbone=False, optimizer=torch.optim.Adam, optimizer_kwargs=None, lr_scheduler=None, lr_scheduler_kwargs=None)[source]

Bases: lightning.LightningModule

A modular Lightning model wrapper for supervised learning tasks.

This class enables the construction of supervised models by combining a backbone (feature extractor), an optional adapter, and a fully connected (FC) head. It provides a clean interface for setting up custom training, validation, and testing pipelines with pluggable loss functions, metrics, optimizers, and learning rate schedulers.

The architecture is structured as follows:

Backbone Model

v

Adapter (Optional)

(Flatten if needed)
v

Fully Connected Head

v

Loss Function

Training and validation steps comprise the following steps:

Forward pass input through the backbone.
Pass through adapter (if provided).
Flatten the output (if flatten is True) before the FC head.
Forward through the FC head.
Compute loss with respect to targets.
Backpropagate and update parameters.
Compute metrics and log them.
Return loss. train_loss, val_loss, and test_loss are always logged, along with any additional metrics specified in the train_metrics, val_metrics, and test_metrics dictionaries.

This wrapper is especially useful to quickly set up supervised models for various tasks, such as image classification, object detection, and segmentation. It is designed to be flexible and extensible, allowing users to easily swap out components like the backbone, adapter, and FC head as needed. The model is built with a focus on simplicity and modularity, making it easy to adapt to different use cases and requirements. The model is designed to be used with PyTorch Lightning and is compatible with its training loop.

Note: For more complex architectures that does not follow the above structure should not inherit from this class.

Note: Input batches must be tuples (input_tensor, target_tensor).

Initializes the supervised model with training components and configs.

Parameters

backbonetorch.nn.Module or LoadableModule: The backbone (feature extractor) model.
fctorch.nn.Module or LoadableModule: The fully connected head. Use nn.Identity() if not required.
loss_fntorch.nn.Module: Loss function to optimize during training.
adapterCallable, optional: Function to transform backbone outputs before feeding into fc.
learning_ratefloat, default=1e-3: Learning rate used for optimization.
flattenbool, default=True: If True, flattens backbone outputs before fc.
train_metricsdict, optional: TorchMetrics dictionary for training evaluation.
val_metricsdict, optional: TorchMetrics dictionary for validation evaluation.
test_metricsdict, optional: TorchMetrics dictionary for test evaluation.
freeze_backbonebool, default=False: If True, backbone parameters are frozen during training.
optimizer: type: Optimizer class to be instantiated. By default, it is set to torch.optim.Adam. Should be a subclass of torch.optim.Optimizer (e.g., torch.optim.SGD).
optimizer_kwargsdict, optional: Additional kwargs passed to the optimizer constructor.
lr_schedulertype, optional: Learning rate scheduler class to be instantiated. By default, it is set to None, which means no scheduler will be used. Should be a subclass of torch.optim.lr_scheduler.LRScheduler (e.g., torch.optim.lr_scheduler.StepLR).
lr_scheduler_kwargsdict, optional: Additional kwargs passed to the scheduler constructor.

_compute_metrics(y_hat, y, step_name)[source]

Calculate the metrics for the given step.

Parameters

y_hattorch.Tensor: The output data from the forward pass.
ytorch.Tensor: The input data/label.
step_namestr: Name of the step. It will be used to get the metrics from the self.metrics attribute.

Returns

Dict[str, torch.Tensor]: A dictionary with the metrics values.

Parameters:

y_hat (torch.Tensor)
y (torch.Tensor)
step_name (str)

Return type:

Dict[str, torch.Tensor]

_loss_func(y_hat, y)[source]

Calculate the loss between the output and the input data.

Parameters

y_hattorch.Tensor: The output data from the forward pass.
ytorch.Tensor: The input data/label.

Returns

torch.Tensor: The loss value.

Parameters:

y_hat (torch.Tensor)
y (torch.Tensor)

Return type:

torch.Tensor

_single_step(batch, batch_idx, step_name)[source]

Perform a single train/validation/test step. It consists in making a forward pass with the input data on the backbone model, computing the loss between the output and the input data, and logging the loss.

