代碼來源:https://github.com/aymericdamien/TensorFlow-Examples
首先看一下用最基本的矩陣運算來搭建神經網絡解決MNIST分類問題,比如搭建一個兩層的全連接配接網絡。
from __future__ import print_function
# Import MNIST data
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("/tmp/data/", one_hot=True)
import tensorflow as tf
# Parameters
learning_rate = 0.1
num_steps = 500
batch_size = 128
display_step = 100
# Network Parameters
n_hidden_1 = 256 # 1st layer number of neurons
n_hidden_2 = 256 # 2nd layer number of neurons
num_input = 784 # MNIST data input (img shape: 28*28)
num_classes = 10 # MNIST total classes (0-9 digits)
# tf Graph input
X = tf.placeholder("float", [None, num_input])
Y = tf.placeholder("float", [None, num_classes])
這裡設定了一些基本的參數,可以看到第一層和第二層都分别有256個神經元,将28*28的輸入分成0-9的10類數字。
# Store layers weight & bias
weights = {
'h1': tf.Variable(tf.random_normal([num_input, n_hidden_1])),
'h2': tf.Variable(tf.random_normal([n_hidden_1, n_hidden_2])),
'out': tf.Variable(tf.random_normal([n_hidden_2, num_classes]))
}
biases = {
'b1': tf.Variable(tf.random_normal([n_hidden_1])),
'b2': tf.Variable(tf.random_normal([n_hidden_2])),
'out': tf.Variable(tf.random_normal([num_classes]))
}
# Create model
def neural_net(x):
# Hidden fully connected layer with 256 neurons
layer_1 = tf.add(tf.matmul(x, weights['h1']), biases['b1'])
# Hidden fully connected layer with 256 neurons
layer_2 = tf.add(tf.matmul(layer_1, weights['h2']), biases['b2'])
# Output fully connected layer with a neuron for each class
out_layer = tf.matmul(layer_2, weights['out']) + biases['out']
return out_layer
這裡定義了神經網絡,根據weight和biase通過矩陣乘法建立網絡
# Construct model
logits = neural_net(X)
# Define loss and optimizer
loss_op = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(
logits=logits, labels=Y))
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate)
train_op = optimizer.minimize(loss_op)
# Evaluate model (with test logits, for dropout to be disabled)
correct_pred = tf.equal(tf.argmax(logits, 1), tf.argmax(Y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
# Initialize the variables (i.e. assign their default value)
init = tf.global_variables_initializer()
這裡建立了模型,結果為logits。
loss_op表示損失函數,這裡損失函數就是交叉熵。
optimizer用Adam算法進行優化,使損失函數最小。
之後就可以開始訓練了
# Start training
with tf.Session() as sess:
# Run the initializer
sess.run(init)
for step in range(1, num_steps+1):
batch_x, batch_y = mnist.train.next_batch(batch_size)
# Run optimization op (backprop)
sess.run(train_op, feed_dict={X: batch_x, Y: batch_y})
if step % display_step == 0 or step == 1:
# Calculate batch loss and accuracy
loss, acc = sess.run([loss_op, accuracy], feed_dict={X: batch_x,
Y: batch_y})
print("Step " + str(step) + ", Minibatch Loss= " + \
"{:.4f}".format(loss) + ", Training Accuracy= " + \
"{:.3f}".format(acc))
print("Optimization Finished!")
# Calculate accuracy for MNIST test images
print("Testing Accuracy:", \
sess.run(accuracy, feed_dict={X: mnist.test.images,
Y: mnist.test.labels}))
運作結果如下: