Load and prepare dataset dicts for instance detection/segmentation and semantic segmentation. Args: dataset_names (list[str]): a list

Load and prepare dataset dicts for instance detection/segmentation and semantic segmentation. Args: dataset_names (list[str]): a list

Dump an "Instances" object to a COCO-format json that's used for evaluation. Args: instances (Instances): img_id (int): the

Dump an "Instances" object to a COCO-format json that's used for evaluation. Args: instances (Instances): img_id (int): the

Args: anchors (list[Boxes]): anchors for each feature map. gt_instances: the ground-truth instances for each image.

Args: anchors (list[Boxes]): anchors for each feature map. gt_instances: the ground-truth instances for each image.

Load Pascal VOC detection annotations to Detectron2 format. Args: dirname: Contain "Annotations", "ImageSets", "JPEGImages"

Load Pascal VOC detection annotations to Detectron2 format. Args: dirname: Contain "Annotations", "ImageSets", "JPEGImages"

Compute the default losses for box head in Fast(er) R-CNN, with softmax cross entropy loss and smooth L1 loss. Returns:

Compute the default losses for box head in Fast(er) R-CNN, with softmax cross entropy loss and smooth L1 loss. Returns:

If gradient clipping is enabled through config options, wraps the existing optimizer instance of some type OptimizerType to become an instanc

If gradient clipping is enabled through config options, wraps the existing optimizer instance of some type OptimizerType to become an instanc

Parse a PASCAL VOC xml file.

Parse a PASCAL VOC xml file.

Deprecated

Returns: list[Tensor]: A list of Tensors of predicted class-specific or class-agnostic boxes for each image. Elem

Deprecated

Returns: list[Tensor]: A list of Tensors of predicted class-specific or class-agnostic boxes for each image. Elem

Deprecated

Returns: list[Tensor]: A list of Tensors of predicted class probabilities for each image. Element i has shape (Ri

Deprecated

Returns: list[Tensor]: A list of Tensors of predicted class probabilities for each image. Element i has shape (Ri

Register a dataset in COCO's json annotation format for instance detection, instance segmentation and keypoint detection. (i.e., Type 1 a

Register a dataset in COCO's json annotation format for instance detection, instance segmentation and keypoint detection. (i.e., Type 1 a

Create configs and perform basic setups.

Create configs and perform basic setups.

Compute the smooth L1 loss for box regression. Returns: scalar Tensor

Compute the smooth L1 loss for box regression. Returns: scalar Tensor

Compute the softmax cross entropy loss for box classification. Returns: scalar Tensor

Compute the softmax cross entropy loss for box classification. Returns: scalar Tensor

Args: cfg (CfgNode): model (nn.Module): evaluators (list[DatasetEvaluator] or None): if None, will call

Args: cfg (CfgNode): model (nn.Module): evaluators (list[DatasetEvaluator] or None): if None, will call

Compute VOC AP given precision and recall. If use_07_metric is true, uses the VOC 07 11-point method (default:False).

Compute VOC AP given precision and recall. If use_07_metric is true, uses the VOC 07 11-point method (default:False).

rec, prec, ap = voc_eval(detpath, annopath, imagesetfile,

rec, prec, ap = voc_eval(detpath, annopath, imagesetfile,

Args: dataset_dict (dict): Metadata of one image, in Detectron2 Dataset format. Returns: dict: a format that

Args: dataset_dict (dict): Metadata of one image, in Detectron2 Dataset format. Returns: dict: a format that

Args: dataset_dict (dict): Metadata of one image, in Detectron2 Dataset format. Returns: dict: a format that

Args: dataset_dict (dict): Metadata of one image, in Detectron2 Dataset format. Returns: dict: a format that

NOTE: this interface is experimental. Args: in_channels (int): number of input feature channels. When using multiple

NOTE: this interface is experimental. Args: input_shape (ShapeSpec): shape of the input feature to this module

Args: dataset_name (str): name of the dataset, e.g., "voc_2007_test"

Args: dataset_name (str): name of the dataset to be evaluated. It must have either the following corresponding me

NOTE: this interface is experimental. Args: in_channels (int): number of input feature channels. When using multiple

NOTE: this interface is experimental. Args: input_shape (ShapeSpec): shape of the input feature to this module