def main(_):
# load data
meta, train_data, test_data = input_data.load_data(FLAGS.data_dir,
flatten=True)
print('data loaded')
print('train images: %s. test images: %s' %
(train_data.images.shape[0], test_data.images.shape[0]))
LABEL_SIZE = meta['label_size'] * meta["num_per_image"]
IMAGE_SIZE = meta['width'] * meta['height']
print('label_size: %s, image_size: %s' % (LABEL_SIZE, IMAGE_SIZE))
# variable in the graph for input data
x = tf.placeholder(tf.float32, [None, IMAGE_SIZE])
y_ = tf.placeholder(tf.float32, [None, LABEL_SIZE])
# define the model
W = tf.Variable(tf.zeros([IMAGE_SIZE, LABEL_SIZE]))
b = tf.Variable(tf.zeros([LABEL_SIZE]))
y = tf.matmul(x, W) + b
# Define loss and optimizer
diff = tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y)
cross_entropy = tf.reduce_mean(diff)
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)
# forword prop
predict = tf.argmax(y, axis=1)
expect = tf.argmax(y_, axis=1)
# evaluate accuracy
correct_prediction = tf.equal(predict, expect)
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
with tf.Session() as sess:
tf.global_variables_initializer().run()
# Train
for i in range(MAX_STEPS):
batch_xs, batch_ys = train_data.next_batch(BATCH_SIZE)
sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})
if i % 100 == 0:
# Test trained model
r = sess.run(accuracy,
feed_dict={
x: test_data.images,
y_: test_data.labels
})
print('step = %s, accuracy = %.2f%%' % (i, r * 100))
# final check after looping
r_test = sess.run(accuracy,
feed_dict={
x: test_data.images,
y_: test_data.labels
})
print('testing accuracy = %.2f%%' % (r_test * 100, ))
saver = tf.train.Saver()
save_path = saver.save(sess, "./model.ckpt")
def main(_):
# load data
meta, train_data, test_data = input_data.load_data(FLAGS.data_dir, flatten=False)
print('data loaded')
print('train images: %s. test images: %s' % (train_data.images.shape[0], test_data.images.shape[0]))
LABEL_SIZE = meta['label_size']
IMAGE_HEIGHT = meta['height']
IMAGE_WIDTH = meta['width']
IMAGE_SIZE = IMAGE_WIDTH * IMAGE_HEIGHT
print('label_size: %s, image_size: %s' % (LABEL_SIZE, IMAGE_SIZE))
# variable in the graph for input data
with tf.name_scope('input'):
x = tf.placeholder(tf.float32, [None, IMAGE_HEIGHT, IMAGE_WIDTH])
y_ = tf.placeholder(tf.float32, [None, LABEL_SIZE])
# must be 4-D with shape `[batch_size, height, width, channels]`
x_image = tf.reshape(x, [-1, IMAGE_HEIGHT, IMAGE_WIDTH, 1])
tf.summary.image('input', x_image, max_outputs=LABEL_SIZE)
# define the model
with tf.name_scope('convolution-layer-1'):
W_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32])
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)
with tf.name_scope('convolution-layer-2'):
W_conv2 = weight_variable([5, 5, 32, 64])
b_conv2 = bias_variable([64])
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2)
with tf.name_scope('densely-connected'):
W_fc1 = weight_variable([IMAGE_WIDTH * IMAGE_HEIGHT * 4, 1024])
b_fc1 = bias_variable([1024])
h_pool2_flat = tf.reshape(h_pool2, [-1, IMAGE_WIDTH*IMAGE_HEIGHT*4])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
with tf.name_scope('dropout'):
# To reduce overfitting, we will apply dropout before the readout layer
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
with tf.name_scope('readout'):
W_fc2 = weight_variable([1024, LABEL_SIZE])
b_fc2 = bias_variable([LABEL_SIZE])
