tensorflow - 如何将图像传递给模型以在 Tensorflow 中进行分类

Question

我使用下面的代码创建了一个模型:

# Deep Learning    
# In[25]:

from __future__ import print_function
import numpy as np
import tensorflow as tf
from six.moves import cPickle as pickle
from six.moves import range


# In[37]:

pickle_file = 'notMNIST.pickle'

with open(pickle_file, 'rb') as f:
  save = pickle.load(f)
  train_dataset = save['train_dataset']
  train_labels = save['train_labels']
  valid_dataset = save['valid_dataset']
  valid_labels = save['valid_labels']
  test_dataset = save['test_dataset']
  test_labels = save['test_labels']
  del save  # hint to help gc free up memory
  print('Training set', train_dataset.shape, train_labels.shape)
  print('Validation set', valid_dataset.shape, valid_labels.shape)
  print('Test set', test_dataset.shape, test_labels.shape)
  print(test_labels)


# Reformat into a TensorFlow-friendly shape:
# - convolutions need the image data formatted as a cube (width by height by #channels)
# - labels as float 1-hot encodings.

# In[38]:

image_size = 28
num_labels = 10
num_channels = 1 # grayscale

import numpy as np

def reformat(dataset, labels):
  dataset = dataset.reshape(
    (-1, image_size, image_size, num_channels)).astype(np.float32)
  #print(np.arange(num_labels))
  labels = (np.arange(num_labels) == labels[:,None]).astype(np.float32)
  #print(labels[0,:])
  print(labels[0])
  return dataset, labels
train_dataset, train_labels = reformat(train_dataset, train_labels)
valid_dataset, valid_labels = reformat(valid_dataset, valid_labels)
test_dataset, test_labels = reformat(test_dataset, test_labels)
print('Training set', train_dataset.shape, train_labels.shape)
print('Validation set', valid_dataset.shape, valid_labels.shape)
print('Test set', test_dataset.shape, test_labels.shape)
#print(labels[0])


# In[39]:

def accuracy(predictions, labels):
  return (100.0 * np.sum(np.argmax(predictions, 1) == np.argmax(labels, 1))
          / predictions.shape[0])


# Let's build a small network with two convolutional layers, followed by one fully connected layer. Convolutional networks are more expensive computationally, so we'll limit its depth and number of fully connected nodes.

# In[47]:

batch_size = 16
patch_size = 5
depth = 16
num_hidden = 64

graph = tf.Graph()

with graph.as_default():

  # Input data.
  tf_train_dataset = tf.placeholder(
    tf.float32, shape=(batch_size, image_size, image_size, num_channels))
  tf_train_labels = tf.placeholder(tf.float32, shape=(batch_size, num_labels))
  tf_valid_dataset = tf.constant(valid_dataset)
  tf_test_dataset = tf.constant(test_dataset)

  # Variables.
  layer1_weights = tf.Variable(tf.truncated_normal(
      [patch_size, patch_size, num_channels, depth], stddev=0.1),name="layer1_weights")
  layer1_biases = tf.Variable(tf.zeros([depth]),name = "layer1_biases")
  layer2_weights = tf.Variable(tf.truncated_normal(
      [patch_size, patch_size, depth, depth], stddev=0.1),name = "layer2_weights")
  layer2_biases = tf.Variable(tf.constant(1.0, shape=[depth]),name ="layer2_biases")
  layer3_weights = tf.Variable(tf.truncated_normal(
      [image_size // 4 * image_size // 4 * depth, num_hidden], stddev=0.1),name="layer3_biases")
  layer3_biases = tf.Variable(tf.constant(1.0, shape=[num_hidden]),name = "layer3_biases")
  layer4_weights = tf.Variable(tf.truncated_normal(
      [num_hidden, num_labels], stddev=0.1),name = "layer4_weights")
  layer4_biases = tf.Variable(tf.constant(1.0, shape=[num_labels]),name = "layer4_biases")

  # Model.
  def model(data):
    conv = tf.nn.conv2d(data, layer1_weights, [1, 2, 2, 1], padding='SAME')
    hidden = tf.nn.relu(conv + layer1_biases)
    conv = tf.nn.conv2d(hidden, layer2_weights, [1, 2, 2, 1], padding='SAME')
    hidden = tf.nn.relu(conv + layer2_biases)
    shape = hidden.get_shape().as_list()
    reshape = tf.reshape(hidden, [shape[0], shape[1] * shape[2] * shape[3]])
    hidden = tf.nn.relu(tf.matmul(reshape, layer3_weights) + layer3_biases)
    return tf.matmul(hidden, layer4_weights) + layer4_biases

  # Training computation.
  logits = model(tf_train_dataset)
  loss = tf.reduce_mean(
    tf.nn.softmax_cross_entropy_with_logits(logits, tf_train_labels))

  # Optimizer.
  optimizer = tf.train.GradientDescentOptimizer(0.05).minimize(loss)

  # Predictions for the training, validation, and test data.
  train_prediction = tf.nn.softmax(logits)
  valid_prediction = tf.nn.softmax(model(tf_valid_dataset))
  test_prediction = tf.nn.softmax(model(tf_test_dataset))


