Get vid ids that satisfy given filter conditions. :param vidIds (int array) : get vids for given ids :param catIds (int array

Get vid ids that satisfy given filter conditions. :param vidIds (int array) : get vids for given ids :param catIds (int array

this will perform the index select, cat the tensors, and provide the attn_bias from cache

this will perform the index select, cat the tensors, and provide the attn_bias from cache

Load and prepare dataset dicts for instance detection/segmentation and semantic segmentation. Args: dataset_names (str or list[str])

Load and prepare dataset dicts for instance detection/segmentation and semantic segmentation. Args: dataset_names (str or list[str])

Get relative positional embeddings according to the relative positions of query and key sizes. Args: q_size (int): size of qu

fuse the objects queries of all frames and predict an overall score based on the fused objects queries :param decoder_output: instanc

Register a dataset in YTVIS's json annotation format for instance tracking. Args: name (str): the name that identifies a dataset

in order to maintain consistency between the initial query and the guided results (segmenter prediction) :param output: segmenter pre

Create configs and perform basic setups.

Compute and display summary metrics for evaluation results. Note this functin can *only* be applied on the default parameter setting

Compute and display summary metrics for evaluation results. Note this functin can *only* be applied on the default parameter setting

Args: x: (B, H, W, C) window_size (int): window size Returns: windows: (num_windows*B, window_size, window_size, C)

NOTE: this interface is experimental. Args: input_shape: shapes (channels and stride) of the input features n

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

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

Args: prob (float): probability of flip. horizontal (boolean): whether to apply horizontal flipping verti

Derive the desired score numbers from summarized COCOeval. Args: coco_eval (None or COCOEval): None represents no predict

Embeds box prompts.

Embeds mask inputs.

Embeds point prompts.

Evaluate predictions. Fill self._results with the metrics of the tasks.

Evaluate predictions. Fill self._results with the metrics of the tasks.

Evaluate the coco results using COCOEval API.

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

Args: input (dict): one dataset dict with "image" field being a CHW tensor Returns: dict: one output dict

Prepare ._gts and ._dts for evaluation based on params :return: None

Prepare ._gts and ._dts for evaluation based on params :return: None