1

我正在将 TensorFlow 对象检测 API 用于对象检测类。我在 core/post_processing.py 中找到了一个用于非最大抑制的函数，当我尝试使用它时，我会遇到以下错误。

文件“C:/tensorflow/models/research/object_detection/object_detection_image.py”，第 62 行，box_selection = post_processing.multiclass_non_max_suppression(detection_boxes, detection_scores, score_thresh=.8, iou_thresh=.5, max_size_per_class=0)

文件“C:\tensorflow\models\research\object_detection\core\post_processing.py”，第 92 行，在 multiclass_non_max_suppression raise ValueError('scores field must be of rank 2')

ValueError：分数字段必须为 2 级

如果我注释掉非最大抑制行，一切都会正常工作。这是代码：

import os
import cv2
import numpy as np
import tensorflow as tf
import glob

from utils import label_map_util
from utils import visualization_utils as vis_util
from core import post_processing


# Name of the directory containing the object detection module we're using
MODEL_NAME = 'inference_graph'
frames_dir = "./images/test/"

# Grab path to current working directory
CWD_PATH = os.getcwd()

# Path to frozen detection graph .pb file, which contains the model that is used
# for object detection.
PATH_TO_CKPT = os.path.join(CWD_PATH,MODEL_NAME,'frozen_inference_graph.pb')

# Path to label map file
PATH_TO_LABELS = os.path.join(CWD_PATH,'training','labelmap.pbtxt')

# Number of classes the object detector can identify
NUM_CLASSES = 1


label_map = label_map_util.load_labelmap(PATH_TO_LABELS)
categories = label_map_util.convert_label_map_to_categories(label_map, max_num_classes=NUM_CLASSES, use_display_name=True)
category_index = label_map_util.create_category_index(categories)

# Load the Tensorflow model into memory.
detection_graph = tf.Graph()
with detection_graph.as_default():
    od_graph_def = tf.GraphDef()
    with tf.gfile.GFile(PATH_TO_CKPT, 'rb') as fid:
        serialized_graph = fid.read()
        od_graph_def.ParseFromString(serialized_graph)
        tf.import_graph_def(od_graph_def, name='')

    sess = tf.Session(graph=detection_graph)


# Input tensor is the image
image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')

# Output tensors are the detection boxes, scores, and classes
# Each box represents a part of the image where a particular object was detected
detection_boxes = detection_graph.get_tensor_by_name('detection_boxes:0')

# Each score represents level of confidence for each of the objects.
# The score is shown on the result image, together with the class label.
detection_scores = detection_graph.get_tensor_by_name('detection_scores:0')
detection_classes = detection_graph.get_tensor_by_name('detection_classes:0')

# Number of objects detected
num_detections = detection_graph.get_tensor_by_name('num_detections:0')

with detection_graph.as_default():
    box_selection = post_processing.multiclass_non_max_suppression(detection_boxes, detection_scores, score_thresh=.8, iou_thresh=.5, max_size_per_class=0)


#---------------

frames = glob.glob(frames_dir + '*.jpg',)

frame_number = 0

for frame_name in frames:
    # Acquire frame and expand frame dimensions to have shape: [1, None, None, 3]
    # i.e. a single-column array, where each item in the column has the pixel RGB value
    frame = cv2.imread(frame_name)
    frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
    frame_expanded = np.expand_dims(frame, axis=0)

    # Perform the actual detection by running the model with the image as input
    (boxes, scores, classes, num) = sess.run(
        [detection_boxes, detection_scores, detection_classes, num_detections],
        feed_dict={image_tensor: frame_expanded})

    # Box selection using non-max-suppression
    selected_boxes = sess.run(box_selection,
                          feed_dict={image_tensor: frame_expanded, max_output_size: 5})

    # Draw the results of the detection (aka 'visulaize the results')
    vis_util.visualize_boxes_and_labels_on_image_array(
        frame,
        np.squeeze(boxes),
        np.squeeze(classes).astype(np.int32),
        np.squeeze(scores),
        category_index,
        use_normalized_coordinates=True,
        line_thickness=8,
        min_score_thresh=0.60)

    # All the results have been drawn on the frame, so it's time to display it.
    cv2.imshow('Object detector', frame)

    frame_number += 1
    # Press 'q' to quit
    if cv2.waitKey(1) == ord('q'):
        break

# Clean up

cv2.destroyAllWindows()

可悲的是，我无法弄清楚如何解决这个问题。我使用了错误的输入吗？谁能帮我？

4

0 回答 0