InstanceSegmentation

class flash.image.instance_segmentation.model.InstanceSegmentation(num_classes, backbone='resnet18_fpn', head='mask_rcnn', pretrained=True, optimizer='Adam', lr_scheduler=None, learning_rate=None, output_transform=<flash.image.instance_segmentation.data.InstanceSegmentationOutputTransform object>, predict_kwargs=None, **kwargs)

The InstanceSegmentation is a Task for detecting objects in images. For more details, see Object Detection.

Parameters

• num_classes (int) – The number of object classes.

• backbone (Optional[str]) – String indicating the backbone CNN architecture to use.

• head (Optional[str]) – String indicating the head module to use on top of the backbone.

• pretrained (bool) – Whether the model should be loaded with it’s pretrained weights.

• 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.

• learning_rate (Optional[float]) – The learning rate to use for training.

• predict_kwargs (Optional[Dict]) – dictionary containing parameters that will be used during the prediction phase.

• **kwargs – additional kwargs used for initializing the task

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]

property predict_kwargs: Dict[str, Any]

The kwargs used for the prediction step.

Return type

Dict[str, Any]