TensorFlow目标检测模型无法调用摄像头问题求助

使用Python 3.9搭配TensorFlow 2.10.1训练目标检测模型后，尝试用摄像头实时检测时出现以下错误：

所用代码如下：

import tensorflow as tf
from object_detection.utils import label_map_util
from object_detection.utils import visualization_utils as viz_utils
from object_detection.builders import model_builder
from object_detection.utils import config_util
import cv2 
import numpy as np
from matplotlib import pyplot as plt

# Load pipeline config and build a detection model
configs = config_util.get_configs_from_pipeline_file(r"K:\\new\\training_demo\\pre-trained-models\\ssd_mobilenet_v2_fpnlite_320x320_coco17_tpu-8\\pipeline.config")
detection_model = model_builder.build(model_config=configs['model'], is_training=False)

# Restore checkpoint
ckpt = tf.compat.v2.train.Checkpoint(model=detection_model)
ckpt.restore(r"K:\\new\\training_demo\\models\\my_ssd_mobilenet_v2_fpnlite\\ckpt-3").expect_partial()

@tf.function
def detect_fn(image):
    """Detect objects in image."""

    image, shapes = detection_model.preprocess(image)
    prediction_dict = detection_model.predict(image, shapes)
    detections = detection_model.postprocess(prediction_dict, shapes)
    print(shapes)
    return detections, prediction_dict, tf.reshape(shapes, [-1])


category_index = label_map_util.create_category_index_from_labelmap("annotations\\label_map.pbtxt")


cap = cv2.VideoCapture(0)
width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))

while cap.isOpened(): 
    ret, frame = cap.read()
    image_np = np.array(frame)
    
    input_tensor = tf.convert_to_tensor(np.expand_dims(image_np, 0), dtype=tf.float32)
    detections = detect_fn(input_tensor)
    
    num_detections = int(detections.pop('num_detections'))
    detections = {key: value[0, :num_detections].numpy()
                  for key, value in detections.items()}
    detections['num_detections'] = num_detections

    # detection_classes should be ints.
    detections['detection_classes'] = detections['detection_classes'].astype(np.int64)

    label_id_offset = 1
    image_np_with_detections = image_np.copy()

    viz_utils.visualize_boxes_and_labels_on_image_array(
                image_np_with_detections,
                detections['detection_boxes'],
                detections['detection_classes']+label_id_offset,
                detections['detection_scores'],
                category_index,
                use_normalized_coordinates=True,
                max_boxes_to_draw=5,
                min_score_thresh=.8,
                agnostic_mode=False)

    cv2.imshow('object detection',  cv2.resize(image_np_with_detections, (800, 600)))
    
    if cv2.waitKey(10) & 0xFF == ord('q'):
        cap.release()
        cv2.destroyAllWindows()
        break

错误ValueError: too many values to unpack (expected 1)的根源是函数返回值与接收变量不匹配：

• detect_fn定义时返回了3个值：detections, prediction_dict, tf.reshape(shapes, [-1])
• 但调用时仅用detections = detect_fn(input_tensor)接收，导致后续对detections执行字典操作时出错

有两种修复方式：

1. 仅保留需要的返回值（推荐，因为代码里没用到另外两个值）：
   修改detect_fn的返回语句，只返回检测结果：

@tf.function
def detect_fn(image):
    """Detect objects in image."""
    image, shapes = detection_model.preprocess(image)
    prediction_dict = detection_model.predict(image, shapes)
    detections = detection_model.postprocess(prediction_dict, shapes)
    return detections

2. 完整接收所有返回值（如果后续需要用到prediction_dict或shapes）：
   修改调用代码，对应接收三个返回值：

detections, pred_dict, reshaped_shapes = detect_fn(input_tensor)

修改后重新运行即可解决该错误。

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