def __init__(self, ckpt_path="./model/model-30000"):
print(ckpt_path)
self.x = tf.placeholder(tf.float32,
shape=[
None, mnist_inference.IMAGE_SIZE,
mnist_inference.IMAGE_SIZE,
mnist_inference.NUM_CHANNEL
],
name='x-input')
self.y = mnist_inference.inference(self.x, False, None)
saver = tf.train.Saver()
self.sess = tf.Session()
saver.restore(self.sess, ckpt_path)
def on_message(self, img):
global users
global msg
''' canvas return base64 data '''
''' base64 convert to png '''
img = img[len("data:image/png;base64,") - 1:]
img = bytes(img, encoding="utf-8")
img += b'='
img_data = base64.b64decode(img)
# save picture to look up for modification
with open('data.png', 'wb') as f:
f.write(img_data)
f.close()
# get handwriting image
img_tmp = cv2.imread("data.png", 0)
# reverse colour to enhance accuracy
rows = img_tmp.shape[0]
cols = img_tmp.shape[1]
for i in range(rows):
for j in range(cols):
img_tmp[i][j] = 255 - img_tmp[i][j]
img_tmp = cv2.resize(img_tmp, (28, 28), interpolation=cv2.INTER_CUBIC)
self.u_img = np.reshape(img_tmp, (28, 28, 1)).astype(
np.float32) # reshape to feed NN
with tf.Graph().as_default() as g:
#定义用于输入图片数据的张量占位符，输入样本的尺寸
x = tf.placeholder(tf.float32,
shape=[
None, mnist_inference.IMAGE_SIZE,
mnist_inference.IMAGE_SIZE,
mnist_inference.NUM_CHANNEL
],
name='x-input')
y = mnist_inference.inference(x, None, None)
variable_averages = tf.train.ExponentialMovingAverage(
mnist_train.MOVING_AVERAGE_DECAY)
variables_to_restore = variable_averages.variables_to_restore()
saver = tf.train.Saver(variables_to_restore)
with tf.Session() as sess:
saver = tf.train.import_meta_graph(
'model/model-9999001.meta') # restore model
saver.restore(sess, tf.train.latest_checkpoint('model'))
result = sess.run(y, feed_dict={x: [self.u_img]})
print(tf.argmax(result, 1).eval()[0])
msg = str(tf.argmax(result, 1).eval()[0])
self.write_message(msg)
def evaluate(mnist):
with tf.Graph().as_default():
x = tf.placeholder(tf.float32,
shape=[
None, mnist_inference.IMAGE_SIZE,
mnist_inference.IMAGE_SIZE,
mnist_inference.NUM_CHANNEL
],
name='x-input')
y_ = tf.placeholder(tf.float32,
shape=[None, mnist_inference.OUTPUT_NODE],
name='y-input')
xs, ys = mnist.test.images, mnist.test.labels
reshape_xs = np.reshape(
xs, (-1, mnist_inference.IMAGE_SIZE, mnist_inference.IMAGE_SIZE,
mnist_inference.NUM_CHANNEL))
val_feed = {x: reshape_xs, y_: mnist.test.labels}
y = mnist_inference.inference(x, False, None)
correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
variable_average = tf.train.ExponentialMovingAverage(
mnist_train.MOVING_AVERAGE_DECAY)
val_to_restore = variable_average.variables_to_restore()
saver = tf.train.Saver(val_to_restore)
with tf.Session() as sess:
ckpt = tf.train.get_checkpoint_state(mnist_train.MODEL_PATH)
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess, ckpt.model_checkpoint_path)
global_step = ckpt.model_checkpoint_path.split('/')[-1].split(
'-')[-1]
accuracy_score = sess.run(accuracy, feed_dict=val_feed)
print('After %s train ,the accuracy is %g' %
(global_step, accuracy_score))
else:
print('No Checkpoint file find')
def train(mnist):
x = tf.placeholder(tf.float32, [None, mnist_cnn.INPUT_NODE],
name="x-input")
y_ = tf.placeholder(tf.float32, [None, mnist_cnn.OUTPUT_NODE],
name="y-input")
regularizer = tf.contrib.layers.l2_regularizer(REGULARAZTION_RATE)
y = mnist_cnn.inference(x, True, regularizer)
global_step = tf.Variable(0, trainable=False)
variable_averages = tf.train.ExponentialMovingAverage(
MOVING_AVERAGE_DECAY, global_step)
variables_averages_op = variable_averages.apply(tf.trainable_variables())
cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(
logits=y, labels=tf.argmax(y_, 1))
cross_entropy_mean = tf.reduce_mean(cross_entropy)
loss = cross_entropy_mean + tf.add_n(tf.get_collection('losses'))
learning_rate = tf.train.exponential_decay(
LEARNING_RATE_BASE, global_step, mnist.train.num_examples / BATCH_SIZE,
LEARNING_RATE_DECAY)
train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(
loss, global_step=global_step)
with tf.control_dependenices([train_step, variables_averages_op]):
train_op = tf.no_op(name='train')
with tf.Session() as sess:
tf.global_variables_initializer().run()
for i in range(TRAINING_STEPS):
xs, ys = mnist.train.next_batch(BATCH_SIZE)
