TensorFlow基础笔记(14) 网络模型的保存与恢复_mnist数据实例

http://blog.csdn.net/huachao1001/article/details/78502910

http://blog.csdn.net/u014432647/article/details/75276718

https://zhuanlan.zhihu.com/p/32887066

#coding:utf-8
#http://blog.csdn.net/zhuiqiuk/article/details/53376283
#http://blog.csdn.net/gan_player/article/details/77586489
from __future__ import absolute_import, unicode_literals
from tensorflow.examples.tutorials.mnist import input_data
import tensorflow as tf
import shutil
import os.path
from tensorflow.python.framework import graph_util

def weight_variable(shape):
    initial = tf.truncated_normal(shape, stddev=0.1)
    return tf.Variable(initial)

def bias_variable(shape):
    initial = tf.constant(0.1, shape=shape)
    return tf.Variable(initial)

def conv2d(x, W):
    return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')

def max_pool_2x2(x):
    return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],
                          strides=[1, 2, 2, 1], padding='SAME')


def inference(input_image, keep_prob):
    W_conv1 = weight_variable([5, 5, 1, 32])
    b_conv1 = bias_variable([32])
    x_image = tf.reshape(input_image, [-1, 28, 28, 1])
    h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
    h_pool1 = max_pool_2x2(h_conv1)

    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)
    h_pool2 = max_pool_2x2(h_conv2)

    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)

    #keep_prob = tf.placeholder("float")
    h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

    W_fc2 = weight_variable([1024, 10])
    b_fc2 = bias_variable([10])

    logits = tf.matmul(h_fc1_drop, W_fc2) + b_fc2

    return logits

def train(export_dir):
    mnist = input_data.read_data_sets("datasets", one_hot=True)

    g = tf.Graph()
    with g.as_default():
        x = tf.placeholder("float", shape=[None, 784])
        y_ = tf.placeholder("float", shape=[None, 10])
        keep_prob = tf.placeholder("float")

        logits = inference(x, keep_prob)
        y_conv = tf.nn.softmax(logits)

        cross_entropy = -tf.reduce_sum(y_ * tf.log(y_conv))
        train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
        correct_prediction = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_, 1))
        accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))

        sess = tf.Session()
        sess.run(tf.initialize_all_variables())

        

        for i in range(201):
            batch = mnist.train.next_batch(50)
            if i % 100 == 0:
                train_accuracy = accuracy.eval(
                    {x: batch[0], y_: batch[1], keep_prob: 1.0}, sess)
                print "step %d, training accuracy %g" % (i, train_accuracy)
            train_step.run(
                {x: batch[0], y_: batch[1], keep_prob: 0.5}, sess)

        print "test accuracy %g" % accuracy.eval(
            {x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}, sess)

        saver = tf.train.Saver()
        step = 200
        checkpoint_file = os.path.join(export_dir, 'model.ckpt')
        saver.save(sess, checkpoint_file, global_step=step)
        checkpoint_file = os.path.join(export_dir, 'model.ckpt')


def export_pb_model(model_name):
  graph = tf.Graph()
  with graph.as_default():
    input_image = tf.placeholder("float", shape=[None,28*28], name='inputdata')
    keep_prob = tf.placeholder("float",  name = 'keep_probdata')
    logits = inference(input_image, keep_prob)
    y_conv = tf.nn.softmax(logits,name='outputdata')
    restore_saver = tf.train.Saver()

  with tf.Session(graph=graph) as sess:
    sess.run(tf.global_variables_initializer())
    latest_ckpt = tf.train.latest_checkpoint('log')
    restore_saver.restore(sess, latest_ckpt)
    output_graph_def = tf.graph_util.convert_variables_to_constants(
        sess, graph.as_graph_def(), ['outputdata'])

#    tf.train.write_graph(output_graph_def, 'log', model_name, as_text=False)
    with tf.gfile.GFile(model_name, "wb") as f:  
        f.write(output_graph_def.SerializeToString()) 


def test_pb_model(model_name):
    mnist = input_data.read_data_sets("datasets", one_hot=True)

    with tf.Graph().as_default():
        output_graph_def = tf.GraphDef()
        output_graph_path = model_name
    #    sess.graph.add_to_collection("input", mnist.test.images)

        with open(output_graph_path, "rb") as f:
            output_graph_def.ParseFromString(f.read())
            tf.import_graph_def(output_graph_def, name="")

        with tf.Session() as sess:

            tf.initialize_all_variables().run()
            input_x = sess.graph.get_tensor_by_name("inputdata:0")        
            output = sess.graph.get_tensor_by_name("outputdata:0")
            keep_prob = sess.graph.get_tensor_by_name("keep_probdata:0")

            y_conv_2 = sess.run(output,{input_x:mnist.test.images, keep_prob: 1.0})
            print( "y_conv_2", y_conv_2)

