mnist
from tensorflow.examples.tutorials.mnist import input_data
import tensorflow as tf
def compute_accuracy(v_x, v_y):
global prediction
#input v_x to nn and get the result with y_pre
y_pre = sess.run(prediction, feed_dict={x:v_x})
#find how many right
correct_prediction = tf.equal(tf.argmax(y_pre,1), tf.argmax(v_y,1))
#calculate average
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
#get input content
result = sess.run(accuracy,feed_dict={x: v_x, y: v_y})
return result
def add_layer(inputs, in_size, out_size, activation_function=None,):
#init w: a matric in x*y
Weights = tf.Variable(tf.random_normal([in_size, out_size]))
#init b: a matric in 1*y
biases = tf.Variable(tf.zeros([1, out_size]) + 0.1,)
#calculate the result
Wx_plus_b = tf.matmul(inputs, Weights) + biases
#add the active hanshu
if activation_function is None:
outputs = Wx_plus_b
else:
outputs = activation_function(Wx_plus_b,)
return outputs
#load mnist data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
#define placeholder for input
x = tf.placeholder(tf.float32, [None, 784])
y = tf.placeholder(tf.float32, [None, 10])
#add layer
prediction = add_layer(x, 784, 10, activation_function=tf.nn.softmax)
#calculate the loss
cross_entropy = tf.reduce_mean(-tf.reduce_sum(y*tf.log(prediction), reduction_indices=[1]))
#use Gradientdescentoptimizer
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)
#init session
sess = tf.Session()
#init all variables
sess.run(tf.global_variables_initializer())
#start training
for i in range(1000):
#get batch to learn easily
batch_x, batch_y = mnist.train.next_batch(100)
res=sess.run(train_step,feed_dict={x: batch_x, y: batch_y})
if i % 10 == 0:
print(res)
if i % 50 == 0:
print(compute_accuracy(mnist.test.images, mnist.test.labels))
mnist_vis_tensorboard
# encoding=utf-8
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
def weight_variable(shape):
initial = tf.truncated_normal(shape, stddev=0.1)
return tf.Variable(initial)
def bias_variable(shape):
initial = tf.constant(0.1, shape=shape)
return tf.Variable(initial)
myGraph = tf.Graph()
with myGraph.as_default():
with tf.name_scope('inputsAndLabels'):
x_raw = tf.placeholder(tf.float32, shape=[None, 784])
y = tf.placeholder(tf.float32, shape=[None, 10])
with tf.name_scope('hidden1'):
x = tf.reshape(x_raw, shape=[-1,28,28,1])
W_conv1 = weight_variable([5,5,1,32])
b_conv1 = bias_variable([32])
l_conv1 = tf.nn.relu(tf.nn.conv2d(x,W_conv1, strides=[1,1,1,1],padding='SAME') + b_conv1)
l_pool1 = tf.nn.max_pool(l_conv1, ksize=[1,2,2,1], strides=[1,2,2,1], padding='SAME')
tf.summary.image('x_input',x,max_outputs=10)
tf.summary.histogram('W_con1',W_conv1)
tf.summary.histogram('b_con1',b_conv1)
with tf.name_scope('hidden2'):
W_conv2 = weight_variable([5,5,32,64])
b_conv2 = bias_variable([64])
l_conv2 = tf.nn.relu(tf.nn.conv2d(l_pool1, W_conv2, strides=[1,1,1,1], padding='SAME')+b_conv2)
l_pool2 = tf.nn.max_pool(l_conv2, ksize=[1,2,2,1],strides=[1,2,2,1], padding='SAME')
tf.summary.histogram('W_con2', W_conv2)
tf.summary.histogram('b_con2', b_conv2)
with tf.name_scope('fc1'):
W_fc1 = weight_variable([64*7*7, 1024])
b_fc1 = bias_variable([1024])
l_pool2_flat = tf.reshape(l_pool2, [-1, 64*7*7])
l_fc1 = tf.nn.relu(tf.matmul(l_pool2_flat, W_fc1) + b_fc1)
keep_prob = tf.placeholder(tf.float32)
