Input: - srcs: List of multi features [bs, ci, hi, wi] - masks: List of multi masks [bs, hi, wi] - refpoi

Input: - src: [bs, sum(hi*wi), 256] - pos: pos embed for src. [bs, sum(hi*wi), 256] - spatial_shapes: h,w

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

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

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

Forward function. Args: x: input features with shape of (num_windows*B, N, C) mask: (0/-inf) mask with shape of (num_

Forward function. Args: x: Input feature, tensor size (B, H*W, C). H, W: Spatial resolution of the input feature.

Forward function. Args: x: Input feature, tensor size (B, H*W, C). H, W: Spatial resolution of the input feature.

Forward function. Args: x: Input feature, tensor size (B, H*W, C). H, W: Spatial resolution of the input feature.

Forward function.

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

Perform the computation Parameters: outputs: raw outputs of the model target_sizes: tensor of dimension [batch_size x

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

Transform a json object string into a Box object. If the incoming json is a list, you must use BoxList.from_json. :param jso

Transform a json object string into a BoxList object. If the incoming json is a dict, you must use Box.from_json. :param jso

Transform a yaml object string into a BoxList object. :param yaml_string: string to pass to `yaml.load` :param f

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/ Input: - boxes1, boxes2: N,4 Output: - giou: N, 4

get_gaussian_map_from_points B,C,H,W -> B,N,2 float(0, 1) float(0, 1) softargmax function Args: hm (float): Input images(

return the dicf contained in args. e.g: >>> with open(path, 'w') as f: json.dump(get_raw_dict(args), f, indent=2

Equivalent to nn.functional.interpolate, but with support for empty batch sizes. This will eventually be supported natively by PyTorch, and t

Return value of key as a list :param item: key of value to transform :param mod: function to map against list :param default

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

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

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 softmax values for each sets of scores in x.

[summary] Args: img ([type]): 3,H,W. tensor. boxes (): tensor(Kx4) or list of tensor(1x4). labels ([type]): list of ints.

Function to plot specific fields from training log(s). Plots both training and test results. :: Inputs - logs = list containing Path objects

[summary] Args: img ([type]): 3,H,W. tensor. boxes ([type]): Kx4. tensor labels ([type]): K. tensor. return: