卷积神经网络学习笔记（二）：CNN代码实例

对于刚刚入门神经网络，以及初学TensorFlow的我来说，讲已有的知识转化成不常接触的代码确实不是一件很容易的事情。看一篇CNN代码，虽然是别人写好有注释的笔记，但是个人认为真的是很困难的（相信遇到这类困难的不只我一个）。在边看边写的过程中，要无数次的查阅TF的官方文档，但是如此，还是要坚持去看下去。以一篇CNN的实例代码，做详细的解释，希望对自己能有所帮助，如若能解和我有同样困难人之困惑，便更是荣幸。

from __future__ import division, print_function, absolute_import

# Import MNIST data
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("/tmp/data/", one_hot=False)

import tensorflow as tf
import matplotlib.pyplot as plt
import numpy as np

如上是做一些数据及包的导入，不做太多的解释。但是其中有一个问题，对于初次使用Pycharm的朋友， Matplotlib图表不能在Pycharm中显示。解决此问题请参考：

http://blog.csdn.net/xinluqishi123/article/details/63523531

# Training Parameters
learning_rate = 0.001
num_steps = 2000
batch_size = 128

# Network Parameters
num_input = 784 # MNIST data input (img shape: 28*28)
num_classes = 10 # MNIST total classes (0-9 digits)
dropout = 0.75 # Dropout, probability to keep units

设置一些初始的参数。

# Create the neural network
def conv_net(x_dict, n_classes, dropout, reuse, is_training):

    # Define a scope for reusing the variables
    with tf.variable_scope('ConvNet', reuse=reuse):
        # TF Estimator input is a dict, in case of multiple inputs
        x = x_dict['images']

        # MNIST data input is a 1-D vector of 784 features (28*28 pixels)
        # Reshape to match picture format [Height x Width x Channel]
        # Tensor input become 4-D: [Batch Size, Height, Width, Channel]
        x = tf.reshape(x, shape=[-1, 28, 28, 1])

        # Convolution Layer with 32 filters and a kernel size of 5
        conv1 = tf.layers.conv2d(x, 32, 5, activation=tf.nn.relu)
        # Max Pooling (down-sampling) with strides of 2 and kernel size of 2
        conv1 = tf.layers.max_pooling2d(conv1, 2, 2)

        # Convolution Layer with 32 filters and a kernel size of 5
        conv2 = tf.layers.conv2d(conv1, 64, 3, activation=tf.nn.relu)
        # Max Pooling (down-sampling) with strides of 2 and kernel size of 2
        conv2 = tf.layers.max_pooling2d(conv2, 2, 2)

        # Flatten the data to a 1-D vector for the fully connected layer
        fc1 = tf.contrib.layers.flatten(conv2)

        # Fully connected layer (in tf contrib folder for now)
        fc1 = tf.layers.dense(fc1, 1024)
        # Apply Dropout (if is_training is False, dropout is not applied)
        fc1 = tf.layers.dropout(fc1, rate=dropout, training=is_training)

        # Output layer, class prediction
        out = tf.layers.dense(fc1, n_classes)

    return out

上面的代码，建立了一个卷积神经网络。

# Define the model function (following TF Estimator Template)
def model_fn(features, labels, mode):

    # Build the neural network
    # Because Dropout have different behavior at training and prediction time, we
    # need to create 2 distinct computation graphs that still share the same weights.
    logits_train = conv_net(features, num_classes, dropout, reuse=False, is_training=True)
    logits_test = conv_net(features, num_classes, dropout, reuse=True, is_training=False)

    # Predictions
    pred_classes = tf.argmax(logits_test, axis=1)
    pred_probas = tf.nn.softmax(logits_test)

    # If prediction mode, early return
    if mode == tf.estimator.ModeKeys.PREDICT:
        return tf.estimator.EstimatorSpec(mode, predictions=pred_classes) 

    # Define loss and optimizer
    loss_op = tf.reduce_mean(tf.nn.sparse_softmax_cross_entropy_with_logits(
        logits=logits_train, labels=tf.cast(labels, dtype=tf.int32)))
    optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate)
    train_op = optimizer.minimize(loss_op, global_step=tf.train.get_global_step())

    # Evaluate the accuracy of the model
    acc_op = tf.metrics.accuracy(labels=labels, predictions=pred_classes)

    # TF Estimators requires to return a EstimatorSpec, that specify
    # the different ops for training, evaluating, ...
    estim_specs = tf.estimator.EstimatorSpec(
      mode=mode,
      predictions=pred_classes,
      loss=loss_op,
      train_op=train_op,
      eval_metric_ops={'accuracy': acc_op})

    return estim_specs