1.神经网络
import tensorflow as tf
import numpy as np
import input_data
def init_weights(shape):
return tf.Variable(tf.random_normal(shape, stddev=0.01))
def model(X, w_h, w_o):
h = tf.nn.sigmoid(tf.matmul(X, w_h)) # this is a basic mlp, think 2 stacked logistic regressions
return tf.matmul(h, w_o) # note that we dont take the softmax at the end because our cost fn does that for us
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
trX, trY, teX, teY = mnist.train.images, mnist.train.labels, mnist.test.images, mnist.test.labels
X = tf.placeholder("float", [None, 784])
Y = tf.placeholder("float", [None, 10])
w_h = init_weights([784, 625]) # create symbolic variables ######！！！！！
w_o = init_weights([625, 10])
py_x = model(X, w_h, w_o)
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(py_x, Y)) # compute costs
train_op = tf.train.GradientDescentOptimizer(0.05).minimize(cost) # construct an optimizer
predict_op = tf.argmax(py_x, 1)
# Launch the graph in a session
with tf.Session() as sess:
# you need to initialize all variables
tf.initialize_all_variables().run()
for i in range(100):
for start, end in zip(range(0, len(trX), 128), range(128, len(trX)+1, 128)): ### ？？？ 128
sess.run(train_op, feed_dict={X: trX[start:end], Y: trY[start:end]})
print(i, np.mean(np.argmax(teY, axis=1) == sess.run(predict_op, feed_dict={X: teX})))
2.modern net
import tensorflow as tf
import numpy as np
import input_data
def init_weights(shape):
return tf.Variable(tf.random_normal(shape, stddev=0.01))
def model(X, w_h, w_h2, w_o, p_keep_input, p_keep_hidden): # this network is the same as the previous one except with an extra hidden layer + dropout
X = tf.nn.dropout(X, p_keep_input)
h = tf.nn.relu(tf.matmul(X, w_h)) #应用ReLU激活函数
h = tf.nn.dropout(h, p_keep_hidden)
h2 = tf.nn.relu(tf.matmul(h, w_h2))
h2 = tf.nn.dropout(h2, p_keep_hidden)
return tf.matmul(h2, w_o)
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
trX, trY, teX, teY = mnist.train.images, mnist.train.labels, mnist.test.images, mnist.test.labels
X = tf.placeholder("float", [None, 784])
Y = tf.placeholder("float", [None, 10])
w_h = init_weights([784, 625])
w_h2 = init_weights([625, 625])
w_o = init_weights([625, 10])
p_keep_input = tf.placeholder("float")
p_keep_hidden = tf.placeholder("float")
py_x = model(X, w_h, w_h2, w_o, p_keep_input, p_keep_hidden)
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(py_x, Y))
train_op = tf.train.RMSPropOptimizer(0.001, 0.9).minimize(cost)
predict_op = tf.argmax(py_x, 1)
# Launch the graph in a session
with tf.Session() as sess:
# you need to initialize all variables
tf.initialize_all_variables().run()
for i in range(100):
for start, end in zip(range(0, len(trX), 128), range(128, len(trX)+1, 128)):
sess.run(train_op, feed_dict={X: trX[start:end], Y: trY[start:end],
p_keep_input: 0.8, p_keep_hidden: 0.5})
print(i, np.mean(np.argmax(teY, axis=1) ==
sess.run(predict_op, feed_dict={X: teX,
p_keep_input: 1.0,p_keep_hidden: 1.0})))
3.多层感知机
# 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 = 0.001
training_epochs = 15
batch_size = 100
display_step = 1
# Network Parameters
n_hidden_1 = 256 # 1st layer number of features
n_hidden_2 = 256 # 2nd layer number of features
n_input = 784 # MNIST data input (img shape: 28*28)
n_classes = 10 # MNIST total classes (0-9 digits)
# tf Graph input
x = tf.placeholder("float", [None, n_input])
y = tf.placeholder("float", [None, n_classes])
# Create model
def multilayer_perceptron(x, weights, biases):
# Hidden layer with RELU activation
layer_1 = tf.add(tf.matmul(x, weights['h1']), biases['b1'])
layer_1 = tf.nn.relu(layer_1)
# Hidden layer with RELU activation
layer_2 = tf.add(tf.matmul(layer_1, weights['h2']), biases['b2'])
layer_2 = tf.nn.relu(layer_2)
# Output layer with linear activation
out_layer = tf.matmul(layer_2, weights['out']) + biases['out']
return out_layer
# Store layers weight & bias
weights = {
'h1': tf.Variable(tf.random_normal([n_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, n_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([n_classes]))
}
# Construct model
pred = multilayer_perceptron(x, weights, biases)
# Define loss and optimizer
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(pred, y))
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)
# Initializing the variables
init = tf.initialize_all_variables()
# Launch the graph
with tf.Session() as sess:
sess.run(init)
# Training cycle
for epoch in range(training_epochs):
avg_cost = 0.
total_batch = int(mnist.train.num_examples/batch_size)
# Loop over all batches
for i in range(total_batch):
batch_x, batch_y = mnist.train.next_batch(batch_size)
# Run optimization op (backprop) and cost op (to get loss value)
_, c = sess.run([optimizer, cost], feed_dict={x: batch_x,
y: batch_y})
# Compute average loss
avg_cost += c / total_batch
# Display logs per epoch step
if epoch % display_step == 0:
print("Epoch:", 'd' % (epoch+1), "cost=", \
"{:.9f}".format(avg_cost))
print("Optimization Finished!")
# Test model
correct_prediction = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))
# Calculate accuracy
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
print("Accuracy:", accuracy.eval({x: mnist.test.images, y: mnist.test.labels}))