l_fc1_drop = tf.nn.dropout(l_fc1, keep_prob)
tf.summary.histogram('W_fc1', W_fc1)
tf.summary.histogram('b_fc1', b_fc1)
with tf.name_scope('fc2'):
W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])
y_conv = tf.matmul(l_fc1_drop, W_fc2) + b_fc2
tf.summary.histogram('W_fc1', W_fc1)
tf.summary.histogram('b_fc1', b_fc1)
with tf.name_scope('train'):
cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=y_conv, labels=y))
train_step = tf.train.AdamOptimizer(learning_rate=1e-4).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
tf.summary.scalar('loss', cross_entropy)
tf.summary.scalar('accuracy', accuracy)
with tf.Session(graph=myGraph) as sess:
sess.run(tf.global_variables_initializer())
saver = tf.train.Saver()
merged = tf.summary.merge_all()
summary_writer = tf.summary.FileWriter('./mnistEven/', graph=sess.graph)
for i in range(2000):
batch = mnist.train.next_batch(50)
#cross_entropy = -tf.reduce_sum(y_ * tf.log(y))
_, loss_val = sess.run([train_step, cross_entropy],feed_dict={x_raw:batch[0], y:batch[1], keep_prob:0.5})
if i%100 == 0:
train_accuracy = accuracy.eval(feed_dict={x_raw:batch[0], y:batch[1], keep_prob:1.0})
print('step %d training accuracy:%g'%(i, train_accuracy))
print('loss = ' + str(loss_val))
summary = sess.run(merged,feed_dict={x_raw:batch[0], y:batch[1], keep_prob:1.0})
summary_writer.add_summary(summary,i)
test_accuracy = accuracy.eval(feed_dict={x_raw:mnist.test.images, y:mnist.test.labels, keep_prob:1.0})
print('test accuracy:%g' %test_accuracy)
saver.save(sess,save_path='./model/mnistmodel',global_step=1)
mnist_nlstm
from tensorflow.examples.tutorials.mnist import input_data
import tensorflow as tf
def compute_accuracy(v_x, v_y):
global pred
#input v_x to nn and get the result with y_pre
y_pre = sess.run(pred, feed_dict={x:v_x})
#find how many right
correct_prediction = tf.equal(tf.argmax(y_pre,1), tf.argmax(v_y,1))
#calculate average
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
#get input content
result = sess.run(accuracy,feed_dict={x: v_x, y: v_y})
return result
def LSTM_cell():
return tf.contrib.rnn.BasicLSTMCell(n_hidden_units, forget_bias=1.0, state_is_tuple=True)
def Drop_lstm_cell():
return tf.contrib.rnn.DropoutWrapper(LSTM_cell(), output_keep_prob=0.5)
def Mul_lstm_cell():
return tf.contrib.rnn.MultiRNNCell([Drop_lstm_cell() for _ in range(lstm_layer)], state_is_tuple=True)
def RNN(X,weights,biases):
# hidden layer for input
X = tf.reshape(X, [-1, n_inputs])
X_in = tf.matmul(X, weights['in']) + biases['in']
X_in = tf.reshape(X_in, [-1,n_steps, n_hidden_units])
# cell
#lstm_cell = tf.contrib.rnn.BasicLSTMCell(n_hidden_units, forget_bias=1.0, state_is_tuple=True)
lstm_cell = Mul_lstm_cell()
_init_state = lstm_cell.zero_state(batch_size, dtype=tf.float32)
outputs,states = tf.nn.dynamic_rnn(lstm_cell, X_in, initial_state=_init_state, time_major=False)
#hidden layer for output as the final results
#results = tf.matmul(states[2][1], weights['out']) + biases['out']
# or
outputs = tf.unstack(tf.transpose(outputs, [1,0,2]))
results = tf.matmul(outputs[-1], weights['out']) + biases['out']
return results
#load mnist data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
# parameters init
lstm_layer = 3
l_r = 0.001
training_iters = 100000
batch_size = 128
n_inputs = 28
n_steps = 28
n_hidden_units = 128
n_classes = 10