y_conv = tf.matmul(h_fc1_drop, W_fc2) + b_fc2
# Define loss and optimizer
# Returns:
# A 1-D `Tensor` of length `batch_size`
# of the same type as `logits` with the softmax cross entropy loss.
with tf.name_scope('loss'):
cross_entropy = tf.reduce_mean(
# -tf.reduce_sum(y_ * tf.log(y_conv), reduction_indices=[1]))
tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y_conv))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
variable_summaries(cross_entropy)
# forword prop
with tf.name_scope('forword-prop'):
predict = tf.argmax(y_conv, axis=1)
expect = tf.argmax(y_, axis=1)
# evaluate accuracy
with tf.name_scope('evaluate_accuracy'):
correct_prediction = tf.equal(predict, expect)
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
variable_summaries(accuracy)
with tf.Session(config=config) as sess:
merged = tf.summary.merge_all()
train_writer = tf.summary.FileWriter(LOG_DIR + '/train', sess.graph)
test_writer = tf.summary.FileWriter(LOG_DIR + '/test', sess.graph)
tf.global_variables_initializer().run()
# Train
for i in range(MAX_STEPS):
batch_xs, batch_ys = train_data.next_batch(BATCH_SIZE)
step_summary, _ = sess.run([merged, train_step], feed_dict={x: batch_xs, y_: batch_ys, keep_prob: 1.0})
train_writer.add_summary(step_summary, i)
if i % 100 == 0:
# Test trained model
valid_summary, train_accuracy = sess.run([merged, accuracy], feed_dict={x: batch_xs, y_: batch_ys, keep_prob: 1.0})
train_writer.add_summary(valid_summary, i)
# final check after looping
test_x, test_y = test_data.next_batch(2000)
test_summary, test_accuracy = sess.run([merged, accuracy], feed_dict={x: test_x, y_: test_y, keep_prob: 1.0})
test_writer.add_summary(test_summary, i)
print('step %s, training accuracy = %.2f%%, testing accuracy = %.2f%%' % (i, train_accuracy * 100, test_accuracy * 100))
saver = tf.train.Saver()
saver.save(sess, "model/1char/model.ckpt")
train_writer.close()
test_writer.close()
# final check after looping
test_x, test_y = test_data.next_batch(2000)
test_accuracy = accuracy.eval(feed_dict={x: test_x, y_: test_y, keep_prob: 1.0})
print('testing accuracy = %.2f%%' % (test_accuracy * 100, ))
def main(_):
# load data
print('开始')
meta, train_data, test_data = input_data.load_data(c_dir + '/' +
FLAGS.data_dir,
flatten=False)
print('data loaded')
print('train images: %s. test images: %s' %
(train_data.images.shape[0], test_data.images.shape[0]))
LABEL_SIZE = meta['label_size']
NUM_PER_IMAGE = meta['num_per_image']
IMAGE_HEIGHT = meta['height']
IMAGE_WIDTH = meta['width']
IMAGE_SIZE = IMAGE_WIDTH * IMAGE_HEIGHT
print('label_size: %s, image_size: %s' % (LABEL_SIZE, IMAGE_SIZE))
# variable in the graph for input data
with tf.name_scope('input'):
x = tf.placeholder(tf.float32, [None, IMAGE_HEIGHT, IMAGE_WIDTH])
y_ = tf.placeholder(tf.float32, [None, NUM_PER_IMAGE * LABEL_SIZE])
# must be 4-D with shape `[batch_size, height, width, channels]`
x_image = tf.reshape(x, [-1, IMAGE_HEIGHT, IMAGE_WIDTH, 1])
tf.summary.image('input', x_image, max_outputs=LABEL_SIZE)
# define the model
with tf.name_scope('convolution-layer-1'):
W_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32])
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)
with tf.name_scope('convolution-layer-2'):
W_conv2 = weight_variable([5, 5, 32, 64])
b_conv2 = bias_variable([64])
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2)
with tf.name_scope('densely-connected'):
W_fc1 = weight_variable([IMAGE_WIDTH * IMAGE_HEIGHT * 4, 1024])
b_fc1 = bias_variable([1024])
h_pool2_flat = tf.reshape(h_pool2,
[-1, IMAGE_WIDTH * IMAGE_HEIGHT * 4])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
with tf.name_scope('dropout'):
# To reduce overfitting, we will apply dropout before the readout layer
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
with tf.name_scope('readout'):
W_fc2 = weight_variable([1024, LABEL_SIZE])
b_fc2 = bias_variable([LABEL_SIZE])
