Проблема с использованием core.post_processing.multiclass_non_max_suppression в API обнаружения объектов Tensorflow

Question

Я использую Tensorflow Object Detection API для класса обнаружения объектов. В core / post_processing.py я нашел функцию для подавления не max, которая, когда я пытаюсь ее использовать, сталкивается со следующей ошибкой.

Файл "C: / tenorflow / models / исследование / object_detection / object_detection_image.py ", строка 62, в поле box_selection = post_processing.multiclass_non_max_suppression (обнаружение_боксов, обнаружение_отчетов, Score_thresh = .8, iou_thresh = .5, max_size_per_class = 0)

файл" тензор потока \ models \ research \ object_detection \ core \ post_processing.py ", строка 92, в мультиклассе_non_max_suppression повышение ValueError ('поле оценки должно иметь ранг 2') *1006*

ValueError: поле оценки должно иметь ранг 2

Если я закомментирую строки не максимального подавления, все будет работать нормально. Вот код:

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()

К сожалению, я не могу понять, как решить эту проблему. Я использую неправильный ввод? Кто-нибудь может мне помочь?