Clip bounding box with format (xmin, ymin, xmax, ymax) to specified boundary. All bounding boxes will be clipped to the new region `(0, 0, width,

Convert bounding boxes from format (x, y, w, h) to (xmin, ymin, xmax, ymax) Parameters ---------- xywh : list, tuple or numpy.ndarray

Return vector c that perpendicular to (a - b).

Return vector c that perpendicular to (a - b).

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

Initializes model with pretrained weights. Layers that don't match with pretrained layers in name or size are kept unchanged.

creates and loads a YOLOX model Args: name (str): name of model. for example, "yolox-s", "yolox-tiny". pretrained (bool): load pr

Prepare image for inputting to the neural network. Returns a Variable

Convert box coordinates to center and scale. adapted from https://github.com/Microsoft/human-pose-estimation.pytorch

Gathers elements from `input_tensor` based on match results. For columns that are matched to a row, gathered_tensor[col] is set to input_tens

Transform ndarray image to torch tensor. Parameters ---------- img: numpy.ndarray An ndarray with shape: `(H, W, 3)`. Return

Initializes model with pretrained weights. Layers that don't match with pretrained layers in name or size are kept unchanged.

starts with conv layer then has `num_blocks` `ResLayer`

Returns number of boxes held in collection. Returns: a tensor representing the number of boxes held in the collection.

Prepare image for inputting to the neural network. Returns a Variable

Update a matched track :type new_track: STrack :type frame_id: int :type update_feature: bool :return:

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

Set the indicated fields of x to val. Args: x: tensor. indicator: boolean with same shape as x. val: scal

Evaluate mAP result for coco dataset. Parameters ---------- res_file: str Path to result json file. ann_type: str ann

Flip pose heatmap according to joint pairs. Parameters ---------- heatmap : numpy.ndarray Heatmap of joints. joint_pairs : lis

Flip 3d joints. Parameters ---------- joints_3d : numpy.ndarray Joints in shape (num_joints, 3, 2) width : int Image w

resize image with unchanged aspect ratio using padding

Convert bounding box to format `(center x, center y, aspect ratio, height)`, where the aspect ratio is `width / height`.

Convert bounding box to format `(center x, center y, aspect ratio, height)`, where the aspect ratio is `width / height`.

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

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

Update a matched track :type new_track: STrack :type frame_id: int :type update_feature: bool :return:

all_result: result dict of predictions outputpath: output directory