从二值掩码生成最大连通区域的外接矩形掩码 mask: 输入二值掩码 (H, W)，0为背景，1为目标 return: 矩形掩码 (H, W)，目标区域为最大连通区域的外接框

Get the defined colormap. :return: A mapping from the class names to the respective RGB values.

Return the ego pose data of the <= 13 sample_datas associated with this sample. The method return translation, rotation, rotation_rat

Check if there is a desired font present in the user's system. If there is, use that font; otherwise, use a default font. :param fonts_va

从二值掩码中获取最大的连通区域 mask: 输入二值掩码 (H, W)，0为背景，1为目标 return: 只保留最大连通区域的掩码

Get the trajectory of the ego vehicle and optionally rotate and center it. :param sample_token: Sample token. :param rotation

This returns the index of the record in a table in constant runtime. :param table_name: Table name. :param token: Token of th

:param img: H W C int :param mask: H W int :param seq: aug_pipe :return:img H W C int mask H W int

Initialize an inference state.

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

Load the video frames from a directory of JPEG files ("<frame_index>.jpg" format). The frames are resized to image_size x image_size and are

Load the video frames from a video file.

compute bounding box given an input mask Inputs: - masks: [B, 1, H, W] masks, dtype=torch.Tensor Returns: - box_coords: [B, 1,

If gradient clipping is enabled through config options, wraps the existing optimizer type to become a new dynamically created class Optimizer

More memory-friendly matching

Perform PostProcessing on output masks.

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.

Prepare inference_state and consolidate temporary outputs before tracking.

Remove all input points or mask in all frames throughout the video.

Remove all input points or mask in all frames throughout the video.

Sample 1 random point (along with its label) from the center of each error region, that is, the point with the largest distance to the bounda

Sample `num_pt` random points (along with their labels) independently from the error regions. Inputs: - gt_masks: [B, 1, H_im, W_im] mas

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:

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

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

Args: windows: (num_windows*B, window_size, window_size, C) window_size (int): Window size H (int): Height of image

Args: windows: (num_windows*B, window_size, window_size, C) window_size (int): Window size H (int): Height of image

Same input/output format as :meth:`SemanticSegmentor.forward`

Implement lazy loading for the database tables. Otherwise throw the default error. :param attr_name: The name of the variable to look