def get_model(img_h, nclass):
input = Input(shape=(img_h, None, 1), name='the_input')
y_pred = densenet.dense_cnn(input, nclass)
# y_pred = densenet.dense_blstm(input, nclass)
basemodel = Model(inputs=input, outputs=y_pred)
basemodel.summary()
labels = Input(name='the_labels', shape=[None], dtype='float32')
input_length = Input(name='input_length', shape=[1], dtype='int64')
label_length = Input(name='label_length', shape=[1], dtype='int64')
loss_out = Lambda(ctc_lambda_func, output_shape=(1, ),
name='ctc')([y_pred, labels, input_length, label_length])
model = Model(inputs=[input, labels, input_length, label_length],
outputs=loss_out)
if GPU_NUM > 1:
model = multi_gpu_model(model, gpus=GPU_NUM)
model.compile(loss={
'ctc': lambda y_true, y_pred: y_pred
},
optimizer='adam',
metrics=['accuracy'])
return basemodel, model
def getOldModel(img_h, nclass=None):
"""
获得预训练模型
:param img_h:
:param nclass:
:return:
"""
if nclass == None:
nclass = 5990
input_base = Input(shape=(img_h, None, 1), name='the_input')
y_pred = densenet.dense_cnn(input_base, nclass) # 预训练的模型是5990个字符
basemodel = Model(inputs=input_base, outputs=y_pred)
pretrainModelPath = './models/pretrainedModel/weights_densenet.h5'
print(
"--------------------------------------------------------------------------------------"
)
if os.path.exists(pretrainModelPath):
print("Loading model weights...")
basemodel.load_weights(pretrainModelPath)
print('done!')
else:
print("No pre-trained model loaded!")
print(
"--------------------------------------------------------------------------------------"
)
return basemodel
def get_model(img_h, nclass):
input = Input(shape=(img_h, None, 1), name='the_input')
y_pred = densenet.dense_cnn(input, nclass)
basemodel = Model(inputs=input, outputs=y_pred)
basemodel.summary()
labels = Input(name='the_labels', shape=[None], dtype='float32')
input_length = Input(name='input_length', shape=[1], dtype='int64')
label_length = Input(name='label_length', shape=[1], dtype='int64')
loss_out = Lambda(ctc_lambda_func, output_shape=(1,), name='ctc')([y_pred, labels, input_length, label_length])
model = Model(inputs=[input, labels, input_length, label_length], outputs=loss_out)
model.compile(loss={'ctc': lambda y_true, y_pred: y_pred}, optimizer='adam', metrics=['accuracy'])
return basemodel, model
def get_model(img_h, nclass):
input = Input(shape=(img_h, None, 1), name='the_input')
y_pred = densenet.dense_cnn(input, nclass)
basemodel = Model(inputs=input, outputs=y_pred)
basemodel.summary()
labels = Input(name='the_labels', shape=[
None,
], dtype='float32')
input_length = Input(name='input_length', shape=[1], dtype='int64')
label_length = Input(name='label_length', shape=[1], dtype='int64')
loss_out = Lambda(ctc_lambda_func, output_shape=(1, ),
name='ctc')([y_pred, labels, input_length, label_length])
model = Model(inputs=[input, labels, input_length, label_length],
outputs=loss_out)
return basemodel, model
def load_model(self,):
from keras.layers import Input, Conv2D, MaxPooling2D, ZeroPadding2D
from keras.models import Model
from densenet import dense_cnn
self.g2 = tf.Graph()
self.sess2 = tf.Session(graph=self.g2 )
with self.sess2.as_default():
with self.g2.as_default():
input = Input(shape=(32, None, 1), name='the_input')
nclass = 5991
y_pred = dense_cnn(input, nclass)
self.basemodel = Model(inputs=input, outputs=y_pred)
#---------------------test--------------------------------
jsonFile = self.basemodel.to_json()
with open(r'./test_modle.json', 'w') as file:
file.write(jsonFile)
#---------------------------------------------------------
modelPath = r'weights-densent-13.hdf5'#手写体数字5991
self.basemodel.load_weights(modelPath)
print('xxxxxxxxxxxxxxxxxxxxxxx')
return self.basemodel
def get_model_origin_conv(img_h, nclass):
old_nClass = len(keys.alphabet[:])
