YOLOv8集成Google TTS时遭遇AttributeError问题求助

我做的项目是用YOLOv8检测目标标签和坐标，把标签转成字符串后用gTTS生成语音，但获取预测标签时一直报AttributeError，刚接触这个框架，求帮忙。

原代码 #

import cv2
from gtts import gTTS
import os
from ultralytics import YOLO

def convert_labels_to_text(labels):
    text = ", ".join(labels)
    return text

class YOLOWithLabels(YOLO):
    def __call__(self, frame):
        results = super().__call__(frame)
        labels = results.pred[0].get_field("labels").tolist()
        annotated_frame = results.render()
        return annotated_frame, labels

cap = cv2.VideoCapture(0)
model = YOLOWithLabels('yolov8n.pt')

while cap.isOpened():
    success, frame = cap.read()

    if success:
        annotated_frame, labels = model(frame)

        message = convert_labels_to_text(labels)

        tts_engine = gTTS(text=message)  # Initialize gTTS with the message

        tts_engine.save("output.mp3")
        os.system("output.mp3")

        cv2.putText(annotated_frame, message, (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
        cv2.imshow("YOLOv8 Inference", annotated_frame)

        if cv2.waitKey(1) & 0xFF == ord("q"):
            break

    else:
        break

cap.release()
cv2.destroyAllWindows()

错误信息 #

File "C:\Users\alien\Desktop\YOLOv8 project files\gtts service\testservice.py", line 13, in __call__
    labels = results.pred[0].get_field("labels").tolist()
             ^^^^^^^^^^^^
AttributeError: 'list' object has no attribute 'pred'

打印results的输出 #

orig_shape: (480, 640)
path: 'image0.jpg'
probs: None
save_dir: None
speed: {'preprocess': 3.1604766845703125, 'inference': 307.905912399292, 'postprocess': 2.8924942016601562}]
0: 480x640 1 person, 272.4ms
Speed: 3.0ms preprocess, 272.4ms inference, 4.0ms postprocess per image at shape (1, 3, 640, 640)
[ultralytics.yolo.engine.results.Results object with attributes:
    boxes: ultralytics.yolo.engine.results.Boxes object
    keypoints: None
    keys: ['boxes']
    masks: None
    names: {0: 'person', 1: 'bicycle', 2: 'car', 3: 'motorcycle', 4: 'airplane', 5: 'bus', 6: 'train', 7: 'truck', 8: 'boat', 9: 'traffic light', 10: 'fire hydrant', 11: 'stop sign', 12: 'parking meter', 13: 'bench', 14: 'bird', 15: 'cat', 16: 'dog', 17: 'horse', 18: 'sheep', 19: 'cow', 20: 'elephant', 21: 'bear', 22: 'zebra', 23: 'giraffe', 24: 'backpack', 25: 'umbrella', 26: 'handbag', 27: 'tie', 28: 'suitcase', 29: 'frisbee', 30: 'skis', 31: 'snowboard', 32: 'sports ball', 33: 'kite', 34: 'baseball bat', 35: 'baseball glove', 36: 'skateboard', 37: 'surfboard', 38: 'tennis racket', 39: 'bottle', 40: 'wine glass', 41: 'cup', 42: 'fork', 43: 'knife', 44: 'spoon', 45: 'bowl', 46: 'banana', 47: 'apple', 48: 'sandwich', 49: 'orange', 50: 'broccoli', 51: 'carrot', 52: 'hot dog', 53: 'pizza', 54: 'donut', 55: 'cake', 56: 'chair', 57: 'couch', 58: 'potted plant', 59: 'bed', 60: 'dining table', 61: 'toilet', 62: 'tv', 63: 'laptop', 64: 'mouse', 65: 'remote', 66: 'keyboard', 67: 'cell phone', 68: 'microwave', 69: 'oven', 70: 'toaster', 71: 'sink', 72: 'refrigerator', 73: 'book', 74: 'clock', 75: 'vase', 76: 'scissors', 77: 'teddy bear', 78: 'hair drier', 79: 'toothbrush'}
    orig_img: array([[[168, 167, 166],
            [165, 165, 165],
            [165, 166, 167],
            ...,
            [183, 186, 178],
            [183, 186, 178],
            [184, 187, 179]],

           [[168, 167, 165],
            [166, 165, 165],
            [166, 167, 166],
            ...,
            [184, 187, 179],
            [183, 186, 178],
            [184, 187, 179]],

           [[168, 167, 164],
            [167, 167, 164],
            [167, 167, 165],
            ...,
            [184, 187, 178],
            [184, 187, 179],
            [183, 186, 178]],

           ...,

           [[196, 192, 185],
            [196, 192, 185],
            [196, 192, 185],
            ...,
            [ 25,  29,  38],
            [ 22,  25,  35],
            [ 20,  24,  34]],

           [[199, 195, 187],
            [197, 193, 186],
            [197, 193, 186],
            ...,
            [ 23,  26,  35],
            [ 22,  25,  35],
            [ 22,  25,  35]],

           [[199, 195, 187],
            [199, 195, 187],
            [199, 195, 187],
            ...,
            [ 20,  24,  33],
            [ 19,  23,  33],
            [ 19,  23,  33]]], dtype=uint8)

解决方案 #

问题出在YOLOv8的API使用上，你用的是旧版本YOLO的写法，YOLOv8的__call__方法返回的是Results对象的列表，而不是单个Results对象，而且获取标签的方式也变了。

修正后的代码如下：

import cv2
from gtts import gTTS
import os
from ultralytics import YOLO

def convert_labels_to_text(labels):
    text = ", ".join(labels)
    return text

class YOLOWithLabels(YOLO):
    def __call__(self, frame):
        results = super().__call__(frame)
        # 取列表中的第一个Results对象
        result = results[0]
        # 获取类别ID，再通过names映射成标签名称
        class_ids = result.boxes.cls.tolist()
        labels = [result.names[int(id)] for id in class_ids]
        # 渲染带标注的帧
        annotated_frame = result.plot()
        return annotated_frame, labels

cap = cv2.VideoCapture(0)
model = YOLOWithLabels('yolov8n.pt')

while cap.isOpened():
    success, frame = cap.read()

    if success:
        annotated_frame, labels = model(frame)

        message = convert_labels_to_text(labels)

        # 只有检测到目标时才生成语音，避免空文本报错
        if message:
            tts_engine = gTTS(text=message)
            tts_engine.save("output.mp3")
            os.system("output.mp3")

        cv2.putText(annotated_frame, message, (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
        cv2.imshow("YOLOv8 Inference", annotated_frame)

        if cv2.waitKey(1) & 0xFF == ord("q"):
            break

    else:
        break

cap.release()
cv2.destroyAllWindows()

关键修改点 #

• 处理results返回值：super().__call__(frame)返回的是Results对象列表，需要取第一个元素result = results[0]
• 正确获取标签：YOLOv8中，检测框的类别ID存在result.boxes.cls里，通过result.names字典可以把ID转换成对应的标签名称
• 渲染标注帧：用result.plot()替代旧的results.render()，这是YOLOv8的标准渲染方法
• 增加空判断：当没有检测到目标时，message为空，此时不执行gTTS操作，避免报错

内容的提问来源于stack exchange，提问作者asfriendlyascarbon