move all tensor attributes to device. Args: device (torch.device): target device. Returns: Mesh: self.

Returns a dictionary of info about the object.

load mesh from path. Args: path (str): path to mesh file, supports ply, obj, glb. clean (bool, optional): perform mes

Change the device of the data inplace. Example: >>> self = SamplingResult.random() >>> print(f'self = {self.to(None)}

Update a new data sample.

Build loss.

nn.Module: the normalization layer named "norm1"

nn.Module: the normalization layer named "norm2"

write the mesh to a path. Args: path (str): path to write, supports ply, obj and glb.

Initialize the weights in backbone. Args: pretrained (str, optional): Path to pre-trained weights. Defaults to Non

Convert the model into training mode.

Initialize a pose model from config file. Args: config (str or :obj:`mmcv.Config`): Config file path or the config object.

This encodes bbox(x,y,w,h) into (center, scale) Args: x, y, w, h (float): left, top, width and height padding (float)

Multiple with alpha and add beta with clip.

Criterion of wingloss. Note: - batch_size: N - num_keypoints: K - dimension of keypoints: D (D=2 or D=3)

Args: rng (None | int | numpy.random.RandomState): seed or state. kwargs (keyword arguments): - num_p

Get the frame image. Returns: array: The frame image.

Inference a single image with a list of person bounding boxes. Note: - num_people: P - num_keypoints: K - bbox height: H

sort kpts and remove the repeated ones.

Write results into a json file.

Build a dataset from config dict. Args: cfg (dict): Config dict. It should at least contain the key "type". default_args (dict, o

Get the expansion of a residual block. The block expansion will be obtained by the following order: 1. If ``expansion`` is given, just retur

Load netG (and netD).

Dump model and checkpointables to a file. Args: name (str): name of the file. kwargs (dict): extra arbitrary

Create a superset of inputs needed to run backbone. Args: input_shape (tuple): input batch dimensions. Default: (1, 3, 64, 64

Decode hand keypoint, relative root depth and hand type. Args: img_metas (list(dict)): Information about data augmentation

Inference function. Returns: output (list[np.ndarray]): list of output hand keypoint heatmaps, relative root depth an

Convert rotations given as axis/angle to rotation matrices. Args: axis_angle: Rotations given as a vector in axis angle form,

Method representing the Node's activity. This method override the standard run() method of Thread. Users should not override this met

Calculate bottom-up masked mse loss. Note: - batch_size: N - num_channels: C - heatmaps height: H

Convert rotations given as rotation matrices to quaternions. Args: matrix: Rotation matrices as tensor of shape (..., 3, 3). Re

nn.Module: the normalization layer named "norm3"