The forward expects a NestedTensor, which consists of: - samples.tensor: batched images, of shape [batch_size x 3 x H x W]

This performs the loss computation. Parameters: outputs: dict of tensors, see the output specification of the model for the form

Generalized IoU from https://giou.stanford.edu/ The boxes should be in [x0, y0, x1, y1] format Returns a [N, M] pairwise matrix, where

Generalized IoU from https://giou.stanford.edu/ The boxes should be in [x0, y0, x1, y1] format Returns a [N, M] pairwise matrix, where

:param joints: [num_joints, 3] :return: target, target_weight(1: visible, 0: invisible)

:param joints: [num_joints, 3] :return: target, target_weight(1: visible, 0: invisible)

:param target_poses [[], [], [], []] :return: ndarray (NUM_TARGETS, WINDOW_SIZE, WINDOW_SIZE)

:param target_poses [[], [], [], []] :return: ndarray (NUM_TARGETS, WINDOW_SIZE, WINDOW_SIZE)

:return target_poses: [[], [], [], []]

:return target_poses: [[], [], [], []]

resume training from previous checkpoint :param fname: filename(with path) of checkpoint file :return: model, optimizer, checkpoint epoch

resume training from previous checkpoint :param fname: filename(with path) of checkpoint file :return: model, optimizer, checkpoint epoch

Compute the cardinality error, ie the absolute error in the number of predicted non-empty boxes This is not really a loss, it is intended for

Compute the cardinality error, ie the absolute error in the number of predicted non-empty boxes This is not really a loss, it is intended for

:param extension_vertex: :param fetch_list: 'aerial_image_chw': 'aerial_image_hwc': 'walked_pat

:param extension_vertex: :param fetch_list: 'aerial_image_chw': 'aerial_image_hwc': 'walked_pat

:return: if is_key_point: res == [(x,y), ..., (x,y)] # time_step == 1 # + else: res == [(x,y), ..., (x,y

:return: if is_key_point: res == [(x,y), ..., (x,y)] # time_step == 1 # + else: res == [(x,y), ..., (x,y

Compute the bounding boxes around the provided masks The masks should be in format [N, H, W] where N is the number of masks, (H, W) are the spati

Compute the bounding boxes around the provided masks The masks should be in format [N, H, W] where N is the number of masks, (H, W) are the spati