data_juicer.ops.common.dwpose_func module

class data_juicer.ops.common.dwpose_func.Wholebody(onnx_det, onnx_pose, device)

基类：object

__init__(onnx_det, onnx_pose, device)

data_juicer.ops.common.dwpose_func.nms(boxes, scores, nms_thr)

Single class NMS implemented in Numpy.

data_juicer.ops.common.dwpose_func.multiclass_nms(boxes, scores, nms_thr, score_thr)

Multiclass NMS implemented in Numpy. Class-aware version.

data_juicer.ops.common.dwpose_func.demo_postprocess(outputs, img_size, p6=False)

data_juicer.ops.common.dwpose_func.preprocess_det(img, input_size, swap=(2, 0, 1))

data_juicer.ops.common.dwpose_func.inference_detector(session, oriImg)

data_juicer.ops.common.dwpose_func.preprocess_pose(img: ndarray, out_bbox, input_size: Tuple[int, int] = (192, 256)) → Tuple[ndarray, ndarray, ndarray]

Do preprocessing for RTMPose model inference.

参数:

• img (np.ndarray) -- Input image in shape.

• input_size (tuple) -- Input image size in shape (w, h).

返回:

• resized_img (np.ndarray): Preprocessed image.

• center (np.ndarray): Center of image.

• scale (np.ndarray): Scale of image.

返回类型:

tuple

data_juicer.ops.common.dwpose_func.inference(sess: InferenceSession, img: ndarray) → ndarray

Inference RTMPose model.

参数:

• sess (onnxruntime.InferenceSession) -- ONNXRuntime session.

• img (np.ndarray) -- Input image in shape.

返回:

Output of RTMPose model.

返回类型:

outputs (np.ndarray)

data_juicer.ops.common.dwpose_func.postprocess(outputs: List[ndarray], model_input_size: Tuple[int, int], center: Tuple[int, int], scale: Tuple[int, int], simcc_split_ratio: float = 2.0) → Tuple[ndarray, ndarray]

Postprocess for RTMPose model output.

参数:

• outputs (np.ndarray) -- Output of RTMPose model.

• model_input_size (tuple) -- RTMPose model Input image size.

• center (tuple) -- Center of bbox in shape (x, y).

• scale (tuple) -- Scale of bbox in shape (w, h).

• simcc_split_ratio (float) -- Split ratio of simcc.

返回:

• keypoints (np.ndarray): Rescaled keypoints.

• scores (np.ndarray): Model predict scores.

返回类型:

tuple

data_juicer.ops.common.dwpose_func.bbox_xyxy2cs(bbox: ndarray, padding: float = 1.0) → Tuple[ndarray, ndarray]

Transform the bbox format from (x,y,w,h) into (center, scale)

参数:

• bbox (ndarray) -- Bounding box(es) in shape (4,) or (n, 4), formatted as (left, top, right, bottom)

• padding (float) -- BBox padding factor that will be multilied to scale. Default: 1.0

返回:

A tuple containing center and scale. - np.ndarray[float32]: Center (x, y) of the bbox in shape (2,) or

(n, 2)

• np.ndarray[float32]: Scale (w, h) of the bbox in shape (2,) or

  (n, 2)

返回类型:

tuple

data_juicer.ops.common.dwpose_func.get_warp_matrix(center: ndarray, scale: ndarray, rot: float, output_size: Tuple[int, int], shift: Tuple[float, float] = (0.0, 0.0), inv: bool = False) → ndarray

Calculate the affine transformation matrix that can warp the bbox area in the input image to the output size.

参数:

• center (np.ndarray[2, ]) -- Center of the bounding box (x, y).

• scale (np.ndarray[2, ]) -- Scale of the bounding box wrt [width, height].

• rot (float) -- Rotation angle (degree).

• output_size (np.ndarray[2, ] | list(2,)) -- Size of the destination heatmaps.

• shift (0-100%) -- Shift translation ratio wrt the width/height. Default (0., 0.).

• inv (bool) -- Option to inverse the affine transform direction. (inv=False: src->dst or inv=True: dst->src)

返回:

A 2x3 transformation matrix

返回类型:

np.ndarray

data_juicer.ops.common.dwpose_func.top_down_affine(input_size: dict, bbox_scale: dict, bbox_center: dict, img: ndarray) → Tuple[ndarray, ndarray]

Get the bbox image as the model input by affine transform.

参数:

• input_size (dict) -- The input size of the model.

• bbox_scale (dict) -- The bbox scale of the img.

• bbox_center (dict) -- The bbox center of the img.

• img (np.ndarray) -- The original image.

返回:

A tuple containing center and scale. - np.ndarray[float32]: img after affine transform. - np.ndarray[float32]: bbox scale after affine transform.

返回类型:

tuple

data_juicer.ops.common.dwpose_func.get_simcc_maximum(simcc_x: ndarray, simcc_y: ndarray) → Tuple[ndarray, ndarray]

Get maximum response location and value from simcc representations.

备注

instance number: N num_keypoints: K heatmap height: H heatmap width: W

参数:

• simcc_x (np.ndarray) -- x-axis SimCC in shape (K, Wx) or (N, K, Wx)

• simcc_y (np.ndarray) -- y-axis SimCC in shape (K, Wy) or (N, K, Wy)

返回:

• locs (np.ndarray): locations of maximum heatmap responses in shape

  (K, 2) or (N, K, 2)

• vals (np.ndarray): values of maximum heatmap responses in shape

  (K,) or (N, K)

返回类型:

tuple

data_juicer.ops.common.dwpose_func.decode(simcc_x: ndarray, simcc_y: ndarray, simcc_split_ratio) → Tuple[ndarray, ndarray]

Modulate simcc distribution with Gaussian.

参数:

• simcc_x (np.ndarray[K, Wx]) -- model predicted simcc in x.

• simcc_y (np.ndarray[K, Wy]) -- model predicted simcc in y.

• simcc_split_ratio (int) -- The split ratio of simcc.

返回:

A tuple containing center and scale. - np.ndarray[float32]: keypoints in shape (K, 2) or (n, K, 2) - np.ndarray[float32]: scores in shape (K,) or (n, K)

返回类型:

tuple

data_juicer.ops.common.dwpose_func.inference_pose(session, out_bbox, oriImg)

data_juicer.ops.common.dwpose_func.smart_resize(x, s)

data_juicer.ops.common.dwpose_func.smart_resize_k(x, fx, fy)

data_juicer.ops.common.dwpose_func.padRightDownCorner(img, stride, padValue)

data_juicer.ops.common.dwpose_func.transfer(model, model_weights)

data_juicer.ops.common.dwpose_func.draw_bodypose(canvas, candidate, subset)

data_juicer.ops.common.dwpose_func.draw_handpose(canvas, all_hand_peaks)

data_juicer.ops.common.dwpose_func.draw_facepose(canvas, all_lmks)

data_juicer.ops.common.dwpose_func.handDetect(candidate, subset, oriImg)

data_juicer.ops.common.dwpose_func.faceDetect(candidate, subset, oriImg)

data_juicer.ops.common.dwpose_func.npmax(array)

data_juicer.ops.common.dwpose_func.draw_pose(pose, H, W)

class data_juicer.ops.common.dwpose_func.DWposeDetector(onnx_det, onnx_pose, device)

基类：object

__init__(onnx_det, onnx_pose, device)