A callable which takes a dataset dict in Detectron2 Dataset format, and map it into a format used by the model. This is the default callable to be used to map your dataset dict into training data. You may need to follow it to implement your own one for customized logic, such as
| 18 | |
| 19 | |
| 20 | class DatasetMapper: |
| 21 | """ |
| 22 | A callable which takes a dataset dict in Detectron2 Dataset format, |
| 23 | and map it into a format used by the model. |
| 24 | |
| 25 | This is the default callable to be used to map your dataset dict into training data. |
| 26 | You may need to follow it to implement your own one for customized logic, |
| 27 | such as a different way to read or transform images. |
| 28 | See :doc:`/tutorials/data_loading` for details. |
| 29 | |
| 30 | The callable currently does the following: |
| 31 | |
| 32 | 1. Read the image from "file_name" |
| 33 | 2. Applies cropping/geometric transforms to the image and annotations |
| 34 | 3. Prepare data and annotations to Tensor and :class:`Instances` |
| 35 | """ |
| 36 | |
| 37 | @configurable |
| 38 | def __init__( |
| 39 | self, |
| 40 | is_train: bool, |
| 41 | *, |
| 42 | augmentations: List[Union[T.Augmentation, T.Transform]], |
| 43 | image_format: str, |
| 44 | use_instance_mask: bool = False, |
| 45 | use_keypoint: bool = False, |
| 46 | instance_mask_format: str = "polygon", |
| 47 | keypoint_hflip_indices: Optional[np.ndarray] = None, |
| 48 | precomputed_proposal_topk: Optional[int] = None, |
| 49 | recompute_boxes: bool = False, |
| 50 | ): |
| 51 | """ |
| 52 | NOTE: this interface is experimental. |
| 53 | |
| 54 | Args: |
| 55 | is_train: whether it's used in training or inference |
| 56 | augmentations: a list of augmentations or deterministic transforms to apply |
| 57 | image_format: an image format supported by :func:`detection_utils.read_image`. |
| 58 | use_instance_mask: whether to process instance segmentation annotations, if available |
| 59 | use_keypoint: whether to process keypoint annotations if available |
| 60 | instance_mask_format: one of "polygon" or "bitmask". Process instance segmentation |
| 61 | masks into this format. |
| 62 | keypoint_hflip_indices: see :func:`detection_utils.create_keypoint_hflip_indices` |
| 63 | precomputed_proposal_topk: if given, will load pre-computed |
| 64 | proposals from dataset_dict and keep the top k proposals for each image. |
| 65 | recompute_boxes: whether to overwrite bounding box annotations |
| 66 | by computing tight bounding boxes from instance mask annotations. |
| 67 | """ |
| 68 | if recompute_boxes: |
| 69 | assert use_instance_mask, "recompute_boxes requires instance masks" |
| 70 | # fmt: off |
| 71 | self.is_train = is_train |
| 72 | self.augmentations = T.AugmentationList(augmentations) |
| 73 | self.image_format = image_format |
| 74 | self.use_instance_mask = use_instance_mask |
| 75 | self.instance_mask_format = instance_mask_format |
| 76 | self.use_keypoint = use_keypoint |
| 77 | self.keypoint_hflip_indices = keypoint_hflip_indices |
no outgoing calls
no test coverage detected