Initialize a transformer encoder layer. Args: activation: Activation function to use in the feedforward network

use_prev_mem_frame: bool, whether to condition on previous memory frames for adding points use_stateless_refinement: bool, whether to

Transforms for SAM2.

Args: tensor (Tensor[float]): a Nx4 matrix. Each row is (x1, y1, x2, y2).

Args: img (ndarray): an RGB image of shape (H, W, 3) in range [0, 255]. scale (float): scale the input image

Args: img_rgb: a numpy array of shape (H, W, C), where H and W correspond to the height and width of the image re

Args: output_size (tuple): h, w spatial_scale (float): scale the input boxes by this number sampling_rati

Arguments: keypoints: A Tensor, numpy array, or list of the x, y, and visibility of each keypoint. The shape shou

Args: tensor (Tensor[float]): a Nx5 matrix. Each row is (x_center, y_center, width, height, angle),

Args: tensor: bool Tensor of N,H,W, representing N instances in the image.

Arguments: polygons (list[list[np.ndarray]]): The first level of the list correspond to individual instances,

Args: tensor: (N, M, M) mask tensor that defines the mask within each ROI.

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)

b :param path: Path to colmap scene main folder.

Yield a box as a Tensor of shape (4,) at a time.

Yield a box as a Tensor of shape (5,) at a time.

Yields: list[ndarray]: the polygons for one instance. Each Tensor is a float64 vector representing a polygon.

根据局部坐标系中的分量生成8方向标签（使用 classify_dir8 逻辑）。 Returns: 方向标签字符串，如果无法分类则返回 None

Gather obj_id_to_mask from all GPUs. Optionally resize the masks to the video resolution.