使用自己的模型运行 TF 对象检测 API 时出现 FailedPreconditionError [英] FailedPreconditionError when running TF Object Detection API with own model

问题描述

我正在尝试使用我自己的数据集运行我在 TensorFlow Object Detection API 中所做的模型，但是在运行脚本时出现这样的错误:

I`m trying to run the model I did in TensorFlow Object Detection API with my own dataset, but when running script I get such error:

python object_detection/detect_test.py

Traceback (most recent call last):
  File "object_detection/detect_test.py", line 81, in <module>
    feed_dict={image_tensor: image_np_expanded})
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 789, in run
    run_metadata_ptr)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 997, in _run
    feed_dict_string, options, run_metadata)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 1132, in _do_run
    target_list, options, run_metadata)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 1152, in _do_call
    raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.FailedPreconditionError: Attempting to use uninitialized value SecondStageBoxPredictor/ClassPredictor/biases
         [[Node: SecondStageBoxPredictor/ClassPredictor/biases/read = Identity[T=DT_FLOAT, _class=["loc:@SecondStageBoxPredictor/ClassPredictor/biases"], _device="/job:localhost/replica:0/task:0/cpu:0"](SecondStageBoxPredictor/ClassPredictor/biases)]]

Caused by op u'SecondStageBoxPredictor/ClassPredictor/biases/read', defined at:
  File "object_detection/detect_test.py", line 40, in <module>
    tf.import_graph_def(od_graph_def, name='')
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/importer.py", line 311, in import_graph_def
    op_def=op_def)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 2506, in create_op
    original_op=self._default_original_op, op_def=op_def)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 1269, in __init__
    self._traceback = _extract_stack()

FailedPreconditionError (see above for traceback): Attempting to use uninitialized value SecondStageBoxPredictor/ClassPredictor/biases
         [[Node: SecondStageBoxPredictor/ClassPredictor/biases/read = Identity[T=DT_FLOAT, _class=["loc:@SecondStageBoxPredictor/ClassPredictor/biases"], _device="/job:localhost/replica:0/task:0/cpu:0"](SecondStageBoxPredictor/ClassPredictor/biases)]]

这有点奇怪，因为我正在关注 他们的教程 用于模型使用，错误可能是说某些变量未初始化.

This is kind of weird because I was following their tutorial for model usage, and the error is probably saying that some Variables are not initialize.

这是我的代码:

detect_test.py

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

# Path to frozen detection graph. This is the actual model that is used for the object detection.
PATH_TO_CKPT = '/home/jun/PycharmProjects/tf_workspace/models/output_inference_graph_151.pb'

# List of the strings that is used to add correct label for each box.
PATH_TO_LABELS = '/home/jun/PycharmProjects/tf_workspace/models/object_detection/data/pascal_label_map_new.pbtxt'

NUM_CLASSES = 3

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='')

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)

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

# 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 = 'object_detection/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)

with detection_graph.as_default():
  with tf.Session(graph=detection_graph) as sess:
    for image_path in TEST_IMAGE_PATHS:
      image = Image.open(image_path)
      # the array based representation of the image will be used later in order to prepare the
      # result image with boxes and labels on it.
      image_np = load_image_into_numpy_array(image)
      # 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)

在这种情况下，我将非常感谢您的帮助！提前致谢！

I will be so greatful for any help in this situation! Thanks in advance!

推荐答案

最后，我在评估后更改了 matplotlib 显示图像的行，以简单地保存结果图像.他们一直在示例中使用 jupyter notebook，因此可能会有一些功能.

Finally I have changed row where matplotlib is showing image after evaluating to simply save resulting image. They have been using jupyter notebook in their example so there could be some features because of this.

最终代码:

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 object_detection.utils import label_map_util
from object_detection.utils import visualization_utils as vis_util

NUM_CLASSES = 3

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='')

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)

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

# 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 = 'object_detection/test_images/'
TEST_IMAGE_PATHS = [ os.path.join(PATH_TO_TEST_IMAGES_DIR, 'image{}.jpg'.format(i)) for i in range(1, 6) ]

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

with detection_graph.as_default():
  with tf.Session(graph=detection_graph) as sess:
    sess.run(tf.global_variables_initializer())
    img = 1
    for image_path in TEST_IMAGE_PATHS:
      image = Image.open(image_path)
      # the array based representation of the image will be used later in order to prepare the
      # result image with boxes and labels on it.
      image_np = load_image_into_numpy_array(image)
      # 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.imsave(str(img) + '.jpg', image_np)
      img += 1

这篇关于使用自己的模型运行 TF 对象检测 API 时出现 FailedPreconditionError的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！