class Model(Observable, Observer):
def __init__(self, structure):
Observable.__init__(self)
self.neural_net = NeuralNet(structure, random_init_bound=0.05)
self.commands = []
def load(self, path):
self.neural_net.load(path)
def predict(self, x):
return self.neural_net.evaluate(x)
def update(self, command):
self.notify_observers()
def add_command(self, command):
self.commands.append(command)
command.add_observer(self)
self.notify_observers()
def undo(self):
if self.commands:
self.commands.pop()
self.notify_observers()
def clear(self):
self.commands.clear()
self.notify_observers()
cumulative_acc = 0
# k-Fold Cross validation
kf = KFold(n_splits=splits, shuffle=True)
for i, (train_index, test_index) in enumerate(kf.split(x)):
x_train, x_test = x[train_index], x[test_index]
y_train, y_test = y[train_index], y[test_index]
_cost, _accuracy = nnet.train(x_train,
y_train,
epochs=epochs,
alpha=alpha,
reg_para=reg_para,
batch_size=batch_size,
print_details=False,
epochs_bw_details=epochs_bw_details,
dropout=dropout_percent,
dropout_layers=d_layers)
op = nnet.predict(x_test)
cumulative_acc += nnet.evaluate(op, y_test)
print("-" * 30 + "\nKFold #{0}\n".format(i) + "-" * 30)
print(classification_report(y_test.argmax(axis=1), op.argmax(axis=1)))
print()
print("Mean cross validation accuracy = {0}".format(cumulative_acc / splits))
s = input("Dump model? (y/n)\n")
if s == 'y':
nnet.dump()
