model_watermark_detect/watermark_verify/inference/yolov5_inference.py

"""
定义yolox推理流程
"""
import cv2
import numpy as np
import onnxruntime as ort


class YOLOV5Inference:
    def __init__(self, model_path, input_size=(640, 640), swap=(2, 0, 1)):
        """
        初始化YOLOX模型推理流程
        :param model_path: 图像分类模型onnx文件路径
        :param input_size: 模型输入大小
        :param swap: 变换方式，pytorch需要进行轴变换(默认参数)，tensorflow无需进行轴变换
        """
        self.model_path = model_path
        self.input_size = input_size
        self.swap = swap

    def input_processing(self, image_path):
        """
        对输入图片进行预处理
        :param image_path: 图片路径
        :return: 图片经过处理完成的ndarray
        """
        img = cv2.imread(image_path)
        if len(img.shape) == 3:
            padded_img = np.ones((self.input_size[0], self.input_size[1], 3), dtype=np.uint8) * 114
        else:
            padded_img = np.ones(self.input_size, dtype=np.uint8) * 114

        r = min(self.input_size[0] / img.shape[0], self.input_size[1] / img.shape[1])
        resized_img = cv2.resize(
            img,
            (int(img.shape[1] * r), int(img.shape[0] * r)),
            interpolation=cv2.INTER_LINEAR,
        ).astype(np.uint8)
        padded_img[: int(img.shape[0] * r), : int(img.shape[1] * r)] = resized_img

        padded_img = padded_img.transpose(self.swap).copy()
        padded_img = np.ascontiguousarray(padded_img, dtype=np.float32)
        height, width, channels = img.shape
        return padded_img, r, height, width, channels

    def predict(self, image_path):
        """
        对单张图片进行推理
        :param image_path: 图片路径
        :return: 推理结果
        """
        img, ratio, height, width, channels = self.input_processing(image_path)

        session = ort.InferenceSession(self.model_path)

        ort_inputs = {session.get_inputs()[0].name: img[None, :, :, :]}
        output = session.run(None, ort_inputs)
        output = self.output_processing(output[0], ratio)
        return output

    def output_processing(self, outputs, ratio):
        """
        YOLOv5 的输出处理流程
        :param outputs: 模型输出 (1, 25200, 85)
        :param ratio: 预处理时的缩放比例
        """
        outputs = outputs[0]
        boxes = outputs[:, :4]
        obj_conf = outputs[:, 4:5]
        class_conf = outputs[:, 5:]
        scores = obj_conf * class_conf

        # xywh to xyxy
        boxes_xyxy = np.zeros_like(boxes)
        boxes_xyxy[:, 0] = boxes[:, 0] - boxes[:, 2] / 2  # x1
        boxes_xyxy[:, 1] = boxes[:, 1] - boxes[:, 3] / 2  # y1
        boxes_xyxy[:, 2] = boxes[:, 0] + boxes[:, 2] / 2  # x2
        boxes_xyxy[:, 3] = boxes[:, 1] + boxes[:, 3] / 2  # y2

        # 还原原图坐标
        boxes_xyxy /= ratio

        # NMS
        dets = multiclass_nms(boxes_xyxy, scores, nms_thr=0.45, score_thr=0.25)
        return dets



def nms(boxes, scores, nms_thr):
    """Single class NMS implemented in Numpy."""
    x1 = boxes[:, 0]
    y1 = boxes[:, 1]
    x2 = boxes[:, 2]
    y2 = boxes[:, 3]

    areas = (x2 - x1 + 1) * (y2 - y1 + 1)
    order = scores.argsort()[::-1]

    keep = []
    while order.size > 0:
        i = order[0]
        keep.append(i)
        xx1 = np.maximum(x1[i], x1[order[1:]])
        yy1 = np.maximum(y1[i], y1[order[1:]])
        xx2 = np.minimum(x2[i], x2[order[1:]])
        yy2 = np.minimum(y2[i], y2[order[1:]])

        w = np.maximum(0.0, xx2 - xx1 + 1)
        h = np.maximum(0.0, yy2 - yy1 + 1)
        inter = w * h
        ovr = inter / (areas[i] + areas[order[1:]] - inter)

        inds = np.where(ovr <= nms_thr)[0]
        order = order[inds + 1]

    return keep


def multiclass_nms_class_agnostic(boxes, scores, nms_thr, score_thr):
    """Multiclass NMS implemented in Numpy. Class-agnostic version."""
    cls_inds = scores.argmax(1)
    cls_scores = scores[np.arange(len(cls_inds)), cls_inds]

    valid_score_mask = cls_scores > score_thr
    if valid_score_mask.sum() == 0:
        return None
    valid_scores = cls_scores[valid_score_mask]
    valid_boxes = boxes[valid_score_mask]
    valid_cls_inds = cls_inds[valid_score_mask]
    keep = nms(valid_boxes, valid_scores, nms_thr)
    if keep:
        dets = np.concatenate(
            [valid_boxes[keep], valid_scores[keep, None], valid_cls_inds[keep, None]], 1
        )
    return dets


def multiclass_nms_class_aware(boxes, scores, nms_thr, score_thr):
    """Multiclass NMS implemented in Numpy. Class-aware version."""
    final_dets = []
    num_classes = scores.shape[1]
    for cls_ind in range(num_classes):
        cls_scores = scores[:, cls_ind]
        valid_score_mask = cls_scores > score_thr
        if valid_score_mask.sum() == 0:
            continue
        else:
            valid_scores = cls_scores[valid_score_mask]
            valid_boxes = boxes[valid_score_mask]
            keep = nms(valid_boxes, valid_scores, nms_thr)
            if len(keep) > 0:
                cls_inds = np.ones((len(keep), 1)) * cls_ind
                dets = np.concatenate(
                    [valid_boxes[keep], valid_scores[keep, None], cls_inds], 1
                )
                final_dets.append(dets)
    if len(final_dets) == 0:
        return None
    return np.concatenate(final_dets, 0)


def multiclass_nms(boxes, scores, nms_thr, score_thr, class_agnostic=True):
    """Multiclass NMS implemented in Numpy"""
    if class_agnostic:
        nms_method = multiclass_nms_class_agnostic
    else:
        nms_method = multiclass_nms_class_aware
    return nms_method(boxes, scores, nms_thr, score_thr)