Parameters

batchtorch.Tensor: The input data. It must be a 2-element tuple of tensors, where the first tensor is the input data and the second tensor is the mask.
batch_idxint: The index of the batch.
step_namestr: The name of the step. It will be used to log the loss. The possible values are: “train”, “val” and “test”. The loss will be logged as “{step_name}_loss”.

Returns

torch.Tensor: A tensor with the loss value.

Parameters:

batch (torch.Tensor)
batch_idx (int)
step_name (str)

Return type:

torch.Tensor

adapter = None

backbone

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. Optimization with multiple optimizers only works in the manual optimization mode.

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.
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 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.

Metrics can be made available to monitor by simply logging it using self.log('metric_to_track', metric_val) in your LightningModule.

Note:

Some things to know:

Lightning calls .backward() and .step() automatically in case of automatic optimization.
If a 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 optimizer.
If you use torch.optim.LBFGS, Lightning handles the closure function automatically for you.
If you use multiple optimizers, you will have to switch to ‘manual optimization’ mode and step them yourself.
If you need to control how often the optimizer steps, override the optimizer_step() hook.

fc

flatten = True

forward(x)[source]

Perform a forward pass with the input data on the backbone model.

Parameters

xtorch.Tensor: The input data.

Returns

torch.Tensor: The output data from the forward pass.

Parameters:: x (torch.Tensor)
Return type:: torch.Tensor

freeze_backbone = False

learning_rate = 0.001

loss_fn

lr_scheduler = None

lr_scheduler_kwargs

metrics

optimizer

optimizer_kwargs

predict_step(batch, batch_idx, dataloader_idx=None)[source]

Step function called during predict(). By default, it calls forward(). Override to add any processing logic.

The predict_step() is used to scale inference on multi-devices.

To prevent an OOM error, it is possible to use BasePredictionWriter callback to write the predictions to disk or database after each batch or on epoch end.

The BasePredictionWriter should be used while using a spawn based accelerator. This happens for Trainer(strategy="ddp_spawn") or training on 8 TPU cores with Trainer(accelerator="tpu", devices=8) as predictions won’t be returned.

Args:: batch: The output of your data iterable, normally a DataLoader. batch_idx: The index of this batch. dataloader_idx: The index of the dataloader that produced this batch.

(only if multiple dataloaders used)
Return:: Predicted output (optional).

Example

class MyModel(LightningModule):

    def predict_step(self, batch, batch_idx, dataloader_idx=0):
        return self(batch)

dm = ...
model = MyModel()
trainer = Trainer(accelerator="gpu", devices=2)
predictions = trainer.predict(model, dm)

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.

Args:

batch: The output of your data iterable, normally a DataLoader. batch_idx: The index of this batch. dataloader_idx: The index of the dataloader that produced this batch.

(only if multiple dataloaders used)

Return:

Tensor - The loss tensor
dict - A dictionary. Can include any keys, but must include the key 'loss'.
None - 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.

Parameters:

batch (torch.Tensor)
batch_idx (int)

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.

Args:

batch: The output of your data iterable, normally a DataLoader. batch_idx: The index of this batch. dataloader_idx: The index of the dataloader that produced this batch.

(only if multiple dataloaders used)

Return:

Tensor - The loss tensor
dict - A dictionary which can include any keys, but must include the key 'loss' in the case of automatic optimization.
None - In automatic optimization, this will skip to the next batch (but is not supported for multi-GPU, TPU, or DeepSpeed). For manual optimization, this has no special meaning, as returning the loss is not required.

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

To use multiple optimizers, you can switch to ‘manual optimization’ and control their stepping:

def __init__(self):
    super().__init__()
    self.automatic_optimization = False


# Multiple optimizers (e.g.: GANs)
def training_step(self, batch, batch_idx):
    opt1, opt2 = self.optimizers()

    # do training_step with encoder
    ...
    opt1.step()
    # do training_step with decoder
    ...
    opt2.step()

Note:: When accumulate_grad_batches > 1, the loss returned here will be automatically normalized by accumulate_grad_batches internally.

