Args: inputs: A float tensor of arbitrary shape. The predictions for each example. targets: A float tensor with t

Args: inputs: A float tensor of arbitrary shape. The predictions for each example. targets: A float tensor wi

Concatenates a list of BitMasks into a single BitMasks Arguments: bitmasks_list (list[BitMasks]) Returns:

match the detection results with the groundtruth in the whole database

Contrast distortion.

3x3 convolution with padding

Compute the DICE loss, similar to generalized IOU for masks Args: inputs: A float tensor of arbitrary shape. The pred

:meth: dump the object into a dict :return: a dict with "box" and "score" keys

Flip human joints horizontally. Note: num_keypoints: K Args: joints_3d (np.ndarray([K, 3])): Coordinates of keypoints.

embed_dim: output dimension for each position pos: a list of positions to be encoded: size (M,) out: (M, D)

embed_dim: output dimension for each position pos: a list of positions to be encoded: size (M,) out: (M, D)

embed_dim: output dimension for each position pos: a list of positions to be encoded: size (M,) out: (M, D)

embed_dim: output dimension for each position pos: a list of positions to be encoded: size (M,) out: (M, D)

Get the affine transform matrix, given the center/scale/rot/output_size. Args: center (np.ndarray[2, ]): Center of the bounding box (x, y

Args: image_size (tuple): height, width Returns: crop_size (tuple): height, width in absolute pixels

Args: image_size (tuple): height, width Returns: crop_size (tuple): height, width in absolute pixels

Calculate the transformation matrix under the constraint of unbiased. Paper ref: Huang et al. The Devil is in the Details: Delving into Unbiased

A context where the model is temporarily changed to eval mode, and restored to previous mode afterwards. Args: model: a torch Mo

Inference function. Returns: output_heatmap (np.ndarray): Output heatmaps. Args: x (torch.Tensor[NxKxHxW]):

Equivalent to nn.functional.interpolate, but with support for empty batch sizes. This will eventually be supported natively by PyTorch, and t

gt: ground truth with size (N, H, W) num_classes: the number of classes of different label

Args: model (Module): Module to load checkpoint. filename (str): Accept local filepath, URL, ``torchvision://xxx``, `

Args: model (Module): Module to load checkpoint. filename (str): Accept local filepath, URL, ``torchvision://xxx``, `

Copy master parameters to model parameters. Args: model_params: List of model parameters created by :func:`prep_param_lists`.

Greedily select boxes with high confidence and overlap <= thr. Args: dets: [[x1, y1, x2, y2, score]]. thr: Retain overlap < thr.

Calculate oks ious. Args: g: Ground truth keypoints. d: Detected keypoints. a_g: Area of the ground truth object.

Given two lists of boxes of size N and M, compute the intersection area between __all__ N x M pairs of boxes. The box order must be (xmin

:meth: read the object from a dict :param dict odf: a dict with "box", "score", "occ" and "extra.ignore" keys, e.g., odf = {"box": [5

DARK post-pocessing. Implemented by udp. Paper ref: Huang et al. The Devil is in the Details: Delving into Unbiased Data Processing for Human

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

Get final keypoint predictions from heatmaps and apply scaling and translation to map them back to the image. Note: num_keypoints: K

See pack_kwargs.

See split_non_tensors.

Apply affine transformation defined by the transform matrix on the joints. Args: joints (np.ndarray[..., 2]): Origin coordinate of jo

Designed to work with network_to_half. BatchNorm layers need parameters in single precision. Find all layers and convert them back to flo

Args: index (int): Index Returns: tuple: Tuple (image, target). target is the object returned by ``coco.load

Args: index (int): Index Returns: tuple: Tuple (image, target). target is the object returned by ``coco.load

Args: image (ndarray): (H,W) or (H,W,C) ndarray of type uint8 in range [0, 255], or floating point in range [0, 1

Constructor of Microsoft COCO helper class for reading and visualizing annotations. :param annotation_file (str): location of annotat

Constructor of Microsoft COCO helper class for reading and visualizing annotations. :param annotation_file (str): location of annotat