Removes small disconnected regions and holes in a mask. Returns the mask and an indicator of if the mask has been modified.

Compute a binary mask from an uncompressed RLE.

Loss used in RetinaNet for dense detection: https://arxiv.org/abs/1708.02002. Args: inputs: A float tensor of arbitrary shape.

Initialize the neck :param trunk: the backbone :param position_encoding: the positional encoding to use :param d_model: the di

Build SAM-style prompt encoder and mask decoder.

Find proper places to draw text given a binary mask.

Find proper places to draw text given a binary mask.

When outputting a single mask, if the stability score from the current single-mask output (based on output token 0) falls below a thr

Embeds box prompts.

Embeds mask inputs.

Embeds point prompts.

Identical to the corresponding method in the parent (SAM2VideoPredictor), but cloning the memories and their pos enc to enable compil

Encode the current image and its prediction into a memory feature.

Compute the losses related to the masks: the focal loss and the dice loss. and also the MAE or MSE loss between predicted IoUs and ac

Gets the batch size of the output given the batch size of the input prompts.

Compute stability scores of the mask logits based on the IoU between upper and lower thresholds.

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

Compute the image backbone features on the fly for the given img_ids.

Fuse the current frame's visual feature map with previous memory.

read video using decord.VideoReader Args: ele (dict): a dict contains the configuration of video. support keys: - vid

Reset all tracking inputs and results across the videos.

Run the memory encoder on `high_res_masks`. This is usually after applying non-overlapping constraints to object scores. Since their

Args: Same as in :meth:`__init__()`. Returns: fig (matplotlib.pyplot.figure): top level container for all th

Directly turn binary `mask_inputs` into a output mask logits without using SAM. (same input and output shapes as in _forward_sam_head

Add new points to a frame.

Generates point grids for all crop layers.

Generates a 2D grid of points evenly spaced in [0,1]x[0,1].

Calculate the start and end frame indices based on the given time range. Args: ele (dict): A dictionary containing optional 'video_s

Remove all input points or mask in a specific frame for a given object.

Compute region similarity as the Jaccard Index. Arguments: annotation (ndarray): binary annotation map. segmentation (ndarray

Compute region similarity as the Jaccard Index. Arguments: annotation (ndarray): binary annotation map. segmentation (ndarray

Compute the DICE loss, similar to generalized IOU for masks Args: inputs: A float tensor of arbitrary shape. The pred

Args: box_coord (tuple): a tuple containing x0, y0, x1, y1 coordinates, where x0 and y0 are the coordinates of th

Args: x_data (list[int]): a list containing x values of all the points being drawn. Length of list should match t

A post processor to fill small holes in mask scores with area under `max_area`.

Identical to the corresponding method in the parent (SAM2VideoPredictor), but cloning the backbone features and pos encoding to enabl

Forward video tracking on each frame (and sample correction clicks).

Generates a list of crop boxes of different sizes. Each layer has (2**i)**2 boxes for the ith layer.

Get 1D sine positional embedding as in the original Transformer paper.

Return an activation function given a string

Compute per-pixel accuracy. Args: gt_masks: List[np.ndarray], shape: (n_frames, h, w), dtype: np.uint8 pred_masks: List[np.ndarra

Args: gt_masks: List[np.ndarray], shape: (n_frames, h, w), dtype: np.uint8 pred_masks: List[np.ndarray], shape: (n_frames, h, w),

Args: inputs: A float tensor of arbitrary shape. The predictions for each example. targets: A float tensor with t

Filter masks at the edge of a crop, but not at the edge of the original image.