Tensorflow numpy 图像重塑 [灰度图像]

我正在尝试使用我训练过的神经网络数据在 jupyter 笔记本中执行 Tensorflow“object_detection_tutorial.py”，但它会抛出 ValueError。上面提到的文件是 YouTube 上用于对象检测的 Sentdexs 张量流教程的一部分。

你可以在这里找到它： （)

我的图像尺寸：490x704。这样就会得到一个 344960 数组。

但它说：ValueError: cannot reshape array of size 344960 into shape (490,704,3)

我究竟做错了什么？

Code:

Imports

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

环境设置

# This is needed to display the images.
%matplotlib inline

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

物体检测导入

from utils import label_map_util

from utils import visualization_utils as vis_util

变量

# What model to download.
MODEL_NAME = 'shard_graph'

# 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('training', 'object-detection.pbtxt')

NUM_CLASSES = 90

将（冻结的）Tensorflow 模型加载到内存中。

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='')

加载标签图

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)

辅助代码

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)

检测

# 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, 'frame_{}.png'.format(i)) for i in range(0, 2) ]

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

-

with detection_graph.as_default():
  with tf.Session(graph=detection_graph) as sess:
    # Definite input and output Tensors for detection_graph
    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.
    detection_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.
    detection_scores = detection_graph.get_tensor_by_name('detection_scores:0')
    detection_classes = detection_graph.get_tensor_by_name('detection_classes:0')
    num_detections = detection_graph.get_tensor_by_name('num_detections:0')
    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)
      # Actual detection.
      (boxes, scores, classes, num) = sess.run(
          [detection_boxes, detection_scores, detection_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)

脚本的最后一部分抛出错误：

----------------------------------------------------------------------
ValueError                           Traceback (most recent call last)
<ipython-input-62-7493eea60222> in <module>()
     14       # the array based representation of the image will be used later in order to prepare the
     15       # result image with boxes and labels on it.
---> 16       image_np = load_image_into_numpy_array(image)
     17       # Expand dimensions since the model expects images to have shape: [1, None, None, 3]
     18       image_np_expanded = np.expand_dims(image_np, axis=0)

<ipython-input-60-af094dcdd84a> in load_image_into_numpy_array(image)
      2   (im_width, im_height) = image.size
      3   return np.array(image.getdata()).reshape(
----> 4       (im_height, im_width, 3)).astype(np.uint8)

ValueError: cannot reshape array of size 344960 into shape (490,704,3)

Edit:

所以我改变了这个函数的最后一行：

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)

to:

(im_height, im_width)).astype(np.uint8)

ValueError 已解决。但现在引发了另一个与数组格式相关的 ValueError：

----------------------------------------------------------------------
ValueError                           Traceback (most recent call last)
<ipython-input-107-7493eea60222> in <module>()
     20       (boxes, scores, classes, num) = sess.run(
     21           [detection_boxes, detection_scores, detection_classes, num_detections],
---> 22           feed_dict={image_tensor: image_np_expanded})
     23       # Visualization of the results of a detection.
     24       vis_util.visualize_boxes_and_labels_on_image_array(

~/.local/lib/python3.6/site-packages/tensorflow/python/client/session.py in run(self, fetches, feed_dict, options, run_metadata)
    898     try:
    899       result = self._run(None, fetches, feed_dict, options_ptr,
--> 900                          run_metadata_ptr)
    901       if run_metadata:
    902         proto_data = tf_session.TF_GetBuffer(run_metadata_ptr)

~/.local/lib/python3.6/site-packages/tensorflow/python/client/session.py in _run(self, handle, fetches, feed_dict, options, run_metadata)
   1109                              'which has shape %r' %
   1110                              (np_val.shape, subfeed_t.name,
-> 1111                               str(subfeed_t.get_shape())))
   1112           if not self.graph.is_feedable(subfeed_t):
   1113             raise ValueError('Tensor %s may not be fed.' % subfeed_t)

ValueError: Cannot feed value of shape (1, 490, 704) for Tensor 'image_tensor:0', which has shape '(?, ?, ?, 3)'

这是否意味着这个张量流模型不是为灰度图像设计的？有办法让它发挥作用吗？

SOLUTION

感谢 Matan Hugi，它现在工作得很好。我所要做的就是将此函数更改为：

def load_image_into_numpy_array(image):
    # The function supports only grayscale images
    last_axis = -1
    dim_to_repeat = 2
    repeats = 3
    grscale_img_3dims = np.expand_dims(image, last_axis)
    training_image = np.repeat(grscale_img_3dims, repeats, dim_to_repeat).astype('uint8')
    assert len(training_image.shape) == 3
    assert training_image.shape[-1] == 3
    return training_image

Tensorflow 预期输入以 NHWC 格式格式化， 这意味着：（批次、高度、宽度、通道）。

第 1 步 - 添加最后一个维度：

last_axis = -1
grscale_img_3dims = np.expand_dims(image, last_axis)

步骤 2 - 重复最后一个维度 3 次：

dim_to_repeat = 2
repeats = 3
np.repeat(grscale_img_3dims, repeats, dim_to_repeat)

所以你的函数应该是：

def load_image_into_numpy_array(image):
    # The function supports only grayscale images
    assert len(image.shape) == 2, "Not a grayscale input image" 
    last_axis = -1
    dim_to_repeat = 2
    repeats = 3
    grscale_img_3dims = np.expand_dims(image, last_axis)
    training_image = np.repeat(grscale_img_3dims, repeats, dim_to_repeat).astype('uint8')
    assert len(training_image.shape) == 3
    assert training_image.shape[-1] == 3
    return training_image