func.py

#以下代码改自
import cv2
import numpy as np

OBJ_THRESH = 0.25
NMS_THRESH = 0.45

# The follew two param is for map test
# OBJ_THRESH = 0.001
# NMS_THRESH = 0.65

IMG_SIZE = (640, 640)  # (width, height), such as (1280, 736)

CLASSES = ("person", "bicycle", "car","motorbike ","aeroplane ","bus ","train","truck ","boat","traffic light",
           "fire hydrant","stop sign ","parking meter","bench","bird","cat","dog ","horse ","sheep","cow","elephant",
           "bear","zebra ","giraffe","backpack","umbrella","handbag","tie","suitcase","frisbee","skis","snowboard","sports ball","kite",
           "baseball bat","baseball glove","skateboard","surfboard","tennis racket","bottle","wine glass","cup","fork","knife ",
           "spoon","bowl","banana","apple","sandwich","orange","broccoli","carrot","hot dog","pizza ","donut","cake","chair","sofa",
           "pottedplant","bed","diningtable","toilet ","tvmonitor","laptop	","mouse	","remote ","keyboard ","cell phone","microwave ",
           "oven ","toaster","sink","refrigerator ","book","clock","vase","scissors ","teddy bear ","hair drier", "toothbrush ")

coco_id_list = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 27, 28, 31, 32, 33, 34,
         35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63,
         64, 65, 67, 70, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 84, 85, 86, 87, 88, 89, 90]


def filter_boxes(boxes, box_confidences, box_class_probs):
    """Filter boxes with object threshold.
    """
    box_confidences = box_confidences.reshape(-1)
    candidate, class_num = box_class_probs.shape

    class_max_score = np.max(box_class_probs, axis=-1)
    classes = np.argmax(box_class_probs, axis=-1)

    _class_pos = np.where(class_max_score* box_confidences >= OBJ_THRESH)
    scores = (class_max_score* box_confidences)[_class_pos]

    boxes = boxes[_class_pos]
    classes = classes[_class_pos]

    return boxes, classes, scores

def nms_boxes(boxes, scores):
    """Suppress non-maximal boxes.
    # Returns
        keep: ndarray, index of effective boxes.
    """
    x = boxes[:, 0]
    y = boxes[:, 1]
    w = boxes[:, 2] - boxes[:, 0]
    h = boxes[:, 3] - boxes[:, 1]

    areas = w * h
    order = scores.argsort()[::-1]

    keep = []
    while order.size > 0:
        i = order[0]
        keep.append(i)

        xx1 = np.maximum(x[i], x[order[1:]])
        yy1 = np.maximum(y[i], y[order[1:]])
        xx2 = np.minimum(x[i] + w[i], x[order[1:]] + w[order[1:]])
        yy2 = np.minimum(y[i] + h[i], y[order[1:]] + h[order[1:]])

        w1 = np.maximum(0.0, xx2 - xx1 + 0.00001)
        h1 = np.maximum(0.0, yy2 - yy1 + 0.00001)
        inter = w1 * h1

        ovr = inter / (areas[i] + areas[order[1:]] - inter)
        inds = np.where(ovr <= NMS_THRESH)[0]
        order = order[inds + 1]
    keep = np.array(keep)
    return keep

def dfl(position):
    # Distribution Focal Loss (DFL)
    import numpy as np
    
    def softmax(x, axis):
        # 减去输入中的最大值以提高数值稳定性
        exp_x = np.exp(x - np.max(x, axis=axis, keepdims=True))
        # 计算 softmax
        return exp_x / np.sum(exp_x, axis=axis, keepdims=True)
    
    x = np.array(position)
    n,c,h,w = x.shape
    p_num = 4
    mc = c//p_num
    y = x.reshape(n,p_num,mc,h,w)
    # y = y.softmax(2)
    y = softmax(y, axis=2)
    acc_metrix = np.array(range(mc),dtype=float).reshape(1,1,mc,1,1)
    # y = (y*acc_metrix).sum(2)
    y = np.sum(y*acc_metrix, axis=2)
    return y


