python - TF 对象检测 : int() argument must be a string, 类似字节的对象或数字，而不是 'NoneType'

Question

我正在捕捉this关于对象检测 API 的教程，当我运行代码时，即使我不使用网络摄像头(返回相同的问题)，我也会收到此错误:

Traceback (most recent call last):
  File "C:\obj\models\research\object_detection\object_testmien_image.py", line 138, in <module>
    feed_dict={image_tensor: image_np_expanded})
  File "C:\Users\tomsa\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\client\session.py", line 905, in run
    run_metadata_ptr)
  File "C:\Users\tomsa\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\client\session.py", line 1109, in _run
    np_val = np.asarray(subfeed_val, dtype=subfeed_dtype)
  File "C:\Users\tomsa\AppData\Local\Programs\Python\Python35\lib\site-packages\numpy\core\numeric.py", line 492, in asarray
    return array(a, dtype, copy=False, order=order)
TypeError: int() argument must be a string, a bytes-like object or a number, not 'NoneType'

为了打开视频文件，我使用了普通的 cap = cv2.VideoCapture("F:\gopro\file.MOV) 是否正确？为什么它返回无？尽管我收到了其他类似问题的建议，但它没有成功。谢谢您的任何建议!该代码与我链接的教程相同。

编辑:代码如下:

import numpy as np
import os
import six.moves.urllib as urllib
import sys
import tarfile
import tensorflow as tf
import zipfile

from collections import defaultdict
from io import StringIO
import matplotlib
matplotlib.use('Agg')
import matplotlib.pyplot as plt
from PIL import Image

import cv2
cap = cv2.VideoCapture("F:\gopro\file.MOV")

# This is needed since the notebook is stored in the object_detection folder.
sys.path.append("..")


# ## Object detection imports
# Here are the imports from the object detection module.

# In[3]:

from utils import label_map_util

from utils import visualization_utils as vis_util


# # Model preparation 

# ## Variables
# 
# Any model exported using the `export_inference_graph.py` tool can be loaded here simply by changing `PATH_TO_CKPT` to point to a new .pb file.  
# 
# By default we use an "SSD with Mobilenet" model here. See the [detection model zoo](https://github.com/tensorflow/models/blob/master/object_detection/g3doc/detection_model_zoo.md) for a list of other models that can be run out-of-the-box with varying speeds and accuracies.

# In[4]:

# What model to download.
MODEL_NAME = 'ssd_mobilenet_v1_coco_11_06_2017'
MODEL_FILE = MODEL_NAME + '.tar.gz'
DOWNLOAD_BASE = 'http://download.tensorflow.org/models/object_detection/'

# Path to frozen detection graph. This is the actual model that is used for the object detection.
PATH_TO_CKPT = MODEL_NAME + '/frozen_inference_graph.pb'

# List of the strings that is used to add correct label for each box.
PATH_TO_LABELS = os.path.join('data', 'mscoco_label_map.pbtxt')

NUM_CLASSES = 90


# ## Download Model

# In[5]:

opener = urllib.request.URLopener()                         #<-------- comment out by yt
opener.retrieve(DOWNLOAD_BASE + MODEL_FILE, MODEL_FILE)     #<-------- the same
tar_file = tarfile.open(MODEL_FILE)
for file in tar_file.getmembers():
  file_name = os.path.basename(file.name)
  if 'frozen_inference_graph.pb' in file_name:
    tar_file.extract(file, os.getcwd())


# ## Load a (frozen) Tensorflow model into memory.

# In[6]:

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='')


# ## Loading label map
# Label maps map indices to category names, so that when our convolution network predicts `5`, we know that this corresponds to `airplane`.  Here we use internal utility functions, but anything that returns a dictionary mapping integers to appropriate string labels would be fine

# In[7]:

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)


# ## Helper code

# In[8]:

def load_image_into_numpy_array(image):
  print(image.size)
  (im_width, im_height) = image.size
  return np.array(image.getdata()).reshape(
      (im_height, im_width, 3)).astype(np.uint8)


# # Detection

# In[9]:

# For the sake of simplicity we will use only 2 images:
# image1.jpg
# image2.jpg
# If you want to test the code with your images, just add path to the images to the TEST_IMAGE_PATHS.
PATH_TO_TEST_IMAGES_DIR = 'test_images'
TEST_IMAGE_PATHS = [ os.path.join(PATH_TO_TEST_IMAGES_DIR, 'image{}.jpg'.format(i)) for i in range(1, 3) ]

# Size, in inches, of the output images.
IMAGE_SIZE = (12, 8)


# In[10]:

with detection_graph.as_default():
  with tf.Session(graph=detection_graph) as sess:
    while True:
      ret, image_np = cap.read()
      # Expand dimensions since the model expects images to have shape: [1, None, None, 3]
      image_np_expanded = np.expand_dims(image_np, axis=0)
      image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')
      # Each box represents a part of the image where a particular object was detected.
      boxes = detection_graph.get_tensor_by_name('detection_boxes:0')
      # Each score represent how level of confidence for each of the objects.
      # Score is shown on the result image, together with the class label.
      scores = detection_graph.get_tensor_by_name('detection_scores:0')
      classes = detection_graph.get_tensor_by_name('detection_classes:0')
      num_detections = detection_graph.get_tensor_by_name('num_detections:0')
      # Actual detection.
      (boxes, scores, classes, num_detections) = sess.run(
          [boxes, scores, classes, num_detections],
          feed_dict={image_tensor: image_np_expanded})
      # Visualization of the results of a detection.
      vis_util.visualize_boxes_and_labels_on_image_array(
          image_np,
          np.squeeze(boxes),
          np.squeeze(classes).astype(np.int32),
          np.squeeze(scores),
          category_index,
          use_normalized_coordinates=True,
          line_thickness=8)

      cv2.imshow('object detection', cv2.resize(image_np, (800,600)))
      if cv2.waitKey(25) & 0xFF == ord('q'):
        cv2.destroyAllWindows()
        break

Answer 1

在 Python 中 backslashes are escape characters 。为了在文件路径中使用实际的反斜杠，请使用:

cap = cv2.VideoCapture("F:\\gopro\\file.MOV")

或者只使用raw string :

cap = cv2.VideoCapture(r"F:\gopro\file.MOV")

正如文档中所指出的( OpenCV 2 、 OpenCV 3 )，read() 返回两个值:一个成功指示器和检索到的帧。在使用返回的帧之前，您应该始终检查成功指示器(代码中的ret)，在本例中为None。