SemanticSegmentation

class flash.image.segmentation.model.SemanticSegmentation(num_classes, backbone='resnet50', backbone_kwargs=None, head='fpn', head_kwargs=None, pretrained=True, loss_fn=None, optimizer='Adam', lr_scheduler=None, metrics=None, learning_rate=None, multi_label=False, output_transform=None)

SemanticSegmentation is a Task for semantic segmentation of images. For more details, see Semantic Segmentation.

Parameters

• num_classes (int) – Number of classes to classify.

• backbone (Union[str, Module]) – A string or model to use to compute image features.

• backbone_kwargs (Optional[Dict]) – Additional arguments for the backbone configuration.

• head (str) – A string or (model, num_features) tuple to use to compute image features.

• head_kwargs (Optional[Dict]) – Additional arguments for the head configuration.

• pretrained (Union[bool, str]) – Use a pretrained backbone.

• loss_fn (Optional[TypeVar(LOSS_FN_TYPE, Callable, Mapping, Sequence, None)]) – Loss function for training.

• optimizer (TypeVar(OPTIMIZER_TYPE, str, Callable, Tuple[str, Dict[str, Any]], None)) – Optimizer to use for training.

• lr_scheduler (Optional[TypeVar(LR_SCHEDULER_TYPE, str, Callable, Tuple[str, Dict[str, Any]], Tuple[str, Dict[str, Any], Dict[str, Any]], None)]) – The LR scheduler to use during training.

• metrics (Optional[TypeVar(METRICS_TYPE, Metric, Mapping, Sequence, None)]) – Metrics to compute for training and evaluation. Can either be an metric from the torchmetrics package, a custom metric inherenting from torchmetrics.Metric, a callable function or a list/dict containing a combination of the aforementioned. In all cases, each metric needs to have the signature metric(preds,target) and return a single scalar tensor. Defaults to torchmetrics.IOU.

• learning_rate (Optional[float]) – Learning rate to use for training. If None (the default) then the default LR for your chosen optimizer will be used.

• multi_label (bool) – Whether the targets are multi-label or not.

• output – The Output to use when formatting prediction outputs.

• output_transform (Optional[TypeVar(OUTPUT_TRANSFORM_TYPE, flash.core.data.io.output_transform.OutputTransform, None)]) – OutputTransform use for post processing samples.

classmethod available_finetuning_strategies(cls)

Returns a list containing the keys of the available Finetuning Strategies.

Return type

List[str]

classmethod available_lr_schedulers(cls)

Returns a list containing the keys of the available LR schedulers.

Return type

List[str]

classmethod available_optimizers(cls)

Returns a list containing the keys of the available Optimizers.

Return type

List[str]

classmethod available_outputs(cls)

Returns the list of available outputs (that can be used during prediction or serving) for this Task.

Examples

..testsetup:

>>> from flash import Task

>>> print(Task.available_outputs())
['preds', 'raw']

Return type

List[str]