def box_process(position):
    grid_h, grid_w = position.shape[2:4]
    col, row = np.meshgrid(np.arange(0, grid_w), np.arange(0, grid_h))
    col = col.reshape(1, 1, grid_h, grid_w)
    row = row.reshape(1, 1, grid_h, grid_w)
    grid = np.concatenate((col, row), axis=1)
    stride = np.array([IMG_SIZE[1]//grid_h, IMG_SIZE[0]//grid_w]).reshape(1,2,1,1)

    position = dfl(position)
    box_xy  = grid +0.5 -position[:,0:2,:,:]
    box_xy2 = grid +0.5 +position[:,2:4,:,:]
    xyxy = np.concatenate((box_xy*stride, box_xy2*stride), axis=1)

    return xyxy

def post_process(input_data):
    boxes, scores, classes_conf = [], [], []
    defualt_branch=3
    pair_per_branch = len(input_data)//defualt_branch
    # Python 忽略 score_sum 输出
    for i in range(defualt_branch):
        boxes.append(box_process(input_data[pair_per_branch*i]))
        classes_conf.append(input_data[pair_per_branch*i+1])
        scores.append(np.ones_like(input_data[pair_per_branch*i+1][:,:1,:,:], dtype=np.float32))

    def sp_flatten(_in):
        ch = _in.shape[1]
        _in = _in.transpose(0,2,3,1)
        return _in.reshape(-1, ch)

    boxes = [sp_flatten(_v) for _v in boxes]
    classes_conf = [sp_flatten(_v) for _v in classes_conf]
    scores = [sp_flatten(_v) for _v in scores]

    boxes = np.concatenate(boxes)
    classes_conf = np.concatenate(classes_conf)
    scores = np.concatenate(scores)

    # filter according to threshold
    boxes, classes, scores = filter_boxes(boxes, scores, classes_conf)

    # nms
    nboxes, nclasses, nscores = [], [], []
    for c in set(classes):
        inds = np.where(classes == c)
        b = boxes[inds]
        c = classes[inds]
        s = scores[inds]
        keep = nms_boxes(b, s)

        if len(keep) != 0:
            nboxes.append(b[keep])
            nclasses.append(c[keep])
            nscores.append(s[keep])

    if not nclasses and not nscores:
        return None, None, None

    boxes = np.concatenate(nboxes)
    classes = np.concatenate(nclasses)
    scores = np.concatenate(nscores)

    return boxes, classes, scores


def draw(image, boxes, scores, classes):
    orig_h, orig_w, _ = image.shape
    input_h, input_w = IMG_SIZE
    scale_h, scale_w = orig_h/input_h, orig_w/input_w
    for box, score, cl in zip(boxes, scores, classes):
        top, left, right, bottom = [int(_b) for _b in box]
        top, left, right, bottom = int(top*scale_w), int(left*scale_h),\
                                    int(right*scale_w), int(bottom*scale_h)
        # print("%s @ (%d %d %d %d) %.3f" % (CLASSES[cl], top, left, right, bottom, score))
        cv2.rectangle(image, (top, left), (right, bottom), (255, 0, 0), 2)
        cv2.putText(image, '{0} {1:.2f}'.format(CLASSES[cl], score),
                    (top, left - 6), cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 0, 255), 2)

def img_check(path):
    img_type = ['.jpg', '.jpeg', '.png', '.bmp']
    for _type in img_type:
        if path.endswith(_type) or path.endswith(_type.upper()):
            return True
    return False

def myFunc(rknn_lite, IMG_SRC):
    IMG = cv2.cvtColor(IMG_SRC.copy(), cv2.COLOR_BGR2RGB)
    # 等比例缩放
    # IMG = letterbox(IMG)
    # 强制放缩
    IMG = cv2.resize(IMG, IMG_SIZE)
    IMG = np.expand_dims(IMG, 0)
    outputs = rknn_lite.inference(inputs=[IMG], data_format=['nhwc'])

    boxes, classes, scores = post_process(outputs)

    # IMG = cv2.cvtColor(IMG[0], cv2.COLOR_RGB2BGR)
    IMG_P = IMG_SRC.copy()
    if boxes is not None:
        draw(IMG_P, boxes, scores, classes)
    return IMG_P