#define placeholder for input
x = tf.placeholder(tf.float32, [None, n_steps, n_inputs])
y = tf.placeholder(tf.float32, [None, n_classes])
# define w and b
weights = {
'in': tf.Variable(tf.random_normal([n_inputs,n_hidden_units])),
'out': tf.Variable(tf.random_normal([n_hidden_units,n_classes]))
}
biases = {
'in': tf.Variable(tf.constant(0.1,shape=[n_hidden_units,])),
'out': tf.Variable(tf.constant(0.1,shape=[n_classes,]))
}
pred = RNN(x, weights, biases)
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=pred,labels=y))
train_op = tf.train.AdamOptimizer(l_r).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 session
sess = tf.Session()
#init all variables
sess.run(tf.global_variables_initializer())
#start training
# x_image,x_label = mnist.test.next_batch(500)
# x_image = x_image.reshape([500, n_steps, n_inputs])
for i in range(training_iters):
#get batch to learn easily
batch_x, batch_y = mnist.train.next_batch(batch_size)
batch_x = batch_x.reshape([batch_size, n_steps, n_inputs])
sess.run(train_op,feed_dict={x: batch_x, y: batch_y})
if i % 50 == 0:
print(sess.run(accuracy,feed_dict={x: batch_x, y: batch_y,}))
# print(sess.run(accuracy,feed_dict={x: x_image, y: x_label}))
mnist_lstm
from tensorflow.examples.tutorials.mnist import input_data
import tensorflow as tf
def RNN(X,weights,biases):
# hidden layer for input
X = tf.reshape(X, [-1, n_inputs])
X_in = tf.matmul(X, weights['in']) + biases['in']
X_in = tf.reshape(X_in, [-1,n_steps, n_hidden_units])
# cell
lstm_cell = tf.contrib.rnn.BasicLSTMCell(n_hidden_units, forget_bias=1.0, state_is_tuple=True)
_init_state = lstm_cell.zero_state(batch_size, dtype=tf.float32)
outputs,states = tf.nn.dynamic_rnn(lstm_cell, X_in, initial_state=_init_state, time_major=False)
#hidden layer for output as the final results
#results = tf.matmul(states[1], weights['out']) + biases['out']
# or
outputs = tf.unstack(tf.transpose(outputs, [1,0,2]))
results = tf.matmul(outputs[-1], weights['out']) + biases['out']
return results
#load mnist data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
# parameters init
l_r = 0.001
training_iters = 100000
batch_size = 128
n_inputs = 28
n_steps = 28
n_hidden_units = 128
n_classes = 10
#define placeholder for input
x = tf.placeholder(tf.float32, [None, n_steps, n_inputs])
y = tf.placeholder(tf.float32, [None, n_classes])
# define w and b
weights = {
'in': tf.Variable(tf.random_normal([n_inputs,n_hidden_units])),
'out': tf.Variable(tf.random_normal([n_hidden_units,n_classes]))
}
biases = {
'in': tf.Variable(tf.constant(0.1,shape=[n_hidden_units,])),
'out': tf.Variable(tf.constant(0.1,shape=[n_classes,]))
}
pred = RNN(x, weights, biases)
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=pred,labels=y))
train_op = tf.train.AdamOptimizer(l_r).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 session
sess = tf.Session()
#init all variables
sess.run(tf.global_variables_initializer())
#start training
#for i in range(training_iters):
for i in range(training_iters):
#get batch to learn easily
batch_x, batch_y = mnist.train.next_batch(batch_size)
batch_x = batch_x.reshape([batch_size, n_steps, n_inputs])
sess.run(train_op,feed_dict={x: batch_x, y: batch_y})
if i % 50 == 0:
print(sess.run(accuracy,feed_dict={x: batch_x, y: batch_y,}))
#test_data = mnist.test.images.reshape([-1, n_steps, n_inputs])
