Used for computing network FLOPs. See ``tools/get_flops.py``. Args: img (torch.Tensor[N,C,imgH,imgW], or list|tuple of t

Used for computing network FLOPs.

A helpfer function to get the keypoint indices of left and right eyes from the model config. Args: model_cfg (Config): pose model con

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

This function computes the inverse perspective projection of a set of points given an estimated distance. Input: points (bs, N, 2): 2

Calculate the Area Under the Curve (3DAUC) computed for a range of 3DPCK thresholds. Paper ref: `Monocular 3D Human Pose Estimation In The Wi

Calculate the mean per-joint position error (MPJPE) and the error after rigid alignment with the ground truth (P-MPJPE). Note: - batc

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

Get multi-label classification accuracy. Note: - batch size: N - label number: L Args: pred (np.ndarray[N, L, 2]): m

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

Group keypoints into poses given heatmap and tag. Note: batch size: N number of keypoints: K heatmap heig

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

Prepare motion sequences for rendering. Args: motion_seqs_dir (str): Directory path of motion sequences. image_folder (str):

Query model path with prioritized local checks: 1. Check local ModelScope cache. 2. Check local Hugging Face cache. 3

Setup logging. Args: output: A file name or a directory to save log files. If None, log files will not be saved. If outp

This encodes bbox(x,y,w,h) into (center, scale) Args: x, y, w, h Returns: tuple: A tuple containing center and scale.

calculate the distance of points p1 and p2.

Get configurations for deconv layers.

Parse the raw outputs (losses) of the network. Args: losses (dict): Raw output of the network, which usually contain

sort kpts and remove the repeated ones.

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

Aggregate multi-scale outputs. Note: batch size: N keypoints num : K heatmap width: W heatmap height: H Args

Check if the weight(and bias) is all zero.

Inference code avoid repeat forward.

Creates the optimizer

Compose the standard form extrinsic matrix from RT. Batched I/O.

A simple wrapper for 3x3 convolution with padding. Args: inplanes (int): Channel number of inputs. outplanes (int): Channel numbe

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

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

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

scale bbox with scale factor

Create configs and perform basic setups.

Visualize the results.

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

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