mednet.models.classify.alexnet

AlexNet network architecture, from [ALEXNET-2012].

Classes

Alexnet([loss_type, loss_arguments, ...])

AlexNet network architecture model, from [ALEXNET-2012].
class mednet.models.classify.alexnet.Alexnet(loss_type=<class 'torch.nn.modules.loss.BCEWithLogitsLoss'>, loss_arguments={}, optimizer_type=<class 'torch.optim.adam.Adam'>, optimizer_arguments={}, scheduler_type=None, scheduler_arguments={}, model_transforms=[], augmentation_transforms=[], pretrained=False, num_classes=1)[source]

Bases: Model

AlexNet network architecture model, from [ALEXNET-2012].

Note: only usable with a normalized dataset

Parameters:

  • loss_type (type[Module]) –

    The loss to be used for training and evaluation.

    Warning

    The loss should be set to always return batch averages (as opposed to the batch sum), as our logging system expects it so.

  • loss_arguments (dict[str, Any]) – Arguments to the loss.

  • optimizer_type (type[Optimizer]) – The type of optimizer to use for training.

  • optimizer_arguments (dict[str, Any]) – Arguments to the optimizer after params.

  • scheduler_type (type[LRScheduler] | None) – The type of scheduler to use for training.

  • scheduler_arguments (dict[str, Any]) – Arguments to the scheduler after params.

  • model_transforms (Sequence[Callable[[Tensor], Tensor]]) – An optional sequence of torch modules containing transforms to be applied on the input before it is fed into the network.

  • augmentation_transforms (Sequence[Callable[[Tensor], Tensor]]) – An optional sequence of torch modules containing transforms to be applied on the input before it is fed into the network.

  • pretrained (bool) – If set to True, loads pretrained model weights during initialization, else trains a new model.

  • num_classes (int) – Number of outputs (classes) for this model.

forward(x)[source]

Forward the input tensor through the network, producing a prediction.

Parameters:

x – The tensor input to be forwarded.

Returns:

The prediction, as a tensor.

set_normalizer(dataloader)[source]

Initialize the normalizer for the current model.

This function is NOOP if pretrained = True (normalizer set to imagenet weights, during contruction).

Parameters:

dataloader (DataLoader) – A torch Dataloader from which to compute the mean and std. Will not be used if the model is pretrained.

Return type:

None