A transformer block with four layers: (1) self-attention of sparse inputs, (2) cross attention of sparse inputs to dense inputs, (3)

SAM predicts object masks from an image and input prompts. Arguments: image_encoder (ImageEncoderViT): The backbone used t

Expects a torch tensor with shape Bx4. Requires the original image size in (H, W) format.

Expects batched images with shape BxCxHxW and float format. This transformation may not exactly match apply_image. apply_image is

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.

Predicts masks end-to-end from provided images and prompts. If prompts are not known in advance, using SamPredictor is recomm

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

Generate positional encoding for a grid of the specified size.

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

Predict masks for the given input prompts, using the currently set image. Arguments: point_coords (np.ndarray or None): A