Write image to file. Args: img (ndarray): Image array to be written. file_path (str): Image file path. params (None or li

Inference a single image with a list of hand bounding boxes. Note: - num_bboxes: N - num_keypoints: K Args: model (n

Weight initialization for model.

Initialize model weights.

Returns: True if distributed training is enabled

Load state_dict to a module. This method is modified from :meth:`torch.nn.Module.load_state_dict`. Default value for ``strict`` is set to ``F

Helper function for running an optimization process Args: - optimizer: The PyTorch optimizer object - closure: The fu

Non-Maximum Suppression for heatmaps. Args: heatmap(torch.Tensor): Heatmaps before nms. Returns: torch.Tenso

Parse the package dependencies listed in a requirements file but strips specific versioning information. Args: fname (str): path to r

This function computes the perspective projection of a set of points assuming the extrinsinc params have already been applied Args: -

Converts 6D rotation representation by Zhou et al. [1] to rotation matrix using Gram--Schmidt orthogonalisation per Section B of [1]. Arg

Visualize the results.

Apply a specific SMPL model with given model parameters. Note: B: batch size V: number of vertices K: num

training entry

x: (N, T, patch_size**2 * C) imgs: (N, H, W, C)

Calculates landmarks by barycentric interpolation Parameters ---------- vertices: torch.tensor BxVx3, dtype = torch.float32 The t

Calculates landmarks by barycentric interpolation Parameters ---------- vertices: torch.tensor BxVx3, dtype = torch.float32

Visualize the 3D pose estimation results. Args: model (nn.Module): The loaded model. result (list[dict])

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

Project layer to get voxel feature. Adapted from https://github.com/microsoft/voxelpose- pytorch/blob/main/lib/models/project_layer.py

Calculate the normalized distances between preds and target. Note: batch_size: N num_keypoints: K dimension of keypoints:

Denormalize joint coordinates with given statistics mean and std. Args: x (np.ndarray[N, K, 3]): Normalized joint coordinates.

Freeze parameters.

Get the size for multi-scale training. Args: image: Input image. input_size (np.ndarray[2]): Size (w, h) of the image input.

Load checkpoint from somewhere (modelzoo, file, url). Args: filename (str): Accept local filepath, URL, ``torchvision://xxx``,

Make zero inputs for AE loss. Args: t (torch.Tensor): input requires_grad (bool): Option to use requires_grad. device: to

Make stage.

Make transition layer.

Parse imgname to get information of subject, action and camera. A typical h36m image filename is like: S1_Directions_1.54138969_00000

Transform the joints from their pixel coordinates to their camera coordinates. Note: N: number of joints Args:

Cauculate mean per joint position error (MPJPE) or its variants like P-MPJPE or N-MPJPE. Args: keypoint_results (list): K

Restore global position of the root-centered joints. Args: x (np.ndarray[N, K, 3]): root-centered joint coordinates r

Transform the bbox format from xywh to x1y1x2y2. Args: bbox_xywh (ndarray): Bounding boxes (with scores), shaped (n, 4) or (n

Add tensorboard summary.

Apply bug-eye effect. Args: img (np.ndarray): Image data. pose_results (list[dict]): The pose estimation results containing:

Apply sunglasses effect. Args: img (np.ndarray): Image data. pose_results (list[dict]): The pose estimation results containing:

Convert axis-angle representation to rotation matrix. Args: theta: size = [B, 3] Returns: Rotation matrix corresponding to the

Calculates the per vertex displacement due to the blend shapes Parameters ---------- betas : torch.tensor Bx(num_betas) Blend s