TorchVisionODAdapter#

class TorchVisionODAdapter[source]#

Bases: Module

Adapter for interfacing with TorchVision’s object detection models.

The purpose of this adapter is: 1) to convert input BoxLists to dicts before feeding them into the model 2) to convert detections output by the model as dicts into BoxLists

Additionally, it automatically converts to/from 1-indexed class labels (which is what the TorchVision models expect).

__init__(model: torch.nn.Module, ignored_output_inds: Sequence[int] = [0]) → None[source]#

Constructor.

Parameters

  • model (nn.Module) – A torchvision object detection model.

  • ignored_output_inds (Iterable[int], optional) – Class labels to exclude. Defaults to [0].

Return type

None

Methods

__init__(model[, ignored_output_inds])

Constructor.

boxlist_to_model_input_dict(boxlist)

Convert BoxList to dict compatible w/ torchvision detection models.

forward(input[, targets])

Forward pass.

model_output_dict_to_boxlist(out)

Convert model output dict to BoxList.
__contains__(key: str) → bool#
Parameters

key (str) –

Return type

bool

__getitem__(key: Any) → _MockObject#
Parameters

key (Any) –

Return type

_MockObject

__init__(model: torch.nn.Module, ignored_output_inds: Sequence[int] = [0]) → None[source]#

Constructor.

Parameters

  • model (nn.Module) – A torchvision object detection model.

  • ignored_output_inds (Iterable[int], optional) – Class labels to exclude. Defaults to [0].

Return type

None

static __new__(cls, *args: Any, **kwargs: Any) → Any#
Parameters

  • args (Any) –

  • kwargs (Any) –

Return type

Any

boxlist_to_model_input_dict(boxlist: BoxList) → dict[source]#

Convert BoxList to dict compatible w/ torchvision detection models.

Also, make class labels 1-indexed.

Parameters

boxlist (BoxList) – A BoxList with a “class_ids” field.

Returns

A dict with keys: “boxes” and “labels”.

Return type

dict

forward(input: torch.Tensor, targets: Optional[Iterable[BoxList]] = None) → Union[Dict[str, Any], List[BoxList]][source]#

Forward pass.

Parameters

  • input (Tensor[batch_size, in_channels, in_height, in_width]) – batch of images.

  • targets (Optional[Iterable[BoxList]], optional) – In training mode, should be Iterable[BoxList]], with each BoxList having a ‘class_ids’ field. In eval mode, should be None. Defaults to None.

Returns

In training mode, returns a dict of losses. In eval mode, returns a list of BoxLists containing predicted boxes, class_ids, and scores. Further filtering based on score should be done before considering the prediction “final”.

Return type

Union[Dict[str, Any], List[BoxList]]

model_output_dict_to_boxlist(out: dict) → BoxList[source]#

Convert model output dict to BoxList.

Also, exclude any null classes and make class labels 0-indexed.

Parameters

out (dict) – A dict output by a torchvision detection model in eval mode.

Returns

A BoxList with “class_ids” and “scores” fields.

Return type

BoxList