y_conv = tf.matmul(h_fc1_drop, W_fc2) + b_fc2
# Define loss and optimizer
# Returns:
# A 1-D `Tensor` of length `batch_size`
# of the same type as `logits` with the softmax cross entropy loss.
# forword prop
with tf.name_scope('forword-prop'):
predict = tf.argmax(y_conv, axis=1)
expect = tf.argmax(y_, axis=1)
# evaluate accuracy
with tf.name_scope('evaluate_accuracy'):
correct_prediction = tf.equal(predict, expect)
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
variable_summaries(accuracy)
fixed_adv_sample_get_op = stepll_adversarial_images(x, y_conv)
with tf.Session() as sess:
restore(sess)
# 初始化 tf.global_variables_initializer().run()
# Test
test_x, test_y = train_data.next_batch(1)
_predict = predict.eval(feed_dict={
x: test_x,
y_: test_y,
keep_prob: 1.0
})
_expect = expect.eval(feed_dict={
x: test_x,
y_: test_y,
keep_prob: 1.0
})
_adv = fixed_adv_sample_get_op.eval(feed_dict={
x: test_x,
y_: test_y,
keep_prob: 1.0
})
print(_adv.shape)
_adv_predict = predict.eval(feed_dict={
x: _adv,
y_: test_y,
keep_prob: 1.0
})
plt.subplot(1, 2, 1)
plt.imshow(test_x[0])
plt.subplot(1, 2, 2)
plt.imshow(_adv[0])
plt.show()
print(
_predict,
_expect,
_adv_predict,
)
def main(_):
# load data
meta, train_data, test_data = input_data.load_data(FLAGS.data_dir,
flatten=False)
print('data loaded')
print('train images: %s. test images: %s' %
(train_data.images.shape[0], test_data.images.shape[0]))
LABEL_SIZE = meta['label_size']
IMAGE_HEIGHT = meta['height']
IMAGE_WIDTH = meta['width']
# LABEL_SIZE = 62
# IMAGE_HEIGHT = 40
# IMAGE_WIDTH = 40
IMAGE_SIZE = IMAGE_WIDTH * IMAGE_HEIGHT
print('label_size: %s, image_size: %s' % (LABEL_SIZE, IMAGE_SIZE))
# variable in the graph for input data
with tf.name_scope('input'):
x = tf.placeholder(tf.float32, [None, IMAGE_HEIGHT, IMAGE_WIDTH])
y_ = tf.placeholder(tf.float32, [None, LABEL_SIZE])
# must be 4-D with shape `[TRAIN_BATCH_SIZE, height, width, channels]`
x_image = tf.reshape(x, [-1, IMAGE_HEIGHT, IMAGE_WIDTH, 1])
tf.summary.image('input', x_image, max_outputs=LABEL_SIZE)
# define the model
with tf.name_scope('convolution-layer-1'):
W_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32])
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)
with tf.name_scope('convolution-layer-2'):
W_conv2 = weight_variable([3, 3, 32, 64])
b_conv2 = bias_variable([64])
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2)
with tf.name_scope('convolution-layer-3'):
W_conv3 = weight_variable([3, 3, 64, 128])
b_conv3 = bias_variable([128])
h_conv3 = tf.nn.relu(conv2d(h_pool2, W_conv3) + b_conv3)
h_pool3 = max_pool_2x2(h_conv3)
with tf.name_scope('convolution-layer-4'):
W_conv4 = weight_variable([3, 3, 128, 256])
b_conv4 = bias_variable([256])
h_conv4 = tf.nn.relu(conv2d(h_pool3, W_conv4) + b_conv4)
# h_pool4 = max_pool_2x2(h_conv4)
h_pool4 = tf.nn.max_pool(h_conv4,
ksize=[1, 5, 5, 1],
strides=[1, 1, 1, 1],
padding='VALID')
with tf.name_scope('readout'):
W_fc2 = weight_variable([256, LABEL_SIZE])
b_fc2 = bias_variable([LABEL_SIZE])
# pre_fc = tf.reshape(h_pool5, [-1, 512])
# h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
pre_fc = tf.reshape(h_pool4, [-1, 256])
