Compute the average precision, given the recall and precision curves # Arguments recall: The recall curve (list) precision: Th

gt dir: (wider_face_val.mat, wider_easy_val.mat, wider_medium_val.mat, wider_hard_val.mat)

single image evaluation pred: Nx5 gt: Nx4 ignore:

图像预处理

预测可视化 vis_thres: 可视化阈值

Creates kmeans-evolved anchors from training dataset Arguments: path: path to dataset *.yaml, or a loaded dataset n:

norm score pred {key: [[x1,y1,x2,y2,s]]}

Return intersection-over-union (Jaccard index) of boxes. Both sets of boxes are expected to be in (x1, y1, x2, y2) format. Ar

CIntFromPy */

CIntToPy */

ArgTypeTest */

__GNUC__ */

TensorRT推理 :param img_np_nchw: 输入图像