Tensorflow模型的保存和加载

时间:2018-07-13 09:49:45

标签: python tensorflow keras deep-learning conv-neural-network

如何像我们在do keras中一样使用模型图保存张量流模型。 除了可以在预测文件中再次定义整个图形之外,我们还可以保存整个模型(权重和图形)并稍后导入

在Keras中:

checkpoint = ModelCheckpoint('RightLane-{epoch:03d}.h5',monitor='val_loss', verbose=0,  save_best_only=False, mode='auto')

将给出一个可以用于预测的h5文件

model = load_model("RightLane-030.h5")

如何在本机张量流中做到这一点

2 个答案:

答案 0 :(得分:3)

方法1:在一个文件中冻结图形和权重(可能无法进行重新训练)

此选项显示如何将图形和权重保存在一个文件中。它的预期用例是在训练模型后部署/共享模型。为此,我们将使用protobuf(pb)格式。

鉴于张量流会话(和图形),您可以使用以下方式生成一个protobuf

# freeze variables
output_graph_def = tf.graph_util.convert_variables_to_constants(
                               sess=sess,
                               input_graph_def =sess.graph.as_graph_def(),
                               output_node_names=['myMode/conv/output'])

# write protobuf to disk
with tf.gfile.GFile('graph.pb', "wb") as f:
    f.write(output_graph_def.SerializeToString())

其中output_node_names期望为图的结果节点提供名称字符串列表(参见tensorflow documentation)。

然后,您可以加载protobuf并获取具有权重的图形,以轻松执行前向传递。

with tf.gfile.GFile(path_to_pb, "rb") as f:
    graph_def = tf.GraphDef()
    graph_def.ParseFromString(f.read())
with tf.Graph().as_default() as graph:
    tf.import_graph_def(graph_def, name='')
    return graph

方法2:恢复元数据和检查点(易于重新训练)

如果您希望能够继续训练模型,则可能需要恢复完整的图形,即权重以及损失函数,一些梯度信息(例如对于Adam优化器)等。

使用时需要使用tensorflow生成的meta和检查点文件

saver = tf.train.Saver(...variables...)
saver.save(sess, 'my-model')

这将生成两个文件my-modelmy-model.meta

从这两个文件中,您可以使用以下方式加载图形:

  new_saver = tf.train.import_meta_graph('my-model.meta')
  new_saver.restore(sess, 'my-model')

有关更多详细信息,请查看官方的documentation

答案 1 :(得分:0)

这是一个基于tensorflow github的完整示例。我复制了我在其他地方所做的另一封回复。可能还有其他/更好的方法可以在某处执行此操作。

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import numpy as np
import pandas as pd
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.
​
  keep_prob = tf.placeholder_with_default(1.0,())
  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("/tmp")
# Create the model
x = tf.placeholder(tf.float32, [None, 784], name="x")
# Define loss and optimizer
y_ = tf.placeholder(tf.int64, [None])
# Build the graph for the deep net
y_conv, keep_prob = deepnn(x)
with tf.name_scope('loss'):
    cross_entropy = tf.losses.sparse_softmax_cross_entropy(
        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), y_)
    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())
​
with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    for i in range(1000):
      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})
​
    print('test accuracy %g' % accuracy.eval(feed_dict={
        x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))

    simg = np.reshape(mnist.test.images[0],(-1,784))    
    output = sess.run(y_conv,feed_dict={x:simg,keep_prob:1.0})
    print(tf.argmax(output,1).eval())
    saver = tf.train.Saver()
    saver.save(sess,"/tmp/network")

从新的python运行中恢复:

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

import tensorflow as tf
import numpy as np

import argparse
import sys
import tempfile
from tensorflow.examples.tutorials.mnist import input_data

sess =  tf.Session() 
saver = tf.train.import_meta_graph('/tmp/network.meta')
saver.restore(sess,tf.train.latest_checkpoint('/tmp'))
graph = tf.get_default_graph()
mnist = input_data.read_data_sets("/tmp")
simg = np.reshape(mnist.test.images[0],(-1,784))
op_to_restore = graph.get_tensor_by_name("fc2/MatMul:0")
x = graph.get_tensor_by_name("x:0")
output = sess.run(op_to_restore,feed_dict= {x:simg})
print("Result = ", np.argmax(output))