def logging(model, starttime, batch_size, nb_epoch, conv_arch,dense, dropout,
X_shape, y_shape, train_acc, val_acc, dirpath):
now = time.ctime()
model.save_weights('./')
save_model(model.to_json(), now, dirpath)
save_config(model.get_config(), now, dirpath)
save_result(starttime, batch_size, nb_epoch, conv_arch, dense, dropout,
X_shape, y_shape, train_acc, val_acc, dirpath)
def logging(model, starttime, batch_size, nb_epoch, conv_arch,dense, dropout,
X_shape, y_shape, train_acc, val_acc, dirpath):
now = time.ctime()
model.save_weights('../data/weights/{}'.format(now))
save_model(model.to_json(), now, dirpath)
save_config(model.get_config(), now, dirpath)
save_result(starttime, batch_size, nb_epoch, conv_arch, dense, dropout,
X_shape, y_shape, train_acc, val_acc, dirpath)
model.add(Convolution2D(128, 3, 3, border_mode='same', activation='relu'))
model.add(Convolution2D(128, 3, 3, border_mode='same', activation='relu'))
model.add(Convolution2D(128, 3, 3, border_mode='same', activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Flatten()) # this converts our 3D feature maps to 1D feature vectors
model.add(Dense(64, activation='relu'))
model.add(Dense(64, activation='relu'))
model.add(Dense(2, activation='softmax'))
# optimizer:
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
print('Training....')
model.fit(X_train, y_train, nb_epoch=nb_epoch, batch_size=batch_size,
validation_split=0.3, shuffle=True, verbose=1)
# set callback: https://github.com/sallamander/headline-generation/blob/master/headline_generation/model/model.py
# model result:
loss_and_metrics = model.evaluate(X_train, y_train, batch_size=batch_size, verbose=1)
print ('Done!')
print ('Loss: ', loss_and_metrics[0])
print (' Acc: ', loss_and_metrics[1])
# model logging:
notes = 'medium set 100'
save_model(model.to_json(), '../data/results/')
save_config(model.get_config(), '../data/results/')
save_result(loss_and_metrics, notes, '../data/results/')
print('Training....')
#With validation
#hist = model.fit(X_train, y_train, nb_epoch=nb_epoch, batch_size=batch_size
# , validation_data=(X_val, y_val), shuffle=True, verbose=1)
#Without validation
hist = model.fit(X_train,
y_train,
nb_epoch=nb_epoch,
batch_size=batch_size,
shuffle=True,
verbose=1)
print(model.summary())
train_val_accuracy = hist.history
# set callback: https://github.com/sallamander/headline-generation/blob/master/headline_generation/model/model.py
# model result:
loss_and_metrics = model.evaluate(X_test,
y_test,
batch_size=batch_size,
verbose=1)
print('Loss: ', loss_and_metrics[0])
print(' Acc: ', loss_and_metrics[1])
print(hist.history.keys())
# model logging:
notes = 'medium set 100'
save_model(model, './data/results/')
save_history(train_val_accuracy, './data/results/')
#save_config(model.get_config(), './data/results/')
save_result(train_val_accuracy, loss_and_metrics, notes, './data/results/')
model.add(Convolution2D(128, 3, 3, border_mode='same', activation='relu'))
model.add(Convolution2D(128, 3, 3, border_mode='same', activation='relu'))
model.add(Convolution2D(128, 3, 3, border_mode='same', activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Flatten()) # this converts our 3D feature maps to 1D feature vectors
model.add(Dense(64, activation='relu'))
model.add(Dense(64, activation='relu'))
model.add(Dense(2, activation='softmax'))
# optimizer:
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
print 'Training....'
model.fit(X_train, y_train, nb_epoch=nb_epoch, batch_size=batch_size,
validation_split=0.3, shuffle=True, verbose=1)
# set callback: https://github.com/sallamander/headline-generation/blob/master/headline_generation/model/model.py
# model result:
loss_and_metrics = model.evaluate(X_train, y_train, batch_size=batch_size, verbose=1)
print 'Done!'
print 'Loss: ', loss_and_metrics[0]
print ' Acc: ', loss_and_metrics[1]
# model logging:
notes = 'medium set 100'
save_model(model.to_json(), '../data/results/')
save_config(model.get_config(), '../data/results/')
save_result(loss_and_metrics, notes, '../data/results/')