Draw `result` over `img`. Args: img (str or Tensor): The image to be displayed. result (Tensor): The semantic segment

Args: img (PIL Image or Tensor): Image to be cropped and resized. Returns: PIL Image or Tensor: Randomly cro

Constructs a swin_base architecture from `Swin Transformer: Hierarchical Vision Transformer using Shifted Windows <https://arxiv.org/pdf/2103

Express 2d coordinates with one number. Example: assume self.no_tokens = 16, then no_sections = 4: 0 0 0 0 0 0 #

r"""Fills the input Tensor with values drawn from a truncated normal distribution. The values are effectively drawn from the normal distributi

Compute per-vertex loss if vertex annotations are available.

Visualize surface normal. Transfer surface normal value from [-1, 1] to [0, 255] Aargs: normal (torch.tensor, [h, w, 3]): surface nor

Overlays gt_kp and pred_kp on img. Draws vert with text. Renderer is an instance of SMPLRenderer.

Since built-in ``any`` works only when the element of iterable is not iterable, implement the function.

perform evaluation and save ckpt.

Freeze stages param and norm stats.

To calculate the affine matrix, three pairs of points are required. This function is used to get the 3rd point, given 2D points a & b. The 3r

To calculate the affine matrix, three pairs of points are required. This function is used to get the 3rd point, given 2D points a & b. The 3r

Sample from fine grained features. Args: prev_output (list[Tensor]): Prediction of previous decode head. points (Tens

Sample from fine grained features. Args: x (list[Tensor]): Feature pyramid from by neck or backbone. points (Tensor):

Initialize the old MediaPipe API.

Initialize rule, key_indicator, comparison_func, and best score. Here is the rule to determine which rule is used for key indicator w

Override default load function. AWS overrides the function _load_from_state_dict to recover weight_gamma and weight_beta if they are

merge dict ``a`` into dict ``b`` (non-inplace). Values in ``a`` will overwrite ``b``. ``b`` is copied first to avoid in-place modific

Open the current base file with the (original) mode and encoding. Return the resulting stream.

Convert a pillow image to numpy array. Args: img (:obj:`PIL.Image.Image`): The image loaded using PIL flag (str): Flags specifyin

Process image using old MediaPipe API.

Save the current checkpoint and delete unwanted checkpoint.

Save the best checkpoint. It will compare the score according to the compare function, write related information (best score, best ch

Rescale a size by a ratio. Args: size (tuple[int]): (w, h). scale (float | tuple(float)): Scaling factor. Returns: t

Judge whether to perform evaluation. Here is the rule to judge whether to perform evaluation: 1. It will not perform evaluation durin

Swap the parameter of model with parameter in ema_buffer.

Allreduce gradients. Args: params (list[torch.Parameters]): List of parameters of a model coalesce (bool, optional): Whether allr

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..

Clip bboxes to fit the image shape. Args: bboxes (ndarray): Shape (..., 4*k) img_shape (tuple[int]): (height, width) of the image

Convert a BGR image to grayscale image. Args: img (ndarray): The input image. keepdim (bool): If False (by default), then return

Encode the camera intrinsic parameters (focal length and principle point) to a 4-channel map.

Build PyTorch DataLoader. In distributed training, each GPU/process has a dataloader. In non-distributed training, there is only one dataload

Build datasets.

Builder for drop out layers.