Tensorflow-CNN学习以及实现

代码参数解释

卷积操作

tf.nn.conv2d(input, filter, strides, padding, use_cudnn_on_gpu=None, name=None)

input：待卷积的数据。格式要求为一个张量，[batch, in_height, in_width, in_channels].

分别表示 批次数，图像高度，宽度，输入通道数。

filter： 卷积核。格式要求为[filter_height, filter_width, in_channels, out_channels].

分别表示 卷积核的高度，宽度，输入通道数，输出通道数。

strides :一个长为4的list. 表示每次卷积以后卷积窗口在input中滑动的距离

padding ：有SAME和VALID两种选项，表示是否要保留图像边上那一圈不完全卷积的部分。如果是SAME，则保留

use_cudnn_on_gpu ：是否使用cudnn加速。默认是True

池化操作

tf.nn.max_pool

进行最大值池化操作,而avg_pool 则进行平均值池化操作.函数的定义为：

max_pool(value, ksize, strides, padding, data_format="NHWC", name=None):

value: 一个4D张量，格式为[batch, height, width, channels]，与conv2d中input格式一样

ksize: 长为4的list,表示池化窗口的尺寸

strides: 池化窗口的滑动值，与conv2d中的一样

padding: 与conv2d中用法一样。

代码实现以及解释

import tensorflow as tf

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

# Parameters
learning_rate = 0.001
training_iters = 200000
batch_size = 128
display_step = 10

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

# tf Graph input
x = tf.placeholder(tf.float32, [None, n_input])
y = tf.placeholder(tf.float32, [None, n_classes])
keep_prob = tf.placeholder(tf.float32) #dropout (keep probability)

# Create some wrappers for simplicity
def conv2d(x, W, b, strides=1):
# Conv2D wrapper, with bias and relu activation
# 结果返回一个Tensor，这个输出是feature map，shape仍然是[batch, height, width, channels]这种形式。
# 第二个参数（W）：参数含义：[卷积核的高度，卷积核的宽度，图像通道数，卷积核个数]
x = tf.nn.conv2d(x, W, strides=[1, strides, strides, 1], padding='SAME')
x = tf.nn.bias_add(x, b)
return tf.nn.relu(x)

#最大池化，池化也有窗口，有滑动步长
def maxpool2d(x, k=2):
# MaxPool2D wrapper
return tf.nn.max_pool(x, ksize=[1, k, k, 1], strides=[1, k, k, 1],
padding='SAME')

# Create model
def conv_net(x, weights, biases, dropout):
# Reshape input picture
x = tf.reshape(x, shape=[-1, 28, 28, 1])

#第一层，输入x是28*28，通道数为1，输出通道为32，即feature map 数目为32
# 又因为strides=[1,1,1,1] 所以单个通道的输出尺寸应该跟输入图像一样（为了保持输入和输出一样，在最边和上面补充0）。即总的卷积输出应该为?*28*28*32
# 也就是单个通道输出为28*28，共有32个通道，共有？个批次
# 在池化阶段，ksize=[1,2,2,1] 那么卷积结果经过池化以后的结果，其尺寸应该是？*14*14*32
# Convolution Layer
conv1 = conv2d(x, weights['wc1'], biases['bc1'])
# Max Pooling (down-sampling)
conv1 = maxpool2d(conv1, k=2)

#第二层
# 卷积核5*5，输入通道为32，输出通道为64。
# 卷积前图像的尺寸为 ?*14*14*32， 卷积后为?*14*14*64
# 池化后，输出的图像尺寸为?*7*7*64
# Convolution Layer
conv2 = conv2d(conv1, weights['wc2'], biases['bc2'])
# Max Pooling (down-sampling)
conv2 = maxpool2d(conv2, k=2)

# 第三层，是个全连接层, 输入维数7 * 7 * 64, 输出维数为1024
# Fully connected layer
# Reshape conv2 output to fit fully connected layer input
fc1 = tf.reshape(conv2, [-1, weights['wd1'].get_shape().as_list()[0]])
fc1 = tf.add(tf.matmul(fc1, weights['wd1']), biases['bd1'])
fc1 = tf.nn.relu(fc1)
# 这里使用了drop out,即随机安排一些cell输出值为0，可以防止过拟合
# Apply Dropout
fc1 = tf.nn.dropout(fc1, dropout)

# 第四层，输入1024维，输出10维，也就是具体的0~9分类
# Output, class prediction
out = tf.add(tf.matmul(fc1, weights['out']), biases['out'])
return out

# Store layers weight & bias
# 这里的weight就是卷积核，卷积核就是要学习的参数（个人理解，不到位请指点）
weights = {
# 5x5 conv, 1 input, 32 outputs
#
'wc1': tf.Variable(tf.random_normal([5, 5, 1, 32])),
# 5x5 conv, 32 inputs, 64 outputs
'wc2': tf.Variable(tf.random_normal([5, 5, 32, 64])),
# fully connected, 7*7*64 inputs, 1024 outputs
'wd1': tf.Variable(tf.random_normal([7*7*64, 1024])),
# 1024 inputs, 10 outputs (class prediction)
'out': tf.Variable(tf.random_normal([1024, n_classes]))
}

biases = {
'bc1': tf.Variable(tf.random_normal([32])),
'bc2': tf.Variable(tf.random_normal([64])),
'bd1': tf.Variable(tf.random_normal([1024])),
'out': tf.Variable(tf.random_normal([n_classes]))
}

# Construct model
pred = conv_net(x, weights, biases, keep_prob)

# Define loss and optimizer
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=pred, labels=y))
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)

# Evaluate model
correct_pred = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))

# Initializing the variables
init = tf.global_variables_initializer()

# Launch the graph
with tf.Session() as sess:
sess.run(init)
step = 1
# Keep training until reach max iterations
while step * batch_size < training_iters:
batch_x, batch_y = mnist.train.next_batch(batch_size)
# Run optimization op (backprop)
sess.run(optimizer, feed_dict={x: batch_x, y: batch_y,
keep_prob: dropout})
if step % display_step == 0:
# Calculate batch loss and accuracy
loss, acc = sess.run([cost, accuracy], feed_dict={x: batch_x,
y: batch_y,
keep_prob: 1.})
print("Iter " + str(step*batch_size) + ", Minibatch Loss= " + \
"{:.6f}".format(loss) + ", Training Accuracy= " + \
"{:.5f}".format(acc))
step += 1
print("Optimization Finished!")

# Calculate accuracy for 256 mnist test images
print("Testing Accuracy:",
sess.run(accuracy, feed_dict={x: mnist.test.images[:256],
y: mnist.test.labels[:256],
keep_prob: 1.}))

代码运行结果

数据集为MNIST