tensorflow CNN mnist 示例

bear_fish

发布于 2018-09-14 09:50:03

9290

发布于 2018-09-14 09:50:03

文章被收录于专栏：用户2442861的专栏用户2442861的专栏

本文给出使用tensorflow使用CNN构架的mnist分类问题：

构架图如下:

代码如下：

1. 准备输入数据:

# declare the training data placeholders
# input x - for 28 x 28 pixels = 784 - this is the flattened image data that is drawn from
# mnist.train.nextbatch()
x = tf.placeholder(tf.float32, [None, 784])
# dynamically reshape the input
x_shaped = tf.reshape(x, [-1, 28, 28, 1])
# now declare the output data placeholder - 10 digits
y = tf.placeholder(tf.float32, [None, 10])

其中reshape -1代表训练中任一sample。

显然卷积层，可以写个通用的函数，代码如下：

def create_new_conv_layer(input_data, num_input_channels, num_filters,
                          filter_shape, pool_shape, name):
    # setup the filter input shape for tf.nn.conv_2d
    conv_filt_shape = [filter_shape[0], filter_shape[1], num_input_channels,
                       num_filters]

    # initialise weights and bias for the filter
    weights = tf.Variable(tf.truncated_normal(conv_filt_shape, stddev=0.03),
                          name=name+'_W')
    bias = tf.Variable(tf.truncated_normal([num_filters]), name=name+'_b')

    # setup the convolutional layer operation
    out_layer = tf.nn.conv2d(input_data, weights, [1, 1, 1, 1], padding='SAME')

    # add the bias
    out_layer += bias

    # apply a ReLU non-linear activation
    out_layer = tf.nn.relu(out_layer)

    # now perform max pooling
    ksize = [1, pool_shape[0], pool_shape[1], 1]
    strides = [1, 2, 2, 1]
    out_layer = tf.nn.max_pool(out_layer, ksize=ksize, strides=strides,
                               padding='SAME')

    return out_layer

下面安装代码的line/block进行解释，比如创建第一个卷积层:

# create some convolutional layers
layer1 = create_new_conv_layer(x_shaped, 1, 32, [5, 5], [2, 2], name='layer1')

其中x_shaped为输入数据， 1代表channel(第一层gray图片只有一个channel), 32代表有32个filter，5, 5代表filter核大小，2, 2代表pool池化层的大小.

使用上面的函数，创建两层卷积层:

# create some convolutional layers
layer1 = create_new_conv_layer(x_shaped, 1, 32, [5, 5], [2, 2], name='layer1')
layer2 = create_new_conv_layer(layer1, 32, 64, [5, 5], [2, 2], name='layer2')

接下来是全连接层，首先7*7*64 reshape:

flattened = tf.reshape(layer2, [-1, 7 * 7 * 64])

其中-1代表训练中的某个sample

第一个全连接层：

# setup some weights and bias values for this layer,then activate with ReLU
wd1 = tf.Variable(tf.truncated_normal([7 * 7 * 64, 1000], stddev=0.03), name='wd1')
bd1 = tf.Variable(tf.truncated_normal([1000], stddev=0.01), name='bd1')
dense_layer1 = tf.matmul(flattened, wd1) + bd1
dense_layer1 = tf.nn.relu(dense_layer1)

第二个:

# another layer with softmax activations
wd2 = tf.Variable(tf.truncated_normal([1000, 10], stddev=0.03), name='wd2')
bd2 = tf.Variable(tf.truncated_normal([10], stddev=0.01), name='bd2')
dense_layer2 = tf.matmul(dense_layer1, wd2) + bd2
y_ = tf.nn.softmax(dense_layer2)

定义损失函数，以及训练优化optimiser

cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=dense_layer2, labels=y))

# add an optimiser
optimiser = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cross_entropy)

训练代码如下:

# define an accuracy assessment operation
correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

# setup the initialisation operator
init_op = tf.global_variables_initializer()

with tf.Session() as sess:
    # initialise the variables
    sess.run(init_op)
    total_batch = int(len(mnist.train.labels) / batch_size)
    for epoch in range(epochs):
        avg_cost = 0
        for i in range(total_batch):
            batch_x, batch_y = mnist.train.next_batch(batch_size=batch_size)
            _, c = sess.run([optimiser, cross_entropy],
                            feed_dict={x: batch_x, y: batch_y})
            avg_cost += c / total_batch
        test_acc = sess.run(accuracy,
                            feed_dict={x: mnist.test.images, y: mnist.test.labels})
        print("Epoch:", (epoch + 1), "cost =", "{:.3f}".format(avg_cost), "test accuracy: {:.3f}".format(test_acc))

    print "\nTraining complete!"
    print(sess.run(accuracy, feed_dict={x: mnist.test.images, y: mnist.test.labels}))

训练，以及测试结果如下：