NormalizationLayer(0, 255, -0.1, 0.1),
LinearLayer(784, 10, weights='norm_random'),
# TanhLayer,
# LinearLayer(50, 10, weights='norm_random'),
# TanhLayer,
# NormalizationLayer(0,10,0,1),
# SigmoidLayer()
])
# display = ShowTraining(epochs_num = epochs)
trainer = Trainer(show_training=False) #, show_function = display.show)
J_list, dJdy_list, J_test = trainer.learn(
model=model,
train=train,
test=test,
# loss = NegativeLogLikelihoodLoss(),
loss=CrossEntropyLoss(),
# loss = SquaredLoss(),
# optimizer = GradientDescent(learning_rate=0.3),
optimizer=GradientDescentMomentum(learning_rate=0.35 / 10, momentum=0.5),
epochs=epochs,
batch_size=10)
test_results(model, train, test)
raw_input('Press ENTER to exit')
model.save('model.net')
data_train = np.random.rand(1000, 2) * 5
train = []
for x in data_train:
out = Q_hat.forward(x)
train.append(
Q_hat.forward(x) * utils.to_one_hot_vect(np.argmax(out), out.size))
data_test = np.random.rand(1000, 2) * 5
test = []
for x in data_test:
out = Q_hat.forward(x)
test.append(
Q_hat.forward(x) * utils.to_one_hot_vect(np.argmax(out), out.size))
J_list, dJdy_list, J_test = trainer.learn(
model=Q,
train=zip(data_train, train),
test=zip(data_test, test),
# loss = NegativeLogLikelihoodLoss(),
# loss = CrossEntropyLoss(),
loss=SquaredLoss(),
# optimizer = GradientDescent(learning_rate=0.3),
optimizer=GradientDescentMomentum(learning_rate=0.35, momentum=0.5),
epochs=epochs,
batch_size=100)
raw_input('Press ENTER to exit')
Q.save('model.net')