_, loss_value, step = sess.run([train_op, loss, global_step],
feed_dict={
xs: xs,
y_: ys
})
if i % 1000 == 0:
print(
"After %d training steps, loss on training batch is %g." %
(step, loss_value))
def train(mnist):
x = tf.placeholder(tf.float32, shape=[None,
mnist_interence.IMAGE_SIZE,
mnist_interence.IMAGE_SIZE,
mnist_interence.NUM_CHANNEL], name='x-input')
y_ = tf.placeholder(tf.float32, shape=[None, mnist_interence.OUTPUT_NODE], name='y-input')
regularizer = tf.contrib.layers.l2_regularizer(REGULARIZATION_TATE)
y = mnist_interence.inference(x, True, regularizer)
global_step = tf.Variable(0, trainable=False)
variable_average = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY, global_step)
variable_average_ops = variable_average.apply(tf.trainable_variables())
cross_entroy = tf.nn.sparse_softmax_cross_entropy_with_logits(logits=y, labels=tf.argmax(y_, 1))
cross_entroy_mean = tf.reduce_mean(cross_entroy)
loss = cross_entroy_mean + tf.add_n(tf.get_collection('loss'))
learning_rate = tf.train.exponential_decay(LEARNING_RATE_BASE, global_step,
mnist.train.num_examples / BATCH_SIZE, LEARNING_RATE_DECAY)
train_step = tf.train.GradientDescentOptimizer(0.01).minimize(loss, global_step=global_step)
train_op = tf.group(train_step, variable_average_ops)
saver = tf.train.Saver(max_to_keep=10)
with tf.Session() as sess:
ckpt = tf.train.get_checkpoint_state(mnist_train.MODEL_PATH)
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess, ckpt.model_checkpoint_path)
global_step = ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1]
for i in range(eval(global_step), TRAIN_STEP):
xs, ys = mnist.train.next_batch(BATCH_SIZE)
reshape_xs = np.reshape(xs, (BATCH_SIZE, mnist_interence.IMAGE_SIZE,
mnist_interence.IMAGE_SIZE,
mnist_interence.NUM_CHANNEL))
_, loss_value, step, learn_rate = sess.run([train_op, loss, global_step, learning_rate],
feed_dict={x: reshape_xs, y_: ys})
if (i + 1) % 3000 == 0:
print('After %d step, loss on train is %g,and learn rate is %g' % (step, loss_value, learn_rate))
saver.save(sess, os.path.join(MODEL_PATH, MODEL_NAME), global_step=global_step)
else:
print('No Checkpoint file find')
def train(mnist):
# 定义用于输入图片数据的张量占位符，输入样本的尺寸
x = tf.placeholder(tf.float32,
shape=[
None, mnist_interence.IMAGE_SIZE,
mnist_interence.IMAGE_SIZE,
mnist_interence.NUM_CHANNEL
],
name='x-input')
# 定义用于输入图片标签数据的张量占位符，输入样本的尺寸
y_ = tf.placeholder(tf.float32,
shape=[None, mnist_interence.OUTPUT_NODE],
name='y-input')
# 定义采用方差的正则化函数
regularizer = tf.contrib.layers.l2_regularizer(REGULARIZATION_TATE)
# 通过interence函数获得计算结果张量
y = mnist_interence.inference(x, True, regularizer)
global_step = tf.Variable(0, trainable=False)
# 定义平均滑动
variable_average = tf.train.ExponentialMovingAverage(
MOVING_AVERAGE_DECAY, global_step)
# 对所有可以训练的变量采用平均滑动
variable_average_ops = variable_average.apply(tf.trainable_variables())
# 对预测数据y和实际数据y_计算他们概率的交叉值
cross_entroy = tf.nn.sparse_softmax_cross_entropy_with_logits(
logits=y, labels=tf.argmax(y_, 1))
# 对各对交叉值求平均，其实是计算y和y_两个随机变量概率分布的交叉熵，交叉熵值越小则表明两种概率分布越接近
cross_entroy_mean = tf.reduce_mean(cross_entroy)
# 采用交叉熵和正则化参数作为最后的损失函数
loss = cross_entroy_mean + tf.add_n(tf.get_collection('loss'))
# 设置学习率递减方式
learning_rate = tf.train.exponential_decay(
LEARNING_RATE_BASE, global_step, mnist.train.num_examples / BATCH_SIZE,
LEARNING_RATE_DECAY)
# 采用梯度下降的方式计算损失函数的最小值
train_step = tf.train.GradientDescentOptimizer(0.01).minimize(
loss, global_step=global_step)
# 定义学习操作：采用梯度下降求一次模型训练参数，并对求得的模型参数计算滑动平均值
train_op = tf.group(train_step, variable_average_ops)
saver = tf.train.Saver(max_to_keep=10)
with tf.Session() as sess:
tf.global_variables_initializer().run()
for i in range(TRAIN_STEP):
# 由于神经网络的输入大小为[BATCH_SIZE,IMAGE_SIZE,IMAGE_SIZE,CHANNEL]，因此需要reshape输入。
xs, ys = mnist.train.next_batch(BATCH_SIZE)
reshape_xs = np.reshape(
xs, (BATCH_SIZE, mnist_interence.IMAGE_SIZE,
mnist_interence.IMAGE_SIZE, mnist_interence.NUM_CHANNEL))
# 通过计算图，计算模型损失张量和学习张量的当前值
_, loss_value, step, learn_rate = sess.run(
[train_op, loss, global_step, learning_rate],
feed_dict={
x: reshape_xs,
y_: ys
})
if (i + 1) % 3000 == 0:
print(
'After %d step, loss on train is %g,and learn rate is %g' %
(step, loss_value, learn_rate))
saver.save(sess,
os.path.join(MODEL_PATH, MODEL_NAME),
global_step=global_step)