input = Input(shape=(img_h, None, 1), name='the_input')
y_pred_old = densenet.dense_cnn(input, old_nClass)
basemodel = Model(inputs=input, outputs=y_pred_old)
basemodel.load_weights(modelPath)
flatten = basemodel.get_layer('flatten').output
y_pred = Dense(nclass, name='y_pred_out', activation='softmax')(flatten)
labels = Input(name='the_labels', shape=[
None,
], dtype='float32')
input_length = Input(name='input_length', shape=[1], dtype='int64')
label_length = Input(name='label_length', shape=[1], dtype='int64')
loss_out = Lambda(ctc_lambda_func, output_shape=(1, ),
name='ctc')([y_pred, labels, input_length, label_length])
model = Model(inputs=[input, labels, input_length, label_length],
outputs=loss_out)
return basemodel, model
path = 'densenet_savemodel'
densenet_file = './models/densenet/densenet_single_gpu.h5'
export_path = './densenet_savemodel/1/'
if os.path.exists(export_path):
shutil.rmtree(export_path)
if not os.path.exists(path):
os.mkdir(path)
reload(densenet)
characters = keys.alphabet[:]
characters = characters[1:] + u'卍'
nclass = len(characters)
input = Input(shape=(32, None, 1), name='the_input')
y_pred = densenet.dense_cnn(input, nclass)
basemodel = Model(inputs=input, outputs=y_pred)
modelPath = densenet_file
# basemodel = multi_gpu_model(basemodel, gpus=2)
basemodel.load_weights(modelPath)
#---------
K.set_learning_phase(0)
export_path = os.path.join(tf.compat.as_bytes(path),
tf.compat.as_bytes(str(version)))
builder = tf.saved_model.builder.SavedModelBuilder(export_path)
print('input info:', basemodel.input_names, '---', basemodel.input)
print('output info:', basemodel.output_names, '---', basemodel.output)
#-*- coding:utf-8 -*-
from imp import reload
from keras.layers import Input
from keras.models import Model
from keras.utils import plot_model
import densenet
reload(densenet)
input = Input(shape=(32, None, 1), name='the_input')
y_pred = densenet.dense_cnn(input, 5990)
basemodel = Model(inputs=input, outputs=y_pred)
basemodel.load_weights(
'/home/vcaadmin/zhuangwu/huang/scene_text_recognition/densenet/weights_densenet-04-0.66.h5'
)
plot_model(basemodel, to_file='model.png')
print('OK')
#
labels[i, :len(str)] = [int(s) - 1 for s in str]
inputs = {
'the_input': x,
'the_labels': labels,
'input_length': input_length,
'label_length': label_length,
}
outputs = {'ctc': np.zeros([batchsize])}
yield (inputs, outputs)
input = Input(shape=(img_h, None, 1), name='the_input')
y_pred = densenet.dense_cnn(input, nclass, name='new')
basemodel = Model(inputs=input, outputs=y_pred)
basemodel.summary()
labels = Input(name='the_labels', shape=[maxlabellength], dtype='float32')
input_length = Input(name='input_length', shape=[1], dtype='int64')
label_length = Input(name='label_length', shape=[1], dtype='int64')
loss_out = Lambda(ctc_lambda_func, output_shape=(1, ),
name='ctc')([y_pred, labels, input_length, label_length])
model = Model(inputs=[input, labels, input_length, label_length],
outputs=loss_out)
adam = Adam()
char = ''
with open('char_std_5990.txt', encoding='utf-8') as f:
for ch in f.readlines():
ch = ch.strip('\r\n')
char = char + ch
# caffe_ocr中把0作为blank，但是tf 的CTC the last class is reserved to the blank label.
# https://github.com/tensorflow/tensorflow/blob/master/tensorflow/core/util/ctc/ctc_loss_calculator.h
char = char[1:] + '卍'
nclass = len(char)
print('nclass:', len(char))
id_to_char = {i: j for i, j in enumerate(char)}
modelPath = r'model\weights-densent-32-0.9846.hdf5'
_input = Input(shape=(32, None, 1), name='the_input')
y_pred = densenet.dense_cnn(_input, nclass + 1)
basemodel = Model(inputs=_input, outputs=y_pred)
basemodel.load_weights(modelPath)
t = Timer()
def predict(img_path):
img = Image.open(img_path)
im = img.convert('L')
scale = im.size[1] * 1.0 / 32
w = im.size[0] / scale
w = int(w)
print('w:', w)
im = im.resize((w, 32), Image.ANTIALIAS)
