DNN深度神经网络 的原理 以及 使用

DNN  深度神经网络，就是 把原有的多层神经网络 扩展到深度学习里面，加上了BP 反馈，是的整理上 loss 收敛 直至不变，同时也有dropout 前面 有很多这个词 出现，dropout 是指 随机用一定概率 把一些 节点失效，进行参与训练 放置数据整理上陷入overfitting 局部最优解。

DNN ,就是去掉C 之后  使用全连接层+dropout下降+relu激活  一层一层的WX+B的 网络模式。

import input_data
mnist = input_data.read_data_sets("/tmp/data/", one_hot=True)
import tensorflow as tf
 
# Parameters
learning_rate = 0.001
training_iters = 100000
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

x = tf.placeholder(tf.float32, [None, n_input])
y = tf.placeholder(tf.float32, [None, n_classes])
keep_prob = tf.placeholder(tf.float32)

def conv2d(img, w, b):
    return tf.nn.relu(tf.nn.bias_add(tf.nn.conv2d(img, w, strides=[1, 1, 1, 1], padding='SAME'),b))
 
def max_pool(img, k):
    return tf.nn.max_pool(img, ksize=[1, k, k, 1], strides=[1, k, k, 1], padding='SAME')
 
def conv_net(_X, _weights, _biases, _dropout):
    # Reshape input picture
    _X = tf.reshape(_X, shape=[-1, 28, 28, 1])
 
    # Convolution Layer
    conv1 = conv2d(_X, _weights['wc1'], _biases['bc1'])
    # Max Pooling (down-sampling)
    conv1 = max_pool(conv1, k=2)
    # Apply Dropout
    conv1 = tf.nn.dropout(conv1, _dropout)
 
    # Convolution Layer
    conv2 = conv2d(conv1, _weights['wc2'], _biases['bc2'])
    # Max Pooling (down-sampling)
    conv2 = max_pool(conv2, k=2)
    # Apply Dropout
    conv2 = tf.nn.dropout(conv2, _dropout)
 
    # Fully connected layer
    dense1 = tf.reshape(conv2, [-1, _weights['wd1'].get_shape().as_list()[0]]) # Reshape conv2 output to fit dense layer input
    dense1 = tf.nn.relu(tf.add(tf.matmul(dense1, _weights['wd1']), _biases['bd1'])) # Relu activation
    dense1 = tf.nn.dropout(dense1, _dropout) # Apply Dropout
 
    # Output, class prediction
    out = tf.add(tf.matmul(dense1, _weights['out']), _biases['out'])
    return out
 

weights = {
    'wc1': tf.Variable(tf.random_normal([5, 5, 1, 32])), # 5x5 conv, 1 input, 32 outputs
    'wc2': tf.Variable(tf.random_normal([5, 5, 32, 64])), # 5x5 conv, 32 inputs, 64 outputs
    'wd1': tf.Variable(tf.random_normal([7*7*64, 1024])), # fully connected, 7*7*64 inputs, 1024 outputs
    'out': tf.Variable(tf.random_normal([1024, n_classes])) # 1024 inputs, 10 outputs (class prediction)
}
 
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)

cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(pred, y))
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)

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

init = tf.initialize_all_variables()

with tf.Session() as sess:
    sess.run(init)
    step = 1

    while step * batch_size < training_iters:
        batch_xs, batch_ys = mnist.train.next_batch(batch_size)
        
        sess.run(optimizer, feed_dict={x: batch_xs, y: batch_ys, keep_prob: dropout})
        if step % display_step == 0:
            acc = sess.run(accuracy, feed_dict={x: batch_xs, y: batch_ys, keep_prob: 1.})
            
            loss = sess.run(cost, feed_dict={x: batch_xs, y: batch_ys, keep_prob: 1.})
            print "Iter " + str(step*batch_size) + ", Minibatch Loss= " + "{:.6f}".format(loss) + ", Training Accuracy= " + "{:.5f}".format(acc)
        step += 1
    print "Optimization Finished!"
    print "Testing Accuracy:", sess.run(accuracy, feed_dict={x: mnist.test.images[:256], y: mnist.test.labels[:256], keep_prob: 1.})