if args == 'true' :
TRAIN_FLAGS = True
elif args == 'false' :
TRAIN_FLAGS = False
elif op == '--input' :
input_data = load_english_dataset.read_inference_data(args)
else :
print 'invalid program usage. check the usage again.'
sys.exit()
if TRAIN_FLAGS == True:
input_data, ground_truth, test_data, test_ground_truth = load_english_dataset.read_dataset()
assert len(input_data) == len(ground_truth), 'len of input_data : %d, len of gt : %d' % (len(input_data), len(ground_truth))
assert len(test_data) == len(test_ground_truth)
print '# of training dataset : %d, # of testing dataset : %d' %(len(input_data), len(test_data))
def weight_variable(shape):
initial = tf.truncated_normal(shape, stddev=0.1)
initial /= 10.0
return tf.Variable(initial)
def bias_variable(shape):
initial = tf.constant(0.1, shape=shape)
return tf.Variable(initial)
def inference(image, bounding_box, bbox_type, bbox_character):
input_data, ground_truth, test_data, test_ground_truth = [], [], [], []
if TRAIN_FLAGS == True:
input_data, ground_truth, test_data, test_ground_truth = load_english_dataset.read_dataset()
assert len(input_data) == len(ground_truth), 'len of input_data : %d, len of gt : %d' % (len(input_data), len(ground_truth))
assert len(test_data) == len(test_ground_truth)
print '# of training dataset : %d, # of testing dataset : %d' %(len(input_data), len(test_data))
else:
for row in bounding_box:
input_row = []
for x1,y1,x2,y2 in row:
input_row.append(load_english_dataset.read_inference_data(image[x1:x2,y1:y2]))
input_data.append(input_row)
def weight_variable(shape):
initial = tf.truncated_normal(shape, stddev=0.1)
initial /= 10.0
return tf.Variable(initial)
def bias_variable(shape):
initial = tf.constant(0.1, shape=shape)
return tf.Variable(initial)
def conv2d(x, W):
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')
x = tf.placeholder("float", shape=[1,32*32*1]) #[32*32*1]
y_ = tf.placeholder("float", shape=[1,class_size]) #[class_size]
x_image = tf.reshape(x, [-1,32,32,1])
W_conv0 = weight_variable([3,3,1,16])
b_conv0 = bias_variable([16])
h_conv0 = tf.nn.relu(conv2d(x_image, W_conv0) + b_conv0) # h_conv0=[1,32*32*16]
W_conv1 = weight_variable([3,3,16,32])
b_conv1 = bias_variable([32])
h_conv1 = tf.nn.relu(conv2d(h_conv0, W_conv1) + b_conv1) #h_conv1=[1,32*32*32]
h_pool1 = max_pool_2x2(h_conv1) #h_pool1=[1,16*16*32]
W_conv1_5 = weight_variable([3,3,32,32])
b_conv1_5 = bias_variable([32])
h_conv1_5 = tf.nn.relu(conv2d(h_pool1, W_conv1_5) + b_conv1_5) # h_conv1.5=[32*32*32]
W_conv2 = weight_variable([3,3,32,64])
b_conv2 = bias_variable([64])
h_conv2 = tf.nn.relu(conv2d(h_conv1_5, W_conv2) + b_conv2) #h_conv2=[16*16*64]
h_pool2 = max_pool_2x2(h_conv2) #h_pool2=[8*8*64]
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)
W_fc1 = weight_variable([8*8*128, 1024])
b_fc1 = bias_variable([1024])
h_conv3_flat = tf.reshape(h_conv3, [-1, 8*8*128])
h_fc1 = tf.nn.relu(tf.matmul(h_conv3_flat, W_fc1) + b_fc1)
keep_prob = tf.placeholder("float")
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
# is number of Hangul
W_fc2 = weight_variable([1024,1024])
b_fc2 = bias_variable([1024])
h_fc2 = tf.nn.relu(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)
h_fc2_drop = tf.nn.dropout(h_fc2, keep_prob)
W_fc3 = weight_variable([1024,class_size])
b_fc3 = bias_variable([class_size])
y_conv = tf.nn.softmax(tf.matmul(h_fc2_drop, W_fc3) + b_fc3)
cross_entropy = -tf.reduce_sum(y_*tf.log(y_conv + 1e-9))
train_step = tf.train.AdamOptimizer(1e-6).minimize(cross_entropy)
#train_step_2 = tf.train.AdamOptimizer(1e-7).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(y_,1), tf.argmax(y_conv,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
sess.run(tf.initialize_all_variables())
saver = tf.train.Saver()
start_time = time.time()
idx = range(len(ground_truth))
random.shuffle(idx)
LR_CHANGE_FLAG = False
# during training phase, we will train the model.
if TRAIN_FLAGS == True:
for i in range(EPOCH):
#at every 100 iterations, we will compute loss and display it.
if i%20 == 0:
acc = 0.0
loss = 0.0
# we need batch size of 50 for calculate loss.
for k in xrange(len(test_data)):
acc += accuracy.eval(
feed_dict={x:test_data[k], y_:test_ground_truth[k].reshape(1,class_size), keep_prob: 1.0})
loss += sess.run(cross_entropy, {x:test_data[k], y_:test_ground_truth[k].reshape(1, class_size), keep_prob: 1.0})
acc /= float(len(test_data))
loss /= float(len(test_data))
current_time = time.time()
print '%dth iteration...%d secs passed over... accuracy : %lf, loss : %lf'% (i, current_time - start_time, acc, loss)
#we need save checkpoint at every 1000 iterations.
if i>0 and i%200 == 0:
chk_file = checkpoint_dir + 'iteration_' + str(i) + '.ckpt'
saver.save(sess, chk_file)
print 'model saved in files : %s' % chk_file
# every entry in training data is used at training. not a batch
# formulation.
for t in idx:
train_step.run(feed_dict={x:input_data[t], y_:ground_truth[t], keep_prob: 0.5})
# during evaluation phase, we restore model by checkpoint file.
else:
check_file = './checkpoint_english/english_shortcut.ckpt'
saver.restore(sess, check_file)
#label = sess.run(tf.argmax(y_conv,1), feed_dict={x:input_data[0], keep_prob:1.0})
label_interface_file = open(pickle_path + 'english_label_information.txt')
label_interface = pickle.load(label_interface_file)
i = 0
for row in input_data:
j = -1
for input_box in row:
"""
only takes english character.
"""
j += 1
if bbox_type[i][j] != 8 : continue
label_index = sess.run(tf.argmax(y_conv,1), feed_dict = {x:input_box, keep_prob:1.0})
bbox_character[i][j] = str(label_interface[label_index])
i += 1
bbox_character_file = open(pickle_path + 'bbox_character.txt', 'w')
pickle.dump(bbox_character, bbox_character_file)
bbox_character_file.close()
sess.close()