Parameters:

batch (torch.Tensor)
batch_idx (int)

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.

Args:

batch: The output of your data iterable, normally a DataLoader. batch_idx: The index of this batch. dataloader_idx: The index of the dataloader that produced this batch.

(only if multiple dataloaders used)

Return:

Tensor - The loss tensor
dict - A dictionary. Can include any keys, but must include the key 'loss'.
None - Skip to the next batch.

# 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.

Parameters:

batch (torch.Tensor)
batch_idx (int)

Parameters:

backbone (Union[torch.nn.Module, minerva.models.loaders.LoadableModule])
fc (Union[torch.nn.Module, minerva.models.loaders.LoadableModule])
loss_fn (torch.nn.Module)
adapter (Optional[Callable[[torch.Tensor], torch.Tensor]])
learning_rate (float)
flatten (bool)
train_metrics (Optional[Dict[str, torchmetrics.Metric]])
val_metrics (Optional[Dict[str, torchmetrics.Metric]])
test_metrics (Optional[Dict[str, torchmetrics.Metric]])
freeze_backbone (bool)
optimizer (type)
optimizer_kwargs (Optional[Dict[str, Any]])
lr_scheduler (Optional[type])
lr_scheduler_kwargs (Optional[Dict[str, Any]])

class minerva.models.nets.UNet(n_channels=1, bilinear=False, learning_rate=0.001, loss_fn=None, **kwargs)[source]

Bases: minerva.models.nets.base.SimpleSupervisedModel

This class is a simple implementation of the U-Net model, which is a convolutional neural network used for image segmentation. The model consists of a contracting path (encoder) and an expansive path (decoder). The contracting path follows the typical architecture of a convolutional neural network, with repeated applications of convolutions and max pooling layers. The expansive path consists of up-convolutions and concatenation of feature maps from the contracting path. The model also has skip connections, which allows the expansive path to use information from the contracting path at multiple resolutions. The U-Net model was originally proposed by Ronneberger, Fischer, and Brox in 2015.

This architecture, handles arbitrary input sizes, and returns an output of the same size as the input. The expected input size is (N, C, H, W), where N is the batch size, C is the number of channels, H is the height of the input image, and W is the width of the input image.

Note that, for this implementation, the input batch is a single tensor and not a tuple of tensors (e.g., data and label).

Note that this class wrappers the _UNet class, which is the actual implementation of the U-Net model, into a SimpleReconstructionNet class, which is a simple autoencoder pipeline for reconstruction tasks.

References

Ronneberger, Olaf, Philipp Fischer, and Thomas Brox. “U-net: Convolutional networks for biomedical image segmentation.” Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18. Springer International Publishing, 2015.

Wrapper implementation of the U-Net model.

Parameters

n_channelsint, optional: The number of channels of the input, by default 1
bilinearbool, optional: If True use bilinear interpolation for upsampling, by default False.
learning_ratefloat, optional: The learning rate to Adam optimizer, by default 1e-3
loss_fntorch.nn.Module, optional: The function used to compute the loss. If None, it will be used the MSELoss, by default None.
kwargsDict: Additional arguments to be passed to the SimpleSupervisedModel class.

Parameters:

n_channels (int)
bilinear (bool)
learning_rate (float)
loss_fn (Optional[torch.nn.Module])

class minerva.models.nets.WiseNet(in_channels=1, out_channels=1, loss_fn=None, learning_rate=0.001, **kwargs)[source]

Bases: minerva.models.nets.base.SimpleSupervisedModel

A modular Lightning model wrapper for supervised learning tasks.

This class enables the construction of supervised models by combining a backbone (feature extractor), an optional adapter, and a fully connected (FC) head. It provides a clean interface for setting up custom training, validation, and testing pipelines with pluggable loss functions, metrics, optimizers, and learning rate schedulers.

The architecture is structured as follows:

Backbone Model

v

Adapter (Optional)

(Flatten if needed)
v

Fully Connected Head

v

Loss Function

Training and validation steps comprise the following steps:

Forward pass input through the backbone.
Pass through adapter (if provided).
Flatten the output (if flatten is True) before the FC head.
Forward through the FC head.
Compute loss with respect to targets.
Backpropagate and update parameters.
Compute metrics and log them.
Return loss. train_loss, val_loss, and test_loss are always logged, along with any additional metrics specified in the train_metrics, val_metrics, and test_metrics dictionaries.

