`maskmem_pos_enc` is the same across frames and objects, so we cache it as a constant in the inference session to reduce session stor

Load an attribute and add it to self, if it isn't already loaded. :param attr_name: The name of the attribute to be loaded. :

Positionally encode points that are normalized to [0,1].

Reset all tracking inputs and results across the videos.

Add new points to a frame.

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..

Computes the stability score for a batch of masks. The stability score is the IoU between the binary masks obtained by thresholding the p

Check that the sweeps folder was downloaded if required. :param filename: The filename of the sample_data.

Add new points and labels to previous point inputs (add at the end).

3x3 convolution with padding

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

Positionally encode points that are not normalized to [0,1].

For a given sample, return all the sample_datas in chronological order. :param sample_token: Sample token. :return: A list of

Produces two segmentation masks as numpy arrays of size H x W each, where H and W are the height and width of the camera image respec

Sample points in [0, 1] x [0, 1] coordinate space based on their uncertainty. The unceratinties are calculated for each point using 'unce

Load the video frames from video_path. The frames are resized to image_size as in the model and are loaded to GPU if offload_video_to_cpu=Fal

Encodes masks to an uncompressed RLE, in the format expected by pycoco tools.

Build a mapping from name to index to look up index in O(1) time. :param category: The nuImages category table. :return: The mapping from

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

:param img: 原始图片 :param mask: 网络输出，格式：[h, w]

Compute a binary mask from an uncompressed RLE.

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

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

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

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

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.

Creates gradient clipping closure to clip by value or by norm, according to the provided config.

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