            # Test trained model
            #y__2 = tf.placeholder("float", [None, 10])
            y__2 = mnist.test.labels
            correct_prediction_2 = tf.equal(tf.argmax(y_conv_2, 1), tf.argmax(y__2, 1))
            print ("correct_prediction_2", correct_prediction_2 )
            accuracy_2 = tf.reduce_mean(tf.cast(correct_prediction_2, "float"))
            print ("accuracy_2", accuracy_2)

            print ("check accuracy %g" % accuracy_2.eval())


if __name__ == '__main__':
    export_dir = './log'
    if os.path.exists(export_dir):
        shutil.rmtree(export_dir)
    #训练并保存模型ckpt
    train(export_dir)
    model_name = os.path.join(export_dir, 'mnist.pb')
    #ckpt模型转换为pb模型
    export_pb_model(model_name)
    #测试pb模型
    test_pb_model(model_name)

 

$ python mymain.py

#训练并保存模型ckpt

Extracting datasets/train-images-idx3-ubyte.gz
Extracting datasets/train-labels-idx1-ubyte.gz
Extracting datasets/t10k-images-idx3-ubyte.gz
Extracting datasets/t10k-labels-idx1-ubyte.gz
2018-03-19 18:11:27.046638: I tensorflow/core/platform/cpu_feature_guard.cc:137] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA
2018-03-19 18:11:27.169530: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:892] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2018-03-19 18:11:27.170178: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1030] Found device 0 with properties:
name: GeForce GTX 1080 major: 6 minor: 1 memoryClockRate(GHz): 1.7335
pciBusID: 0000:01:00.0
totalMemory: 7.92GiB freeMemory: 5.51GiB
2018-03-19 18:11:27.170196: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1120] Creating TensorFlow device (/device:GPU:0) -> (device: 0, name: GeForce GTX 1080, pci bus id: 0000:01:00.0, compute capability: 6.1)
WARNING:tensorflow:From /usr/local/lib/python2.7/dist-packages/tensorflow/python/util/tf_should_use.py:107: initialize_all_variables (from tensorflow.python.ops.variables) is deprecated and will be removed after 2017-03-02.
Instructions for updating:
Use `tf.global_variables_initializer` instead.
step 0, training accuracy 0.08
step 100, training accuracy 0.86
step 200, training accuracy 0.96
2018-03-19 18:11:29.100338: W tensorflow/core/common_runtime/bfc_allocator.cc:217] Allocator (GPU_0_bfc) ran out of memory trying to allocate 3.32GiB. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory is available.
test accuracy 0.9137

 

#ckpt模型转换为pb模型

2018-03-19 18:11:30.655025: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1120] Creating TensorFlow device (/device:GPU:0) -> (device: 0, name: GeForce GTX 1080, pci bus id: 0000:01:00.0, compute capability: 6.1)
Converted 8 variables to const ops.

 

#测试pb模型

Extracting datasets/train-images-idx3-ubyte.gz
Extracting datasets/train-labels-idx1-ubyte.gz
Extracting datasets/t10k-images-idx3-ubyte.gz
Extracting datasets/t10k-labels-idx1-ubyte.gz
2018-03-19 18:11:32.419375: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1120] Creating TensorFlow device (/device:GPU:0) -> (device: 0, name: GeForce GTX 1080, pci bus id: 0000:01:00.0, compute capability: 6.1)
(u'y_conv_2', array([[ 3.83061661e-06, 2.25869144e-06, 6.98342774e-05, ...,
9.99720514e-01, 5.38732929e-05, 6.28733032e-05],
[ 1.85461645e-03, 3.86392418e-03, 9.55442667e-01, ...,
1.31935649e-05, 2.71034874e-02, 4.14738406e-06],
[ 2.61329369e-05, 9.94501710e-01, 1.34233199e-03, ...,
8.23311449e-04, 1.73626456e-03, 3.27934940e-05],
...,
[ 1.58834242e-04, 1.02327869e-03, 9.29224771e-04, ...,
9.04104114e-03, 1.03222862e-01, 1.16873145e-01],
[ 9.86627676e-03, 1.02333550e-03, 2.13368423e-03, ...,
2.72160349e-03, 3.91508579e-01, 4.37955791e-03],
[ 1.95508893e-03, 2.17417346e-06, 1.18497398e-03, ...,
5.04385412e-07, 3.14567442e-05, 4.29990359e-06]], dtype=float32))
(u'correct_prediction_2', )
(u'accuracy_2', )
check accuracy 0.9137