如何基于训练有素的Tensorflow模型进行预测？

Question

我已经检查了许多关于Stackoverflow的问题，但仍然存在问题。

我遵循了Deep MNIST的专家教程，并使用了mnist_deep.py中的代码，并使用tf.saved_model.builder.SavedModelBuilder()将模型保存到磁盘中。

在我的predict.py中，我使用tf.saved_model.loader.load()加载模型，在加载模型之后，基于我在Google上进行的大量搜索，我知道我必须运行sess.run(y_, feed_dict={x: test_data})进行预测，我也知道变量y ，它应该是最后一层，对于feed_dict的“ x”，它应该是训练中输入的占位符。

我的问题是，我不知道哪个代码属于mnist_deep.py的最后一层。

我的mnist_deep.py代码如下：

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import argparse
import sys
import tempfile

from tensorflow.examples.tutorials.mnist import input_data

import tensorflow as tf

FLAGS = None


def deepnn(x):
  """deepnn builds the graph for a deep net for classifying digits.
  Args:
    x: an input tensor with the dimensions (N_examples, 784), where 784 is the
    number of pixels in a standard MNIST image.
  Returns:
    A tuple (y, keep_prob). y is a tensor of shape (N_examples, 10), with values
    equal to the logits of classifying the digit into one of 10 classes (the
    digits 0-9). keep_prob is a scalar placeholder for the probability of
    dropout.
  """
  # Reshape to use within a convolutional neural net.
  # Last dimension is for "features" - there is only one here, since images are
  # grayscale -- it would be 3 for an RGB image, 4 for RGBA, etc.
  with tf.name_scope('reshape'):
    x_image = tf.reshape(x, [-1, 28, 28, 1])

  # First convolutional layer - maps one grayscale image to 32 feature maps.
  with tf.name_scope('conv1'):
    W_conv1 = weight_variable([5, 5, 1, 32])
    b_conv1 = bias_variable([32])
    h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)

  # Pooling layer - downsamples by 2X.
  with tf.name_scope('pool1'):
    h_pool1 = max_pool_2x2(h_conv1)

  # Second convolutional layer -- maps 32 feature maps to 64.
  with tf.name_scope('conv2'):
    W_conv2 = weight_variable([5, 5, 32, 64])
    b_conv2 = bias_variable([64])
    h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)

  # Second pooling layer.
  with tf.name_scope('pool2'):
    h_pool2 = max_pool_2x2(h_conv2)

  # Fully connected layer 1 -- after 2 round of downsampling, our 28x28 image
  # is down to 7x7x64 feature maps -- maps this to 1024 features.
  with tf.name_scope('fc1'):
    W_fc1 = weight_variable([7 * 7 * 64, 1024])
    b_fc1 = bias_variable([1024])

    h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])
    h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)

  # Dropout - controls the complexity of the model, prevents co-adaptation of
  # features.
  with tf.name_scope('dropout'):
    keep_prob = tf.placeholder(tf.float32)
    h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

  # Map the 1024 features to 10 classes, one for each digit
  with tf.name_scope('fc2'):
    W_fc2 = weight_variable([1024, 10])
    b_fc2 = bias_variable([10])

    y_conv = tf.matmul(h_fc1_drop, W_fc2) + b_fc2
  return y_conv, keep_prob


def conv2d(x, W):
  """conv2d returns a 2d convolution layer with full stride."""
  return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')


def max_pool_2x2(x):
  """max_pool_2x2 downsamples a feature map by 2X."""
  return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],
                        strides=[1, 2, 2, 1], padding='SAME')


def weight_variable(shape):
  """weight_variable generates a weight variable of a given shape."""
  initial = tf.truncated_normal(shape, stddev=0.1)
  return tf.Variable(initial)


def bias_variable(shape):
  """bias_variable generates a bias variable of a given shape."""
  initial = tf.constant(0.1, shape=shape)
  return tf.Variable(initial)



# Import data
mnist = input_data.read_data_sets("./MNIST_data", one_hot=True)

# Create the model
x = tf.placeholder(tf.float32, [None, 784])

# Define loss and optimizer
y_ = tf.placeholder(tf.float32, [None, 10])

# Build the graph for the deep net
y_conv, keep_prob = deepnn(x)

with tf.name_scope('loss'):
  cross_entropy = tf.nn.softmax_cross_entropy_with_logits(labels=y_,
                                                          logits=y_conv)
cross_entropy = tf.reduce_mean(cross_entropy)

with tf.name_scope('adam_optimizer'):
  train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)

with tf.name_scope('accuracy'):
  correct_prediction = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_, 1))
  correct_prediction = tf.cast(correct_prediction, tf.float32)
accuracy = tf.reduce_mean(correct_prediction)

graph_location = tempfile.mkdtemp()
print('Saving graph to: %s' % graph_location)
train_writer = tf.summary.FileWriter(graph_location)
train_writer.add_graph(tf.get_default_graph())

builder = tf.saved_model.builder.SavedModelBuilder("./model")
with tf.Session() as sess:
  sess.run(tf.global_variables_initializer())
  for i in range(20000):
    batch = mnist.train.next_batch(50)
    if i % 100 == 0:
      train_accuracy = accuracy.eval(feed_dict={
          x: batch[0], y_: batch[1], keep_prob: 1.0})
      print('step %d, training accuracy %g' % (i, train_accuracy))
    train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})
  builder.add_meta_graph_and_variables(sess,"CNN4mnist")
  print('test accuracy %g' % accuracy.eval(feed_dict={
      x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))

builder.save()

这是我的predict.py：

import tensorflow as tf
import pandas as pd
import numpy as np

PATH_TEST = "../data/test.csv"

# load test data
print('>>>loading test data...')
test_data=pd.read_csv(PATH_TEST)
test_data /= 255
mean = np.mean(test_data)
test_data -= mean
test_data = np.asarray([ x.reshape(28,28,1) for x in test_data.as_matrix() ])
print(len(test_data))

results = None
with tf.Session() as sess:
    tf.saved_model.loader.load(sess,"CNN4mnist", "./model")
    W = tf.Variable(tf.zeros([784,10]))
    b = tf.Variable(tf.zeros([10]))
    x = tf.placeholder(tf.float32, [None, 28,28,1])
    y = tf.nn.softmax(tf.matmul(x,W) + b)
    results = sess.run(y_, feed_dict={x: test_data})

print(results)
print(">>>saving results...")
df = pd.DataFrame({'Label':results})
df.index += 1
df.index.name='ImageId'
df.to_csv('results.csv')

Answer 1

您无需运行y_ ，而是占位符。

加载模型后，您也无需重新定义变量，而是使用保存的变量。

因此，加载后，只需运行sess.run(y_conv, feed_dict={x: test_data})

y_conv是模型最后一层的预测输出。

要在加载模型后访问y_conv ，请通过以下方式获取它：
y_conv = sess.graph.get_tensor_by_name("it's name goes here")
您需要先命名y_conv然后再保存。

或者，可以在保存之前将y_conv添加到集合中，然后在加载模型后从集合中检索它：
tf.add_to_collection('vars', y_conv)
y_conv = tf.get_collection('vars')[0]