Predicts masks. See 'forward' for more details.

Propagate the input points across frames to track in the entire video.

Prepare inference_state and consolidate temporary outputs before tracking.

Select up to `max_cond_frame_num` conditioning frames from `cond_frame_outputs` that are temporally closest to the current frame at `frame_id

Calculates the image embeddings for the provided image, allowing masks to be predicted with the 'predict' method. Arguments:

Initialize a inference state.

Propagate the input points across frames to track in the entire video.

Prepare inference_state and consolidate temporary outputs before tracking.

Expects a tensor of shape Bx4. The coordinates can be in absolute image or normalized coordinates, if the coords are in absolute imag

Initialize a inference state.

Partition into non-overlapping windows with padding if needed. Args: x (tensor): input tokens with [B, H, W, C]. window_size

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

Get the images

Using a SAM 2 model, generates masks for the entire image. Generates a grid of point prompts over the image, then filters low

Uses SAM-2 to calculate the image embedding for an image, and then allow repeated, efficient mask prediction given prompts.

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

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

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)

Encodes prompts for input to SAM's mask decoder. Arguments: embed_dim (int): The prompts' embedding dimension im

Transforms for SAM2.

Map model-side object index to client-side object id.

Add new mask to a frame.