Flip thetas. Parameters ---------- thetas : numpy.ndarray Joints in shape (num_thetas, 3) theta_pairs : list List of

nn.Module: normalization layer after the first convolution layer

nn.Module: normalization layer after the second convolution layer

Get keypoint predictions from score maps. Note: batch_size: N num_keypoints: K heatmap height: H heatmap width: W

Channel Shuffle operation. This function enables cross-group information flow for multiple groups convolution layers. Args: x (T

Calculate the pose accuracy of PCK for each individual keypoint and the averaged accuracy across all keypoints for coordinates. Note:

In distributed setting, this function only download checkpoint at local rank 0.

In distributed setting, this function only download checkpoint at local rank 0.

Convert [N, L, C] shape tensor to [N, C, H, W] shape tensor. Args: x (Tensor): The input tensor of shape [N, L, C] before conversion.

nn.Module: normalization layer after the third convolution layer

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

Transform vision tokens to feature map. This function only works when the resolution of the feature map is not higher than the initial grid st

GPU version of backward function. Args: grad_output (Tensor): Gradient of output tensor of forward. Return

mesh_out: [bs, multi_n, 10475, 3] gt_mesh: [bs, 1, 10475, 3]

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

Compute the faces, barycentric coordinates for the dynamic landmarks To do so, we first compute the rotation of the neck around the y-axis

Compute the faces, barycentric coordinates for the dynamic landmarks To do so, we first compute the rotation of the neck around the y-axis

Flip 3d xyz joints. Parameters ---------- joints_3d : numpy.ndarray Joints in shape (num_joints, 3) joint_pairs : list

Rotate the point by `rot_rad` degree.

Inference function. Returns: output_regression (np.ndarray): Output regression. Args: x (torch.Tensor[N, K,

Only support locally_connected

Only support locally_connected

Only support locally_connected

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

Flatten [N, C, H, W] shape tensor to [N, L, C] shape tensor. Args: x (Tensor): The input tensor of shape [N, C, H, W] before conversion.

Calculate the pose accuracy of PCK for each individual keypoint and the averaged accuracy across all keypoints from heatmaps. Note: P

Restore the parameters stored with the `store` method. Useful to validate the model with EMA parameters without affecting the original op

Convert quaternion coefficients to rotation matrix. Args: Rotation matrix corresponding to the quaternion -- size = [B, 3, 3] Returns:

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

Save the current parameters for restoring later. Args: parameters: Iterable of `torch.nn.Parameter`; the parameters to be temp

Transform torch tensor to ndarray image. Parameters ---------- img: torch.Tensor A tensor with shape: `(3, H, W)`. Returns

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

Calculates the 3D joint locations from the vertices Parameters ---------- J_regressor : torch.tensor JxV The regressor array tha

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

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

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

Freeze parameters.

Get configurations for deconv layers.

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 each stage.

Make transition layer.

Make transition layer.

Applies a batch of rigid transformations to the joints Parameters ---------- rot_mats : torch.tensor BxNx3x3 Tensor of rotat

Calculates the rotation matrices for a batch of rotation vectors Parameters ---------- rot_vecs: torch.tensor Nx3

Computes a similarity transform (sR, t) that takes a set of 3D points source_points (N x 3) closest to a set of 3D points target_points, where R