#test_label = mnist.test.labels
#print("Testing Accuracy: ", sess.run(accuracy, feed_dict={x: test_data, y: test_label}))
mnist_cnn
from tensorflow.examples.tutorials.mnist import input_data
import tensorflow as tf
def compute_accuracy(v_x, v_y):
global prediction
y_pre = sess.run(prediction, feed_dict={x:v_x, keep_prob:1})
correct_prediction = tf.equal(tf.argmax(y_pre,1), tf.argmax(v_y,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
result = sess.run(accuracy,feed_dict={x: v_x, y: v_y, keep_prob:1})
return result
def weight_variable(shape):
initial = tf.truncated_normal(shape, stddev=0.1)
return tf.Variable(initial)
def bias_variable(shape):
initial = tf.constant(0.1, shape=shape)
return tf.Variable(initial)
def conv2d(x, W):
# strides=[1,x_movement,y_movement,1]
return tf.nn.conv2d(x, W, strides=[1,1,1,1], padding='SAME')
def max_pool_2x2(x):
return tf.nn.max_pool(x, ksize=[1,2,2,1], strides=[1,2,2,1], padding='SAME')
# load mnist data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
x = tf.placeholder(tf.float32, [None,784])
y = tf.placeholder(tf.float32, [None,10])
keep_prob = tf.placeholder(tf.float32)
# reshape(data you want to reshape, [-1, reshape_height, reshape_weight, imagine layers]) image layers=1 when the imagine is in white and black, =3 when the imagine is RGB
x_image = tf.reshape(x, [-1,28,28,1])
# ********************** conv1 *********************************
# transfer a 5*5*1 imagine into 32 sequence
W_conv1 = weight_variable([5,5,1,32])
b_conv1 = bias_variable([32])
# input a imagine and make a 5*5*1 to 32 with stride=1*1, and activate with relu
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1) # output size 28*28*32
h_pool1 = max_pool_2x2(h_conv1) # output size 14*14*32
# ********************** conv2 *********************************
# transfer a 5*5*32 imagine into 64 sequence
W_conv2 = weight_variable([5,5,32,64])
b_conv2 = bias_variable([64])
# input a imagine and make a 5*5*32 to 64 with stride=1*1, and activate with relu
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2) # output size 14*14*64
h_pool2 = max_pool_2x2(h_conv2) # output size 7*7*64
# ********************* func1 layer *********************************
W_fc1 = weight_variable([7*7*64, 1024])
b_fc1 = bias_variable([1024])
# reshape the image from 7,7,64 into a flat (7*7*64)
h_pool2_flat = tf.reshape(h_pool2, [-1,7*7*64])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
h_fc1_drop = tf.nn.dropout(h_fc1,keep_prob)
# ********************* func2 layer *********************************
W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])
prediction = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)
# calculate the loss
cross_entropy = tf.reduce_mean(-tf.reduce_sum(y*tf.log(prediction), reduction_indices=[1]))
# use Gradientdescentoptimizer
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
# init session
sess = tf.Session()
sess.run(tf.global_variables_initializer())
for i in range(1000):
batch_x, batch_y = mnist.train.next_batch(100)
sess.run(train_step,feed_dict={x: batch_x, y: batch_y, keep_prob: 0.5})
if i % 50 == 0:
print(compute_accuracy(mnist.test.images, mnist.test.labels))
mnist_cnn_rnn
from tensorflow.examples.tutorials.mnist import input_data
import tensorflow as tf
lr = 0.001
training_iters = 100000
batch_size = 128
n_input = 49
n_steps = 64
n_hidden_units = 128
n_classes = 10
def compute_accuracy(v_x, v_y):
global prediction
y_pre = sess.run(prediction, feed_dict={x:v_x, keep_prob:1})
correct_prediction = tf.equal(tf.argmax(y_pre,1), tf.argmax(v_y,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
result = sess.run(accuracy,feed_dict={x: v_x, y: v_y, keep_prob:1})
return result
def weight_variable(shape):
initial = tf.truncated_normal(shape, stddev=0.1)
return tf.Variable(initial)
def bias_variable(shape):
initial = tf.constant(0.1, shape=shape)
return tf.Variable(initial)
def conv2d(x, W):
# strides=[1,x_movement,y_movement,1]
return tf.nn.conv2d(x, W, strides=[1,1,1,1], padding='SAME')
def max_pool_2x2(x):
return tf.nn.max_pool(x, ksize=[1,2,2,1], strides=[1,2,2,1], padding='SAME')
def conv_pool_layer(X, img_len, img_hi, out_seq):
W = weight_variable([img_len, img_len, img_hi, out_seq])
b = bias_variable([out_seq])
h_conv = tf.nn.relu(conv2d(X, W) + b)
return max_pool_2x2(h_conv)
def lstm(X):
lstm_cell = tf.contrib.rnn.BasicLSTMCell(n_hidden_units, forget_bias=1.0, state_is_tuple=True)
_init_state = lstm_cell.zero_state(batch_size, dtype=tf.float32)
outputs,states = tf.nn.dynamic_rnn(lstm_cell, X, initial_state=_init_state, time_major=False)
W = weight_variable([n_hidden_units, n_classes])
b = bias_variable([n_classes])
outputs = tf.unstack(tf.transpose(outputs, [1,0,2]))
results = tf.matmul(outputs[-1], W) + b
return results
# load mnist data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
x = tf.placeholder(tf.float32, [None,784])
y = tf.placeholder(tf.float32, [None,10])
keep_prob = tf.placeholder(tf.float32)
# reshape(data you want to reshape, [-1, reshape_height, reshape_weight, imagine layers]) image layers=1 when the imagine is in white and black, =3 when the imagine is RGB
x_image = tf.reshape(x, [-1,28,28,1])
# ********************** conv1 *********************************
# transfer a 5*5*1 imagine into 32 sequence
#W_conv1 = weight_variable([5,5,1,32])
#b_conv1 = bias_variable([32])
# input a imagine and make a 5*5*1 to 32 with stride=1*1, and activate with relu
#h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1) # output size 28*28*32
#h_pool1 = max_pool_2x2(h_conv1) # output size 14*14*32
h_pool1 = conv_pool_layer(x_image, 5, 1, 32)
# ********************** conv2 *********************************
# transfer a 5*5*32 imagine into 64 sequence
#W_conv2 = weight_variable([5,5,32,64])
#b_conv2 = bias_variable([64])
# input a imagine and make a 5*5*32 to 64 with stride=1*1, and activate with relu
#h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2) # output size 14*14*64
#h_pool2 = max_pool_2x2(h_conv2) # output size 7*7*64
h_pool2 = conv_pool_layer(h_pool1, 5, 32, 64)
# reshape data
X_in = tf.reshape(h_pool2, [-1,49,64])
X_in = tf.transpose(X_in, [0,2,1])
#put into a lstm layer
prediction = lstm(X_in)
# ********************* func1 layer *********************************
#W_fc1 = weight_variable([7*7*64, 1024])
#b_fc1 = bias_variable([1024])
# reshape the image from 7,7,64 into a flat (7*7*64)
#h_pool2_flat = tf.reshape(h_pool2, [-1,7*7*64])
#h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
#h_fc1_drop = tf.nn.dropout(h_fc1,keep_prob)
# ********************* func2 layer *********************************
#W_fc2 = weight_variable([1024, 10])
#b_fc2 = bias_variable([10])
#prediction = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)
# calculate the loss
cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=prediction, labels=y))
# use Gradientdescentoptimizer
train_step = tf.train.AdamOptimizer(lr).minimize(cross_entropy)
correct_pred = tf.equal(tf.argmax(prediction,1),tf.argmax(y,1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
# init session
sess = tf.Session()
sess.run(tf.global_variables_initializer())
for i in range(training_iters):
batch_x, batch_y = mnist.train.next_batch(batch_size)
sess.run(train_step,feed_dict={x: batch_x, y: batch_y, keep_prob: 0.5})
if i % 50 == 0:
print(sess.run(accuracy,feed_dict={x: batch_x, y: batch_y,}))
mnist_bi_lstm
from tensorflow.examples.tutorials.mnist import input_data
import tensorflow as tf
def compute_accuracy(v_x, v_y):
global pred
#input v_x to nn and get the result with y_pre
y_pre = sess.run(pred, feed_dict={x:v_x})
#find how many right
correct_prediction = tf.equal(tf.argmax(y_pre,1), tf.argmax(v_y,1))
#calculate average
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
#get input content
result = sess.run(accuracy,feed_dict={x: v_x, y: v_y})
return result
def Bi_lstm(X):
lstm_f_cell = tf.contrib.rnn.BasicLSTMCell(n_hidden_units, forget_bias=1.0, state_is_tuple=True)
lstm_b_cell = tf.contrib.rnn.BasicLSTMCell(n_hidden_units, forget_bias=1.0, state_is_tuple=True)
return tf.contrib.rnn.static_bidirectional_rnn(lstm_f_cell, lstm_b_cell, X, dtype=tf.float32)
def RNN(X,weights,biases):
# hidden layer for input
X = tf.reshape(X, [-1, n_inputs])
X_in = tf.matmul(X, weights['in']) + biases['in']
#reshape data put into bi-lstm cell
X_in = tf.reshape(X_in, [-1,n_steps, n_hidden_units])
X_in = tf.transpose(X_in, [1,0,2])
X_in = tf.reshape(X_in, [-1, n_hidden_units])
X_in = tf.split(X_in, n_steps)
outputs, _, _ = Bi_lstm(X_in)
#hidden layer for output as the final results
results = tf.matmul(outputs[-1], weights['out']) + biases['out']
return results
#load mnist data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
# parameters init
l_r = 0.001
training_iters = 100000
batch_size = 128
n_inputs = 28
n_steps = 28
n_hidden_units = 128
n_classes = 10
#define placeholder for input
x = tf.placeholder(tf.float32, [None, n_steps, n_inputs])
y = tf.placeholder(tf.float32, [None, n_classes])
# define w and b
weights = {
'in': tf.Variable(tf.random_normal([n_inputs,n_hidden_units])),
'out': tf.Variable(tf.random_normal([2*n_hidden_units,n_classes]))
}
biases = {
'in': tf.Variable(tf.constant(0.1,shape=[n_hidden_units,])),
'out': tf.Variable(tf.constant(0.1,shape=[n_classes,]))
}
pred = RNN(x, weights, biases)
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=pred,labels=y))
train_op = tf.train.AdamOptimizer(l_r).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 session
sess = tf.Session()
#init all variables
sess.run(tf.global_variables_initializer())
#start training
# x_image,x_label = mnist.test.next_batch(500)
# x_image = x_image.reshape([500, n_steps, n_inputs])
for i in range(500):
#get batch to learn easily
batch_x, batch_y = mnist.train.next_batch(batch_size)
batch_x = batch_x.reshape([batch_size, n_steps, n_inputs])
sess.run(train_op,feed_dict={x: batch_x, y: batch_y})
if i % 50 == 0:
