目标检测底层实现

VOC,YOLO,COCO互转

def yolo2voc(bboxes, image_height=720, image_width=1280):
    """
    yolo => [xmid, ymid, w, h] (normalized)
    voc  => [x1, y1, x2, y1]
    
    """ 
    bboxes = bboxes.copy().astype(float) # otherwise all value will be 0 as voc_pascal dtype is np.int
    
    bboxes[..., [0, 2]] = bboxes[..., [0, 2]]* image_width
    bboxes[..., [1, 3]] = bboxes[..., [1, 3]]* image_height
    
    bboxes[..., [0, 1]] = bboxes[..., [0, 1]] - bboxes[..., [2, 3]]/2
    bboxes[..., [2, 3]] = bboxes[..., [0, 1]] + bboxes[..., [2, 3]]
    
    return bboxes

def coco2yolo(bboxes, image_height=720, image_width=1280):
    """
    coco => [xmin, ymin, w, h]
    yolo => [xmid, ymid, w, h] (normalized)
    """
    
    bboxes = bboxes.copy().astype(float) # otherwise all value will be 0 as voc_pascal dtype is np.int
    
    # normolizinig
    bboxes[..., [0, 2]]= bboxes[..., [0, 2]]/ image_width
    bboxes[..., [1, 3]]= bboxes[..., [1, 3]]/ image_height
    
    # converstion (xmin, ymin) => (xmid, ymid)
    bboxes[..., [0, 1]] = bboxes[..., [0, 1]] + bboxes[..., [2, 3]]/2
    
    return bboxes

def yolo2coco(bboxes, image_height=720, image_width=1280):
    """
    yolo => [xmid, ymid, w, h] (normalized)
    coco => [xmin, ymin, w, h]
    
    """ 
    bboxes = bboxes.copy().astype(float) # otherwise all value will be 0 as voc_pascal dtype is np.int
    
    # denormalizing
    bboxes[..., [0, 2]]= bboxes[..., [0, 2]]* image_width
    bboxes[..., [1, 3]]= bboxes[..., [1, 3]]* image_height
    
    # converstion (xmid, ymid) => (xmin, ymin) 
    bboxes[..., [0, 1]] = bboxes[..., [0, 1]] - bboxes[..., [2, 3]]/2
    
    return bboxes

def voc2coco(bboxes, image_height=720, image_width=1280):
    bboxes  = voc2yolo(bboxes, image_height, image_width)
    bboxes  = yolo2coco(bboxes, image_height, image_width)
    return bboxes

def coco2voc(bboxes, image_height=720, image_width=1280):
    bboxes  = coco2yolo(bboxes, image_height, image_width)
    bboxes  = yolo2voc(bboxes, image_height, image_width)
    return bboxes

加载图片，且BGR转RGB

def load_image(image_path):
    return cv2.cvtColor(cv2.imread(image_path), cv2.COLOR_BGR2RGB)