# In[48]:

num_steps = 1001
#saver = tf.train.Saver()
with tf.Session(graph=graph) as session:
  tf.initialize_all_variables().run()
  print('Initialized')
  for step in range(num_steps):
    offset = (step * batch_size) % (train_labels.shape[0] - batch_size)
    batch_data = train_dataset[offset:(offset + batch_size), :, :, :]
    batch_labels = train_labels[offset:(offset + batch_size), :]
    feed_dict = {tf_train_dataset : batch_data, tf_train_labels : batch_labels}
    _, l, predictions = session.run(
      [optimizer, loss, train_prediction], feed_dict=feed_dict)
    if (step % 50 == 0):
      print('Minibatch loss at step %d: %f' % (step, l))
      print('Minibatch accuracy: %.1f%%' % accuracy(predictions, batch_labels))
      print('Validation accuracy: %.1f%%' % accuracy(
        valid_prediction.eval(), valid_labels))
  print('Test accuracy: %.1f%%' % accuracy(test_prediction.eval(), test_labels))
  save_path = tf.train.Saver().save(session, "/tmp/model.ckpt")
  print("Model saved in file: %s" % save_path)

我已经保存了模型并编写了另一个 python 程序，我试图在其中恢复模型并将其用于我的图像分类，但我无法创建图像的 4D 张量，我必须通过作为模型的输入。

python文件的代码如下:

# In[8]:

from __future__ import print_function
import numpy as np
import tensorflow as tf
from six.moves import cPickle as pickle
from six.moves import range
from scipy import ndimage   

# In[9]:

image_size = 28
num_labels = 10
num_channels = 1 # grayscale
import numpy as np


# In[10]:

def accuracy(predictions, labels):
  return (100.0 * np.sum(np.argmax(predictions, 1) == np.argmax(labels, 1))
          / predictions.shape[0])


# In[15]:

batch_size = 16
patch_size = 5
depth = 16
num_hidden = 64
pixel_depth =255

graph = tf.Graph()

with graph.as_default():

  '''# Input data.
  tf_train_dataset = tf.placeholder(
    tf.float32, shape=(batch_size, image_size, image_size, num_channels))
  tf_train_labels = tf.placeholder(tf.float32, shape=(batch_size, num_labels))
  #tf_valid_dataset = tf.constant(valid_dataset)
  tf_test_dataset = tf.constant(test_dataset)'''
  tf_train_dataset = tf.placeholder(
    tf.float32, shape=(batch_size, image_size, image_size, num_channels))
  # Variables.
  layer1_weights = tf.Variable(tf.truncated_normal(
      [patch_size, patch_size, num_channels, depth], stddev=0.1),name="layer1_weights")
  layer1_biases = tf.Variable(tf.zeros([depth]),name = "layer1_biases")
  layer2_weights = tf.Variable(tf.truncated_normal(
      [patch_size, patch_size, depth, depth], stddev=0.1),name = "layer2_weights")
  layer2_biases = tf.Variable(tf.constant(1.0, shape=[depth]),name ="layer2_biases")
  layer3_weights = tf.Variable(tf.truncated_normal(
      [image_size // 4 * image_size // 4 * depth, num_hidden], stddev=0.1),name="layer3_biases")
  layer3_biases = tf.Variable(tf.constant(1.0, shape=[num_hidden]),name = "layer3_biases")
  layer4_weights = tf.Variable(tf.truncated_normal(
      [num_hidden, num_labels], stddev=0.1),name = "layer4_weights")
  layer4_biases = tf.Variable(tf.constant(1.0, shape=[num_labels]),name = "layer4_biases")
  saver = tf.train.Saver()
  tf_
  # Model.
  def model(data):
    conv = tf.nn.conv2d(data, layer1_weights, [1, 2, 2, 1], padding='SAME')
    hidden = tf.nn.relu(conv + layer1_biases)
    conv = tf.nn.conv2d(hidden, layer2_weights, [1, 2, 2, 1], padding='SAME')
    hidden = tf.nn.relu(conv + layer2_biases)
    shape = hidden.get_shape().as_list()
    reshape = tf.reshape(hidden, [shape[0], shape[1] * shape[2] * shape[3]])
    hidden = tf.nn.relu(tf.matmul(reshape, layer3_weights) + layer3_biases)
    return tf.matmul(hidden, layer4_weights) + layer4_biases

  valid_prediction = tf.nn.softmax(model(tf_valid_dataset))
  #test_prediction = tf.nn.softmax(model(tf_test_dataset))


# In[19]:

with tf.Session(graph=graph) as sess:
  # Restore variables from disk.
  saver.restore(sess, "/tmp/model.ckpt")
  print("Model restored.")
  image_data = (ndimage.imread('notMNIST_small/A/QXJyaWJhQXJyaWJhU3RkLm90Zg==.png').astype(float) - 
                    pixel_depth / 2) / pixel_depth
  data = [0:,image_data:,]
  sess.run(valid_prediction,feed_dict={tf_valid_dataset:data})
  # Do some work with the model

正如您在 ln[19] 中看到的那样，我已经恢复了我的模型并希望通过创建 4d 张量将图像传递给模型，我正在读取图像然后尝试将其转换为 4d 张量但是 ysntax在我的代码中创建它是错误的，因此需要帮助来更正它。

Answer 1

假设 image_data 是一个灰度图像，它应该是一个二维 NumPy 数组。您可以使用以下命令将其转换为 4 维数组:

data = image_data[np.newaxis, ..., np.newaxis]

np.newaxis在第一个(批量大小)和最后一个( channel )维度中添加大小为 1 的新维度。它等效于以下内容，使用 np.expand_dims() :

data = np.expand_dims(np.expand_dims(image_data, 0), -1)

另一方面，如果您使用的是 RGB 数据，则需要对其进行转换以适合模型。例如，您可以为图像输入定义一个占位符:

input_placeholder = tf.placeholder(tf.float32, shape=[None, image_size, image_size, 3])
input_grayscale = tf.image.rgb_to_grayscale(input_placeholder)

prediction = tf.nn.softmax(model(input_grayscale))

image_data = ...  # Load from file
data = image_data[np.newaxis, ...]  # Only add a batch dimension.

prediction_val = sess.run(prediction, feed_dict={input_placeholder: data})