y_conv = tf.matmul(pre_fc, W_fc2) + b_fc2
# with tf.name_scope('convolution-layer-5'):
# W_conv5 = weight_variable([3, 3, 256, 512])
# b_conv5 = bias_variable([512])
# h_conv5 = tf.nn.relu(conv2d(h_pool4, W_conv5) + b_conv5)
# h_pool5 = max_pool_2x2(h_conv5)
# h_pool5 = tf.nn.max_pool(h_conv5, ksize=[1, 2, 2, 1],
# strides=[1, 2, 2, 1], padding='SAME')
# with tf.name_scope('densely-connected'):
# W_fc1 = weight_variable([IMAGE_WIDTH * IMAGE_HEIGHT * 4, 1024])
# b_fc1 = bias_variable([1024])
# h_pool2_flat = tf.reshape(
# h_pool2, [-1, IMAGE_WIDTH * IMAGE_HEIGHT * 4])
# h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
# with tf.name_scope('dropout'):
# # To reduce overfitting, we will apply dropout before the readout layer
# keep_prob = tf.placeholder(tf.float32)
# h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
# with tf.name_scope('readout'):
# W_fc2 = weight_variable([512, LABEL_SIZE])
# b_fc2 = bias_variable([LABEL_SIZE])
# pre_fc = tf.reshape(h_pool5, [-1, 512])
# y_conv = tf.matmul(pre_fc, W_fc2) + b_fc2
# Define loss and optimizer
# Returns:
# A 1-D `Tensor` of length `TRAIN_BATCH_SIZE`
# of the same type as `logits` with the softmax cross entropy loss.
with tf.name_scope('loss'):
cross_entropy = tf.reduce_mean(
# -tf.reduce_sum(y_ * tf.log(y_conv), reduction_indices=[1]))
tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y_conv))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
variable_summaries(cross_entropy)
# forword prop
with tf.name_scope('forword-prop'):
predict = tf.argmax(y_conv, axis=1)
expect = tf.argmax(y_, axis=1)
# evaluate accuracy
with tf.name_scope('evaluate_accuracy'):
correct_prediction = tf.equal(predict, expect)
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
variable_summaries(accuracy)
with tf.Session() as sess:
merged = tf.summary.merge_all()
train_writer = tf.summary.FileWriter(LOG_DIR + '/train', sess.graph)
test_writer = tf.summary.FileWriter(LOG_DIR + '/test', sess.graph)
tf.global_variables_initializer().run()
# Train
for i in range(MAX_STEPS):
batch_xs, batch_ys = train_data.next_batch(TRAIN_BATCH_SIZE)
step_summary, _ = sess.run([merged, train_step],
feed_dict={
x: batch_xs,
y_: batch_ys
})
train_writer.add_summary(step_summary, i)
if i % 100 == 0:
# Test trained model
valid_summary, train_accuracy = sess.run([merged, accuracy],
feed_dict={
x: batch_xs,
y_: batch_ys
})
train_writer.add_summary(valid_summary, i)
# final check after looping
sum_test_acc = 0
for j in range(TEST_STEPS):
test_x, test_y = test_data.next_batch(TEST_BATCH_SIZE)
test_summary, test_accuracy = sess.run([merged, accuracy],
feed_dict={
x: test_x,
y_: test_y
})
test_writer.add_summary(test_summary, i)
sum_test_acc += test_accuracy
sum_test_acc /= TEST_STEPS
print(
'step %s, training accuracy = %.2f%%, testing accuracy = %.2f%%'
% (i, train_accuracy * 100, sum_test_acc * 100))
train_writer.close()
test_writer.close()
# saver = tf.train.Saver()
# # saver.save(sess, osp.join(LOG_DIR, './models-5-layers-zyf'))
# saver.save(sess, osp.join(LOG_DIR, './models-4-layers-zyf'))
# final check after looping
sum_test_acc = 0
for j in range(TEST_STEPS):
test_x, test_y = test_data.next_batch(TEST_BATCH_SIZE)
