If `resume==True` and `cfg.OUTPUT_DIR` contains the last checkpoint (defined by a `last_checkpoint` file), resume from the file. Resu

Transpose/reshape a tensor from (N, (A x K), H, W) to (N, (HxWxA), K)

Soft non-max suppression algorithm. Implementation of [Soft-NMS -- Improving Object Detection With One Line of Codec] (https://arxiv.org

Calculate the ious between each bbox of bboxes1 and bboxes2. Args: bboxes1(ndarray): shape (n, 4) bboxes2(ndarray): shape (k,

Arguments: box_cls, box_delta: Same as the output of :meth:`RetinaNetHead.forward` anchors (list[Boxes]): A list of #

Create configs and perform basic setups.

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

Performs soft non-maximum suppression in a batched fashion. Each index value correspond to a category, and NMS will not be applied betwe

:param num_imgs: int :param all_gt: list of np.array[m, 8], [:, 4] == 1 indicates ignored regions, which should be dro

r"""Checkpoint a model or part of the model Checkpointing works by trading compute for memory. Rather than storing all intermediate activatio

Create a parser with some common arguments used by detectron2 users. Args: epilog (str): epilog passed to ArgumentParser describing

Create a parser with some common arguments used by detectron2 users. Args: epilog (str): epilog passed to ArgumentParser describing

Create a parser with some common arguments used by detectron2 users. Args: epilog (str): epilog passed to ArgumentParser describing

Create a parser with some common arguments used by detectron2 users. Args: epilog (str): epilog passed to ArgumentParser describing

:param all_gt: list of np.array[m, 8] :param all_det: list of np.array[m, 6], truncation and occlusion not necessary :param allheight:

:param gt0: np.array[ng, 5], ground truth results [x, y, w, h, ignore] :param dt0: np.array[nd, 5], detection results [x, y, w, h, score]

Args: box_centers: [N, 2] anchor_centers: [M, 2] Returns:

Single-image inference. Return bounding-box detection results by thresholding on scores and applying non-maximum suppression (NMS).

Parse information from a line in a requirements text file

Parse the package dependencies listed in a requirements file but strips specific versioning information. Args: fname (str):

Normalize, pad and batch the input images.

Create configs and perform basic setups.

Create configs and perform basic setups.

Create configs and perform basic setups.

Performs soft non-maximum suppression algorithm on axis aligned boxes Args: boxes (Tensor[N, 5]): boxes where NMS will be

Performs soft non-maximum suppression algorithm on rotated boxes Args: boxes (Tensor[N, 5]): boxes where NMS will be perf