long() 参数必须是字符串或张量流中的数字错误

Question

我尝试使用 tensorflow 运行对象检测代码

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
from matplotlib import pyplot as plt
from PIL import Image


from utils import label_map_util

from utils import visualization_utils as vis_util


# # Model preparation 
# 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.

# 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

if not os.path.exists(MODEL_NAME + '/frozen_inference_graph.pb'):
    print ('Downloading the model')
    opener = urllib.request.URLopener()
    opener.retrieve(DOWNLOAD_BASE + MODEL_FILE, MODEL_FILE)
    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())
    print ('Download complete')
else:
    print ('Model already exists')

# ## Load a (frozen) 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='')


# ## 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

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)

#intializing the web camera device

import cv2
cap = cv2.VideoCapture(0)

# Running the tensorflow session
with detection_graph.as_default():
  with tf.Session(graph=detection_graph) as sess:
   ret = True
   while (ret):
      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)
#      plt.figure(figsize=IMAGE_SIZE)
#      plt.imshow(image_np)
      cv2.imshow('image',cv2.resize(image_np,(1280,960)))
      if cv2.waitKey(25) & 0xFF == ord('q'):
          cv2.destroyAllWindows()
          cap.release()
          break

但它告诉我这个问题

Traceback (most recent call last):
  File "object_detection_webcam.py", line 97, in <module>
    feed_dict={image_tensor: image_np_expanded})
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 778, in run
    run_metadata_ptr)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 954, in _run
    np_val = np.asarray(subfeed_val, dtype=subfeed_dtype)
  File "/usr/lib/python2.7/dist-packages/numpy/core/numeric.py", line 531, in asarray
    return array(a, dtype, copy=False, order=order)
TypeError: long() argument must be a string or a number, not 'NoneType'

我们在 Raspberry PI 3 上使用了 tenserflow，我们使用了 Raspberry 相机。

我们尝试导入每个库并且它可以工作（所有导入的库都已安装）

我们将tensorflow/models/research/slim 文件夹添加到$PYTHONPATH

这个问题可能是什么原因，我们该如何解决？

Answer 1

问题出在这部分：

ret = True
while (ret):
    ret,image_np = cap.read()

在最后一帧之后，它会将 None 读入 image_np，但循环内部仍在运行并尝试将 None 提供给网络，并且只会在再次到达 while 时停止。

你需要进行类似这样的重组：

 while ( True ):
     ret, image_np = cap.read()
     if not ret:
         break