Tensorflow对象检测api按图片中对象的顺序打印预测

import tensorflow as tf
from object_detection.utils import label_map_util
from object_detection.utils import visualization_utils as viz_utils

PATH_TO_MODEL_DIR = 'path/to/model/directory'
PATH_TO_LABELS = 'path/to/label/map/file.pbtxt'

# 加载模型
detect_fn = tf.saved_model.load(PATH_TO_MODEL_DIR)

# 加载标签映射文件
category_index = label_map_util.create_category_index_from_labelmap(PATH_TO_LABELS, use_display_name=True)

PATH_TO_IMAGE = 'path/to/image.jpg'

# 加载图像
image_np = load_image_into_numpy_array(PATH_TO_IMAGE)

# 将图像转换为张量
input_tensor = tf.convert_to_tensor(image_np)
input_tensor = input_tensor[tf.newaxis, ...]

# 进行对象检测
detections = detect_fn(input_tensor)

# 提取预测结果
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

# 进行可视化
viz_utils.visualize_boxes_and_labels_on_image_array(
    image_np,
    detections['detection_boxes'],
    detections['detection_classes'],
    detections['detection_scores'],
    category_index,
    use_normalized_coordinates=True,
    max_boxes_to_draw=200,
    min_score_thresh=0.3,
    agnostic_mode=False
)

# 获取对象数量
num_objects = detections['num_detections']

# 按照对象的顺序打印预测结果
for i in range(num_objects):
    class_name = category_index[detections['detection_classes'][i]]['name']
    score = detections['detection_scores'][i]
    print("Object {}: {} (score = {:.2f})".format(i+1, class_name, score))