if optimizer == 'padam':
optim = Padam(learning_rate=learning_rate, p=op['p'], beta1=op['b1'], beta2=op['b2'])
elif optimizer == 'adam':
optim = tf.train.AdamOptimizer(learning_rate=learning_rate, beta1=op['b1'], beta2=op['b2'])
elif optimizer == 'adamw':
# adamw = tf.contrib.opt.extend_with_decoupled_weight_decay(tf.train.AdamOptimizer)
optim = tf.contrib.opt.AdamWOptimizer(weight_decay=op['weight_decay'], learning_rate=learning_rate, beta1=op['b1'], beta2=op['b2'])
elif optimizer == 'amsgrad':
optim = AMSGrad(learning_rate=learning_rate, beta1=op['b1'], beta2=op['b2'])
elif optimizer == 'sgd':
optim = tf.train.MomentumOptimizer(learning_rate=learning_rate, momentum=op['m'])
model.compile(optimizer=optim, loss='categorical_crossentropy', metrics=['accuracy', 'top_k_categorical_accuracy'], global_step=tf.train.get_global_step())
csv_logger = CSVLogger(logfile, append=True, separator=';')
history[optimizer] = model.fit_generator(datagen_train.flow(trainX, trainY, batch_size = batch_size), epochs = epochs,
validation_data = datagen_test.flow(testX, testY, batch_size = batch_size), verbose=1, callbacks = [csv_logger])
scores = model.evaluate_generator(datagen_test.flow(testX, testY, batch_size = batch_size), verbose=1)
print("Final test loss and accuracy:", scores)
# filepath = 'model_'+optimizer+'_' + dataset + '.h5'
save_model(save_model_filepath, model)
# f.close()
#train plot
plt.figure(1)
"""
from keras.preprocessing.image import *
from prepare_data import *
from loss_and_metrics import *
from model import VGG
from keras.models import *
from keras.callbacks import *
import config as cf
train_x,train_y,val_x,val_y = create_data()
model = VGG(shape=(64, 256, 1))
model.summary()
model.compile(loss = custom_loss,
optimizer='adam',
metrics=[char_acc,image_acc])
datagen = ImageDataGenerator(width_shift_range=0.14,
height_shift_range=0.08,
fill_mode='constant',
zoom_range = 0.1,
rotation_range = 10,
#rescale =1./255
)
mcp_save = ModelCheckpoint(cf.CKP_PATH, save_best_only=True, monitor='val_loss', mode='min',verbose=1)
def scheduler(epoch):
if epoch <4 :
return 0.001
elif epoch < 10:
