from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
with tf.variable_scope('Placeholder'):
x = tf.placeholder("float", name='X_placeholder', shape=[None, 784])
y_ = tf.placeholder("float", name='y_placeholder', shape=[None, 10])
x_image = tf.reshape(x, [-1,28,28,1])
with tf.variable_scope('conv1') as scope:
W_conv1 = tf.get_variable('W_conv1', shape=[5, 5, 1, 32],
initializer=tf.random_normal_initializer(stddev=0.1))
b_conv1 = tf.get_variable('b_conv1', shape=[32], initializer=tf.constant_initializer(0.1))
conv1 = tf.nn.conv2d(x_image, W_conv1, strides=[1, 1, 1, 1], padding="SAME")
pre_activation = tf.nn.bias_add(conv1, b_conv1)
activation = tf.nn.relu(pre_activation, name=scope.name)
with tf.variable_scope('pool1') as scope:
pool1 = tf.nn.max_pool(activation, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding="SAME",
name=scope.name)
with tf.variable_scope('conv2') as scope:
W_conv2 = tf.get_variable('W_conv2', shape=[5, 5, 32, 64],
initializer=tf.random_normal_initializer(stddev=0.1))
b_conv2 = tf.get_variable('b_conv2', shape=[64], initializer=tf.constant_initializer(0.1))
conv2 = tf.nn.conv2d(pool1, W_conv2, strides=[1, 1, 1, 1], padding="SAME")
pre_activation = tf.nn.bias_add(conv2, b_conv2)
activation = tf.nn.relu(pre_activation, name=scope.name)
with tf.variable_scope('pool2') as scope:
pool2 = tf.nn.max_pool(activation, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding="SAME",
name=scope.name)
with tf.variable_scope('fc1') as scope:
W_fc1 = tf.get_variable("W_fc1", shape=[7 * 7 * 64, 1024],
initializer=tf.truncated_normal_initializer(stddev=0.1))
b_fc1 = tf.get_variable("b_fc1", shape=[1024], initializer=tf.constant_initializer(0.1))
pool2_falt = tf.reshape(pool2, [-1, 7*7*64])
fc1 = tf.matmul(pool2_falt, W_fc1) + b_fc1
activation = tf.nn.relu(fc1, name=scope.name)
drop_fc1 = tf.nn.dropout(activation, keep_prob=0.5)
with tf.variable_scope('softmax') as scope:
W_softmax = tf.get_variable("W_softmax", shape= [1024, 10],
initializer=tf.truncated_normal_initializer(stddev=0.1))
b_softmax = tf.get_variable("b_softmax", shape=[10], initializer=tf.constant_initializer(0.1))
y_conv=tf.nn.softmax(tf.matmul(drop_fc1, W_softmax) + b_softmax, name=scope.name)
with tf.variable_scope('Loss'):
cross_entropy = -tf.reduce_sum(y_*tf.log(y_conv))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
with tf.variable_scope('Accuracy'):
correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
with tf.Session() as sess:
sess.run(tf.initialize_all_variables())
for i in range(20000):
batch = mnist.train.next_batch(50)
if i%100 == 0:
train_accuracy = accuracy.eval(feed_dict={x:batch[0], y_: batch[1]})
print("step %d, training accuracy %g"%(i, train_accuracy))
train_step.run(feed_dict={x: batch[0], y_: batch[1]})
print("test accuracy %g"%accuracy.eval(feed_dict={x: mnist.test.images, y_: mnist.test.labels}))
saver = tf.train.Saver()
last_chkp = saver.save(sess, 'results/graph.chkp')
#sv.saver.save(sess, 'results/graph.chkp')
saver = tf.train.Saver()
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
saver.restore(sess, 'results/graph.chkp')
prediction=tf.argmax(y_conv,1)
predint=prediction.eval(feed_dict={x: [image_arr]}, session=sess)
print('recognize result:')
print(predint[0])
def get_one_image(img_dir):
image = Image.open(img_dir).convert('L')
print(image.mode)
# plt.imshow(image)
im = image.resize([28, 28])
#image_arr = np.array(image)
tv = list(im.getdata())
tva = [(255-x)*1.0/255.0 for x in tv]
return tva
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
import tensorflow as tf
with tf.variable_scope('Placeholder'):
x = tf.placeholder("float", name='X_placeholder', shape=[None, 784])
y_ = tf.placeholder("float", name='y_placeholder', shape=[None, 10])
x_image = tf.reshape(x, [-1,28,28,1])
with tf.variable_scope('conv1') as scope:
W_conv1 = tf.get_variable('W_conv1', shape=[5, 5, 1, 32],
initializer=tf.random_normal_initializer(stddev=0.1))
b_conv1 = tf.get_variable('b_conv1', shape=[32], initializer=tf.constant_initializer(0.1))
conv1 = tf.nn.conv2d(x_image, W_conv1, strides=[1, 1, 1, 1], padding="SAME")
pre_activation = tf.nn.bias_add(conv1, b_conv1)
activation = tf.nn.relu(pre_activation, name=scope.name)
with tf.variable_scope('pool1') as scope:
pool1 = tf.nn.max_pool(activation, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding="SAME",
name=scope.name)
with tf.variable_scope('conv2') as scope:
W_conv2 = tf.get_variable('W_conv2', shape=[5, 5, 32, 64],
initializer=tf.random_normal_initializer(stddev=0.1))
b_conv2 = tf.get_variable('b_conv2', shape=[64], initializer=tf.constant_initializer(0.1))
conv2 = tf.nn.conv2d(pool1, W_conv2, strides=[1, 1, 1, 1], padding="SAME")
pre_activation = tf.nn.bias_add(conv2, b_conv2)
activation = tf.nn.relu(pre_activation, name=scope.name)
with tf.variable_scope('pool2') as scope:
pool2 = tf.nn.max_pool(activation, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding="SAME",
name=scope.name)
with tf.variable_scope('fc1') as scope:
W_fc1 = tf.get_variable("W_fc1", shape=[7 * 7 * 64, 1024],
initializer=tf.truncated_normal_initializer(stddev=0.1))
b_fc1 = tf.get_variable("b_fc1", shape=[1024], initializer=tf.constant_initializer(0.1))
pool2_falt = tf.reshape(pool2, [-1, 7*7*64])
fc1 = tf.matmul(pool2_falt, W_fc1) + b_fc1
activation = tf.nn.relu(fc1, name=scope.name)
drop_fc1 = tf.nn.dropout(activation, keep_prob=0.5)
with tf.variable_scope('softmax') as scope:
W_softmax = tf.get_variable("W_softmax", shape= [1024, 10],
initializer=tf.truncated_normal_initializer(stddev=0.1))
b_softmax = tf.get_variable("b_softmax", shape=[10], initializer=tf.constant_initializer(0.1))
y_conv=tf.nn.softmax(tf.matmul(drop_fc1, W_softmax) + b_softmax, name=scope.name)
with tf.variable_scope('Loss'):
cross_entropy = -tf.reduce_sum(y_*tf.log(y_conv))
with tf.variable_scope('Accuracy'):
correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
with tf.Session() as sess:
sess.run(tf.initialize_all_variables())
for i in range(20000):
batch = mnist.train.next_batch(50)
if i%100 == 0:
train_accuracy = accuracy.eval(feed_dict={x:batch[0], y_: batch[1]})
print("step %d, training accuracy %g"%(i, train_accuracy))
train_step.run(feed_dict={x: batch[0], y_: batch[1]})
print("test accuracy %g"%accuracy.eval(feed_dict={x: mnist.test.images, y_: mnist.test.labels}))
saver = tf.train.Saver()
last_chkp = saver.save(sess, 'results/graph.chkp')
#sv.saver.save(sess, 'results/graph.chkp')
for op in tf.get_default_graph().get_operations():
print(op.name)
import tensorflow as tf
from PIL import Image
def get_one_image(img_dir):
image = Image.open(img_dir).convert('L')
print(image.mode)
# plt.imshow(image)
im = image.resize([28, 28])
#image_arr = np.array(image)
tv = list(im.getdata())
tva = [(255-x)*1.0/255.0 for x in tv]
return tva
with tf.variable_scope('Placeholder'):
x = tf.placeholder("float", name='X_placeholder', shape=[None, 784])
y_ = tf.placeholder("float", name='y_placeholder', shape=[None, 10])
x_image = tf.reshape(x, [-1,28,28,1])
with tf.variable_scope('conv1') as scope:
W_conv1 = tf.get_variable('W_conv1', shape=[5, 5, 1, 32], initializer=tf.random_normal_initializer(stddev=0.1))
b_conv1 = tf.get_variable('b_conv1', shape=[32], initializer=tf.constant_initializer(0.1))
conv1 = tf.nn.conv2d(x_image, W_conv1, strides=[1, 1, 1, 1], padding="SAME")
pre_activation = tf.nn.bias_add(conv1, b_conv1)
activation = tf.nn.relu(pre_activation, name=scope.name)
with tf.variable_scope('pool1') as scope:
pool1 = tf.nn.max_pool(activation, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding="SAME", name=scope.name)
with tf.variable_scope('conv2') as scope:
W_conv2 = tf.get_variable('W_conv2', shape=[5, 5, 32, 64], initializer=tf.random_normal_initializer(stddev=0.1))
b_conv2 = tf.get_variable('b_conv2', shape=[64], initializer=tf.constant_initializer(0.1))
conv2 = tf.nn.conv2d(pool1, W_conv2, strides=[1, 1, 1, 1], padding="SAME")
pre_activation = tf.nn.bias_add(conv2, b_conv2)
activation = tf.nn.relu(pre_activation, name=scope.name)
with tf.variable_scope('pool2') as scope:
pool2 = tf.nn.max_pool(activation, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding="SAME", name=scope.name)
with tf.variable_scope('fc1') as scope:
W_fc1 = tf.get_variable("W_fc1", shape=[7 * 7 * 64, 1024], initializer=tf.truncated_normal_initializer(stddev=0.1))
b_fc1 = tf.get_variable("b_fc1", shape=[1024], initializer=tf.constant_initializer(0.1))
pool2_falt = tf.reshape(pool2, [-1, 7*7*64])
fc1 = tf.matmul(pool2_falt, W_fc1) + b_fc1
activation = tf.nn.relu(fc1, name=scope.name)
drop_fc1 = tf.nn.dropout(activation, keep_prob=0.5)
with tf.variable_scope('softmax') as scope:
W_softmax = tf.get_variable("W_softmax", shape= [1024, 10], initializer=tf.truncated_normal_initializer(stddev=0.1))
b_softmax = tf.get_variable("b_softmax", shape=[10], initializer=tf.constant_initializer(0.1))
y_conv=tf.nn.softmax(tf.matmul(drop_fc1, W_softmax) + b_softmax, name=scope.name)
test_file = '/root/my_bp/mnist-test/2.bmp'
image_arr = get_one_image(test_file)
saver = tf.train.Saver()
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
saver.restore(sess, 'results/graph.chkp')
prediction=tf.argmax(y_conv,1)
predint=prediction.eval(feed_dict={x: [image_arr]}, session=sess)
print('recognize result:')
print(predint[0])
import tensorflow as tf
from PIL import Image
def get_one_image(img_dir):
image = Image.open(img_dir).convert('L')
print(image.mode)
# plt.imshow(image)
im = image.resize([28, 28])
#image_arr = np.array(image)
tv = list(im.getdata())
tva = [(255-x)*1.0/255.0 for x in tv]
return tva
with tf.variable_scope('Placeholder'):
x = tf.placeholder("float", name='X_placeholder', shape=[None, 784])
y_ = tf.placeholder("float", name='y_placeholder', shape=[None, 10])
x_image = tf.reshape(x, [-1,28,28,1])
with tf.variable_scope('conv1') as scope:
W_conv1 = tf.get_variable('W_conv1', shape=[5, 5, 1, 32], initializer=tf.random_normal_initializer(stddev=0.1))
b_conv1 = tf.get_variable('b_conv1', shape=[32], initializer=tf.constant_initializer(0.1))
conv1 = tf.nn.conv2d(x_image, W_conv1, strides=[1, 1, 1, 1], padding="SAME")
pre_activation = tf.nn.bias_add(conv1, b_conv1)
activation = tf.nn.relu(pre_activation, name=scope.name)
with tf.variable_scope('pool1') as scope:
pool1 = tf.nn.max_pool(activation, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding="SAME", name=scope.name)
with tf.variable_scope('conv2') as scope:
W_conv2 = tf.get_variable('W_conv2', shape=[5, 5, 32, 64], initializer=tf.random_normal_initializer(stddev=0.1))
b_conv2 = tf.get_variable('b_conv2', shape=[64], initializer=tf.constant_initializer(0.1))
conv2 = tf.nn.conv2d(pool1, W_conv2, strides=[1, 1, 1, 1], padding="SAME")
pre_activation = tf.nn.bias_add(conv2, b_conv2)
activation = tf.nn.relu(pre_activation, name=scope.name)
with tf.variable_scope('pool2') as scope:
pool2 = tf.nn.max_pool(activation, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding="SAME", name=scope.name)
with tf.variable_scope('fc1') as scope:
W_fc1 = tf.get_variable("W_fc1", shape=[7 * 7 * 64, 1024], initializer=tf.truncated_normal_initializer(stddev=0.1))
b_fc1 = tf.get_variable("b_fc1", shape=[1024], initializer=tf.constant_initializer(0.1))
pool2_falt = tf.reshape(pool2, [-1, 7*7*64])
fc1 = tf.matmul(pool2_falt, W_fc1) + b_fc1
activation = tf.nn.relu(fc1, name=scope.name)
drop_fc1 = tf.nn.dropout(activation, keep_prob=0.5)
with tf.variable_scope('softmax') as scope:
W_softmax = tf.get_variable("W_softmax", shape= [1024, 10], initializer=tf.truncated_normal_initializer(stddev=0.1))
b_softmax = tf.get_variable("b_softmax", shape=[10], initializer=tf.constant_initializer(0.1))
y_conv=tf.nn.softmax(tf.matmul(drop_fc1, W_softmax) + b_softmax, name=scope.name)
test_file = '/root/my_bp/mnist-test/2.bmp'
image_arr = get_one_image(test_file)
saver = tf.train.Saver()
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
saver.restore(sess, 'results/graph.chkp')
prediction=tf.argmax(y_conv,1)
predint=prediction.eval(feed_dict={x: [image_arr]}, session=sess)
print('recognize result:')
print(predint[0])
扫一扫
2万+
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
