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

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.

Generate positional encoding for a grid of the specified size.

Predict masks given image and prompt embeddings. Arguments: image_embeddings (torch.Tensor): the embeddings from the image

Args: image_embedding (torch.Tensor): image to attend to. Should be shape B x embedding_dim x h x w for any h and w.

Embeds different types of prompts, returning both sparse and dense embeddings. Arguments: points (tuple(torch.Tens

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-

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

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

Load a pretrained model from the Hugging Face hub. Arguments: model_id (str): The Hugging Face repository ID. **

Load a pretrained model from the Hugging Face hub. Arguments: model_id (str): The Hugging Face repository ID. **

Load a pretrained model from the Hugging Face hub. Arguments: model_id (str): The Hugging Face repository ID. **

Generates masks for the given image. Arguments: image (np.ndarray): The image to generate masks for, in HWC uint8 format.

Returns the image embeddings for the currently set image, with shape 1xCxHxW, where C is the embedding dimension and (H,W) are

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

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

:param img: H W C int :param mask: H W int :param seq: aug_pipe :return:img H W C int mask H W int

Initialize an inference state.

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