Forward pass. Args: x (tensor): input Returns: tensor: interpolated data_list

Forward pass. Args: x (tensor): input Returns: tensor: output

Forward pass. Returns: tensor: output

Forward pass. Args: x (tensor): input Returns: tensor: output

Forward pass. Returns: tensor: output

Args: batched_inputs: a list, batched outputs of :class:`DatasetMapper`. Each item in the list contains the input

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

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

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

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.

Forward function.

Args: x: Tensor of shape (N,C,H,W). H, W must be a multiple of ``self.size_divisibility``. Returns: dict[str-

Returns: In training, returns (None, dict of losses) In inference, returns (CxHxW logits, {})

Returns: In training, returns (None, dict of losses) In inference, returns (CxHxW logits, {})

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