This wrapper is especially useful to quickly set up supervised models for various tasks, such as image classification, object detection, and segmentation. It is designed to be flexible and extensible, allowing users to easily swap out components like the backbone, adapter, and FC head as needed. The model is built with a focus on simplicity and modularity, making it easy to adapt to different use cases and requirements. The model is designed to be used with PyTorch Lightning and is compatible with its training loop.

Note: For more complex architectures that does not follow the above structure should not inherit from this class.

Note: Input batches must be tuples (input_tensor, target_tensor).

Initializes the supervised model with training components and configs.

Parameters

backbonetorch.nn.Module or LoadableModule: The backbone (feature extractor) model.
fctorch.nn.Module or LoadableModule: The fully connected head. Use nn.Identity() if not required.
loss_fntorch.nn.Module: Loss function to optimize during training.
adapterCallable, optional: Function to transform backbone outputs before feeding into fc.
learning_ratefloat, default=1e-3: Learning rate used for optimization.
flattenbool, default=True: If True, flattens backbone outputs before fc.
train_metricsdict, optional: TorchMetrics dictionary for training evaluation.
val_metricsdict, optional: TorchMetrics dictionary for validation evaluation.
test_metricsdict, optional: TorchMetrics dictionary for test evaluation.
freeze_backbonebool, default=False: If True, backbone parameters are frozen during training.
optimizer: type: Optimizer class to be instantiated. By default, it is set to torch.optim.Adam. Should be a subclass of torch.optim.Optimizer (e.g., torch.optim.SGD).
optimizer_kwargsdict, optional: Additional kwargs passed to the optimizer constructor.
lr_schedulertype, optional: Learning rate scheduler class to be instantiated. By default, it is set to None, which means no scheduler will be used. Should be a subclass of torch.optim.lr_scheduler.LRScheduler (e.g., torch.optim.lr_scheduler.StepLR).
lr_scheduler_kwargsdict, optional: Additional kwargs passed to the scheduler constructor.

_single_step(batch, batch_idx, step_name)[source]

Perform a single train/validation/test step. It consists in making a forward pass with the input data on the backbone model, computing the loss between the output and the input data, and logging the loss.

Parameters

batchtorch.Tensor: The input data. It must be a 2-element tuple of tensors, where the first tensor is the input data and the second tensor is the mask.
batch_idxint: The index of the batch.
step_namestr: The name of the step. It will be used to log the loss. The possible values are: “train”, “val” and “test”. The loss will be logged as “{step_name}_loss”.

Returns

torch.Tensor: A tensor with the loss value.

Parameters:

batch (torch.Tensor)
batch_idx (int)
step_name (str)

Return type:

torch.Tensor

predict_step(batch, batch_idx, dataloader_idx=None)[source]

Step function called during predict(). By default, it calls forward(). Override to add any processing logic.

The predict_step() is used to scale inference on multi-devices.

To prevent an OOM error, it is possible to use BasePredictionWriter callback to write the predictions to disk or database after each batch or on epoch end.

The BasePredictionWriter should be used while using a spawn based accelerator. This happens for Trainer(strategy="ddp_spawn") or training on 8 TPU cores with Trainer(accelerator="tpu", devices=8) as predictions won’t be returned.

Args:: batch: The output of your data iterable, normally a DataLoader. batch_idx: The index of this batch. dataloader_idx: The index of the dataloader that produced this batch.

(only if multiple dataloaders used)
Return:: Predicted output (optional).

Example

class MyModel(LightningModule):

    def predict_step(self, batch, batch_idx, dataloader_idx=0):
        return self(batch)

dm = ...
model = MyModel()
trainer = Trainer(accelerator="gpu", devices=2)
predictions = trainer.predict(model, dm)

Parameters:

in_channels (int)
out_channels (int)
loss_fn (torch.nn.Module)
learning_rate (float)