Window unpartition into original sequences and removing padding. Args: windows (tensor): input tokens with [B * num_windows, window_s

Uses SAM to calculate the image embedding for an image, and then allow repeated, efficient mask prediction given prompts. Ar

Create the criterion. Parameters: num_classes: number of object categories, omitting the special no-object category m

Predicts masks given an image and prompt embeddings, using a transformer architecture. Arguments: transformer_dim

Creates the matcher Params: cost_class: This is the relative weight of the classification error in the matching cost

Args: img_size (int): Input image size. patch_size (int): Patch size. in_chans (int): Number of input ima

Args: dim (int): Number of input channels. num_heads (int): Number of attention heads. qkv_bias (bool):

Args: kernel_size (Tuple): kernel size of the projection layer. stride (Tuple): stride of the projection layer.

Args: kernel_size (Tuple): kernel size of the projection layer. stride (Tuple): stride of the projection layer.

A transformer decoder that attends to an input image using queries whose positional embedding is supplied. Args: d

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

Run all_gather on arbitrary picklable data (not necessarily tensors) Args: data: any picklable object Returns: list[data]

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

Calculates boxes in XYXY format around masks. Return [0,0,0,0] for an empty mask. For input shape C1xC2x...xHxW, the output shape is C1xC2x..

Generates point grids for all crop layers.

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

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

Generate positional encoding for a grid of the specified size.

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