test_accuracy = accuracy.eval(feed_dict={x: test_x, y_: test_y})
sum_test_acc += test_accuracy
sum_test_acc /= TEST_STEPS
print('testing accuracy = %.2f%%' % (sum_test_acc * 100, ))
if i >= MAX_STEPS * 0.9 or sum_test_acc >= 0.95:
saver = tf.train.Saver()
# saver.save(sess, osp.join(LOG_DIR, './models-5-layers-zyf'))
saver.save(sess,
osp.join(LOG_DIR, './models-7-layers-zyf'),
global_step=i)
def main(_):
# load data
meta, train_data, test_data = input_data.load_data(FLAGS.data_dir,
flatten=True)
print('data loaded. train images: %s. test images: %s' %
(train_data.images.shape[0], test_data.images.shape[0]))
LABEL_SIZE = meta['label_size']
IMAGE_WIDTH = meta['width']
IMAGE_HEIGHT = meta['height']
IMAGE_SIZE = IMAGE_WIDTH * IMAGE_HEIGHT
print('label_size: %s, image_size: %s' % (LABEL_SIZE, IMAGE_SIZE))
# variable in the graph for input data
with tf.name_scope('input'):
x = tf.placeholder(tf.float32, [None, IMAGE_SIZE])
y_ = tf.placeholder(tf.float32, [None, LABEL_SIZE])
variable_summaries(x)
variable_summaries(y_)
# must be 4-D with shape `[batch_size, height, width, channels]`
images_shaped_input = tf.reshape(x, [-1, IMAGE_HEIGHT, IMAGE_WIDTH, 1])
tf.summary.image('input',
images_shaped_input,
max_outputs=LABEL_SIZE * 2)
# define the model
# Adding a name scope ensures logical grouping of the layers in the graph.
with tf.name_scope('linear_model'):
with tf.name_scope('W'):
W = tf.Variable(tf.zeros([IMAGE_SIZE, LABEL_SIZE]))
variable_summaries(W)
with tf.name_scope('b'):
b = tf.Variable(tf.zeros([LABEL_SIZE]))
variable_summaries(b)
with tf.name_scope('y'):
y = tf.matmul(x, W) + b
tf.summary.histogram('y', y)
# Define loss and optimizer
# Returns:
# A 1-D `Tensor` of length `batch_size`
# of the same type as `logits` with the softmax cross entropy loss.
with tf.name_scope('loss'):
diff = tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y)
cross_entropy = tf.reduce_mean(diff)
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(
cross_entropy)
variable_summaries(diff)
# forword prop
predict = tf.argmax(y, axis=1)
expect = tf.argmax(y_, axis=1)
# evaluate accuracy
with tf.name_scope('evaluate_accuracy'):
correct_prediction = tf.equal(predict, expect)
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
variable_summaries(accuracy)
with tf.Session() as sess:
merged = tf.summary.merge_all()
train_writer = tf.summary.FileWriter(LOG_DIR + '/train', sess.graph)
tf.global_variables_initializer().run()
# Train
for i in range(MAX_STEPS):
batch_xs, batch_ys = train_data.next_batch(BATCH_SIZE)
train_summary, _ = sess.run([merged, train_step],
feed_dict={
x: batch_xs,
y_: batch_ys
})
train_writer.add_summary(train_summary, i)
if i % 100 == 0:
# Test trained model
test_summary, r = sess.run([merged, accuracy],
feed_dict={
x: test_data.images,
y_: test_data.labels
})
train_writer.add_summary(test_summary, i)
print('step = %s, accuracy = %.2f%%' % (i, r * 100))
train_writer.close()
# final check after looping
test_summary, r_test = sess.run([merged, accuracy],
feed_dict={
x: test_data.images,
y_: test_data.labels
})
train_writer.add_summary(test_summary, i)
print('testing accuracy = %.2f%%' % (r_test * 100, ))
