Detection

class torchok.tasks.detection.SingleStageDetectionTask(hparams: DictConfig, backbone_name: str, head_name: str, neck_name: str, num_scales: Optional[int] = None, backbone_params: Optional[dict] = None, neck_params: Optional[dict] = None, head_params: Optional[dict] = None, **kwargs)

Bases: BaseTask

__init__(hparams: DictConfig, backbone_name: str, head_name: str, neck_name: str, num_scales: Optional[int] = None, backbone_params: Optional[dict] = None, neck_params: Optional[dict] = None, head_params: Optional[dict] = None, **kwargs)

Init SingleStageDetectionTask.

Parameters

• hparams – Hyperparameters that set in yaml file.

• backbone_name – name of the backbone architecture in the BACKBONES registry.

• neck_name – name of the head architecture in the DETECTION_NECKS registry.

• head_name – name of the neck architecture in the HEADS registry.

• num_scales – number of feature maps that will be passed from backbone to the neck starting from the last one. Example: for backbone output [layer1, layer2, layer3, layer4] and num_scales=3 neck will get [layer2, layer3, layer4].

• backbone_params – parameters for backbone constructor.

• neck_params – parameters for neck constructor. in_channels will be set automatically based on backbone.

• head_params – parameters for head constructor. in_channels will be set automatically based on neck.

• inputs – information about input model shapes and dtypes.

forward(x: Tensor) → Tensor

Forward method.

forward_with_gt(batch: Dict[str, Union[Tensor, int]]) → Dict[str, Any]

Forward with ground truth labels.

as_module() → Sequential

Method for model representation as sequential of modules(need for checkpointing).

training_step(batch: Dict[str, Union[Tensor, int]], batch_idx: int) → Dict[str, Tensor]

Complete training loop.

validation_step(batch: Dict[str, Union[Tensor, int]], batch_idx: int, dataloader_idx: int = 0) → Dict[str, Tensor]

Complete validation loop.

test_step(batch: Dict[str, Union[Tensor, int]], batch_idx: int) → None

Complete test loop.

predict_step(batch: Dict[str, Union[Tensor, int]], batch_idx: int) → Dict[str, Tensor]

Complete predict loop.

training: bool

precision: Union[int, str]

prepare_data_per_node: bool

allow_zero_length_dataloader_with_multiple_devices: bool