Performs the matching Params: outputs: This is a dict that contains at least these entries: "pred_logits": Tenso

r""" Args: query, key, value: map a query and a set of key-value pairs to an output. See "Attention Is All You Need" for more

forward for all data, including sa-1b, generic seg, part seg data currently only support interactive segmentation on sa-1b, stay tune

:param query (N, Length_{query}, C) :param reference_points (N, Length_{query}, n_levels, 2), range

task: seg/det TODO add sam

Input: - tgt: nq, bs, d_model - memory: hw, bs, d_model - pos: hw, bs, d_model - refpoints_un

Input: - tgt/tgt_query_pos: nq, bs, d_model -

Input: - memory: bs, \sum{hw}, d_model - memory_padding_mask: bs, \sum{hw} - spatial_shapes: nlevel, 2 Output:

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

Generate regular square grid of points in [0, 1] x [0, 1] coordinate space. Args: R (int): The number of grids to sample, one for ea

Build a pixel decoder from `cfg.MODEL.MASK_FORMER.PIXEL_DECODER_NAME`.

Returns: output (VisImage): the image output containing the visualizations added to the image.

Build a pixel decoder from `cfg.MODEL.MASK_FORMER.PIXEL_DECODER_NAME`.

Find `num_points` most uncertain points from `uncertainty_map` grid. Args: uncertainty_map (Tensor): A tensor of shape (N, 1, H, W)

Initialize the weights in backbone. Args: pretrained (str, optional): Path to pre-trained weights. Defaults to No

Initialize the weights in backbone. Args: pretrained (str, optional): Path to pre-trained weights. Defaults to Non

Initialize the weights in backbone. Args: pretrained (str, optional): Path to pre-trained weights. Defaults to No

Initialize the weights in backbone. Args: pretrained (str, optional): Path to pre-trained weights. Defaults to Non

Compute the losses related to the bounding boxes, the L1 regression loss and the GIoU loss targets dicts must contain the key "boxes" conta

Compute the losses related to the bounding boxes, the L1 regression loss and the GIoU loss targets dicts must contain the key "boxes" conta

Compute the losses related to the bounding boxes, the L1 regression loss and the GIoU loss targets dicts must contain the key "boxes" conta

Classification loss (Binary focal loss) targets dicts must contain the key "labels" containing a tensor of dim [nb_target_boxes]

Classification loss (Binary focal loss) targets dicts must contain the key "labels" containing a tensor of dim [nb_target_boxes]

Classification loss (NLL) targets dicts must contain the key "labels" containing a tensor of dim [nb_target_boxes]

Classification loss (NLL) targets dicts must contain the key "labels" containing a tensor of dim [nb_target_boxes]

Classification loss (Binary focal loss) targets dicts must contain the key "labels" containing a tensor of dim [nb_target_boxes]

Classification loss (Binary focal loss) targets dicts must contain the key "labels" containing a tensor of dim [nb_target_boxes]

Classification loss (Binary focal loss) targets dicts must contain the key "labels" containing a tensor of dim [nb_target_boxes]

Compute the losses related to the masks: the focal loss and the dice loss. targets dicts must contain the key "masks" containing a tensor of d

Compute the losses related to the masks: the focal loss and the dice loss. targets dicts must contain the key "masks" containing a tensor of d

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