print(sess.run(accuracy,feed_dict={x: batch_x, y: batch_y,}))
test_data = mnist.test.images.reshape([-1, n_steps, n_inputs])
test_label = mnist.test.labels
#print("Testing Accuracy:", sess.run(accuracy, feed_dict={x: test_data, y: test_label}))
print("Testing Accuracy: ", compute_accuracy(test_data, test_label))
mnist.ipynb
# encoding=utf-8
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
def weight_variable(shape):
initial = tf.truncated_normal(shape, stddev=0.1)
return tf.Variable(initial)
def bias_variable(shape):
initial = tf.constant(0.1, shape=shape)
return tf.Variable(initial)
myGraph = tf.Graph()
with myGraph.as_default():
with tf.name_scope('inputsAndLabels'):
x_raw = tf.placeholder(tf.float32, shape=[None, 784])
y = tf.placeholder(tf.float32, shape=[None, 10])
with tf.name_scope('hidden1'):
x = tf.reshape(x_raw, shape=[-1,28,28,1])
W_conv1 = weight_variable([5,5,1,32])
b_conv1 = bias_variable([32])
l_conv1 = tf.nn.relu(tf.nn.conv2d(x,W_conv1, strides=[1,1,1,1],padding='SAME') + b_conv1)
l_pool1 = tf.nn.max_pool(l_conv1, ksize=[1,2,2,1], strides=[1,2,2,1], padding='SAME')
tf.summary.image('x_input',x,max_outputs=10)
tf.summary.histogram('W_con1',W_conv1)
tf.summary.histogram('b_con1',b_conv1)
with tf.name_scope('hidden2'):
W_conv2 = weight_variable([5,5,32,64])
b_conv2 = bias_variable([64])
l_conv2 = tf.nn.relu(tf.nn.conv2d(l_pool1, W_conv2, strides=[1,1,1,1], padding='SAME')+b_conv2)
l_pool2 = tf.nn.max_pool(l_conv2, ksize=[1,2,2,1],strides=[1,2,2,1], padding='SAME')
tf.summary.histogram('W_con2', W_conv2)
tf.summary.histogram('b_con2', b_conv2)
with tf.name_scope('fc1'):
W_fc1 = weight_variable([64*7*7, 1024])
b_fc1 = bias_variable([1024])
l_pool2_flat = tf.reshape(l_pool2, [-1, 64*7*7])
l_fc1 = tf.nn.relu(tf.matmul(l_pool2_flat, W_fc1) + b_fc1)
keep_prob = tf.placeholder(tf.float32)
l_fc1_drop = tf.nn.dropout(l_fc1, keep_prob)
tf.summary.histogram('W_fc1', W_fc1)
tf.summary.histogram('b_fc1', b_fc1)
with tf.name_scope('fc2'):
W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])
y_conv = tf.matmul(l_fc1_drop, W_fc2) + b_fc2
tf.summary.histogram('W_fc1', W_fc1)
tf.summary.histogram('b_fc1', b_fc1)
with tf.name_scope('train'):
cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=y_conv, labels=y))
train_step = tf.train.AdamOptimizer(learning_rate=1e-4).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
tf.summary.scalar('loss', cross_entropy)
tf.summary.scalar('accuracy', accuracy)
with tf.Session(graph=myGraph) as sess:
sess.run(tf.global_variables_initializer())
saver = tf.train.Saver()
merged = tf.summary.merge_all()
summary_writer = tf.summary.FileWriter('./mnistEven/', graph=sess.graph)
for i in range(10001):
batch = mnist.train.next_batch(50)
sess.run(train_step,feed_dict={x_raw:batch[0], y:batch[1], keep_prob:0.5})
if i%100 == 0:
train_accuracy = accuracy.eval(feed_dict={x_raw:batch[0], y:batch[1], keep_prob:1.0})
print('step %d training accuracy:%g'%(i, train_accuracy))
summary = sess.run(merged,feed_dict={x_raw:batch[0], y:batch[1], keep_prob:1.0})
summary_writer.add_summary(summary,i)
test_accuracy = accuracy.eval(feed_dict={x_raw:mnist.test.images, y:mnist.test.labels, keep_prob:1.0})
print('test accuracy:%g' %test_accuracy)
saver.save(sess,save_path='./model/mnistmodel',global_step=1)
转自:https://www.cnblogs.com/hugeng007/p/9489636.html