from parameter import *
K.set_learning_phase(0)
# # Model description and training
model = get_Model(training=True)
try:
model.load_weights('LSTM+BN4--26--0.011.hdf5')
print("...Previous weight data...")
except:
print("...New weight data...")
pass
train_file_path = './DB/train/' ##该目录下是指定好的图片，没有其他的文件夹
tiger_train = TextImageGenerator(train_file_path, img_w, img_h, batch_size, downsample_factor)
tiger_train.build_data()
valid_file_path = './DB/test/'##该目录下是指定好的图片，没有其他的文件夹
tiger_val = TextImageGenerator(valid_file_path, img_w, img_h, val_batch_size, downsample_factor)
tiger_val.build_data()
ada = Adadelta()
early_stop = EarlyStopping(monitor='loss', min_delta=0.001, patience=4, mode='min', verbose=1)
checkpoint = ModelCheckpoint(filepath='LSTM+BN5--{epoch:02d}--{val_loss:.3f}.hdf5', monitor='loss', verbose=1, mode='min', period=1)
# the loss calc occurs elsewhere, so use a dummy lambda func for the loss
model.compile(loss={'ctc': lambda y_true, y_pred: y_pred}, optimizer=ada)
# captures output of softmax so we can decode the output during visualization
model.fit_generator(generator=tiger_train.next_batch(),
# # Model description and training
model = get_Model(training=True)
model.summary()
try:
model.load_weights('LSTM+BN4--50--0.056.hdf5')
print("...Previous weight data...")
except:
print("...New weight data...")
pass
input_shape = (img_w, img_h)
tiger_train = TextImageGenerator(batch_size, input_shape)
tiger_val = TextImageGenerator(batch_size, input_shape)
ada = Adadelta()
early_stop = EarlyStopping(monitor='loss',
min_delta=0.001,
patience=4,
mode='min',
verbose=1)
checkpoint = ModelCheckpoint(
filepath='LSTM+BN7--{epoch:02d}--{val_loss:.3f}.hdf5',
monitor='loss',
verbose=1,
mode='min',
K.set_learning_phase(0)
# # Model description and training
model = get_Model(training=True)
try:
model.load_weights('LSTM+BN5--01--33.762.hdf5')
print("...Previous weight data...")
except:
print("...New weight data...")
pass
train_file_path = './DB'
tiger_train = TextImageGenerator(train_file_path, img_w, img_h, batch_size,
downsample_factor)
tiger_train.build_data()
# valid_file_path = './DB/test/'
# tiger_val = TextImageGenerator(valid_file_path, img_w, img_h, val_batch_size, downsample_factor)
# tiger_val.build_data()
ada = tf.keras.optimizers.Adam()
early_stop = EarlyStopping(monitor='loss',
min_delta=0.001,
patience=4,
mode='min',
verbose=1)
checkpoint = ModelCheckpoint(
filepath='LSTM+BN5--{epoch:02d}--{val_loss:.3f}.hdf5',
model = get_Model(training=True)
try:
model.load_weights('./model_OCR/LSTM+BN5--08--1.671.hdf5')
print("...Previous weight data...")
except:
print("...New weight data...")
pass
print(model.summary())
json_train_path = './train_all.json'
tiger_train = TextImageGenerator(json_train_path,
img_w,
img_h,
batch_size,
'train',
downsample_factor,
max_text_len=max_text_len)
#tiger_train.build_data()
json_val_path = './val_all.json'
tiger_val = TextImageGenerator(json_val_path,
img_w,
img_h,
val_batch_size,
'val',
downsample_factor,
max_text_len=max_text_len)
#tiger_val.build_data()
print('>>>>>>>>>>>>>>>>>', val_batch_size)