def test_calc_delta(self):
l1 = SoftMaxLayer()
n = Sequential([l1])
x = np.array([15.0, 10.0, 2.0])
y = n.forward(x)
self.assertEqual(y.shape, (3, ))
nll = NegativeLogLikelihoodLoss()
t = np.array([0.0, 0.0, 1.0])
self.assertEqual(y.shape, t.shape)
J1 = nll.loss(y, t)
self.assertEqual(J1.shape, (3, ))
assert_almost_equal(J1, [0.0, 0.0, 13.0067176], decimal=5)
cel = CrossEntropyLoss()
t = np.array([0.0, 0.0, 1.0])
J2 = cel.loss(x, t)
self.assertEqual(J2.shape, (3, ))
assert_almost_equal(J2, [0.0, 0.0, 13.0067176], decimal=5)
delta_in = -nll.dJdy_gradient(y, t)
assert_almost_equal(delta_in, [0.0, 0.0, 445395.349996])
delta_out1 = n.backward(delta_in)
assert_almost_equal(delta_out1, [-0.9933049, -0.0066928, 0.9999978],
decimal=5)
#
delta_out2 = -cel.dJdy_gradient(x, t)
assert_almost_equal(delta_out2, [-0.9933049, -0.0066928, 0.9999978],
decimal=5)
def test_calc_loss(self):
l1 = SoftMaxLayer()
n = Sequential([l1])
x = np.array([15.0, 10.0, 2.0])
y = n.forward(x)
self.assertEqual(y.shape, (3, ))
nll = NegativeLogLikelihoodLoss()
t = np.array([0.0, 0.0, 1.0])
self.assertEqual(y.shape, t.shape)
J = nll.loss(y, t)
self.assertEqual(J.shape, (3, ))
assert_almost_equal(J, [0.0, 0.0, 13.0067176], decimal=5)
def test_numeric_gradient(self):
nll = NegativeLogLikelihoodLoss()
y = np.random.rand(2)
t = np.random.rand(2)
nll.loss(y, t)
gradient = nll.numeric_gradient(y)
dJdy = nll.dJdy_gradient(y, t)
assert_almost_equal(np.diag(gradient), dJdy, decimal=5)
# print_data(1, test_data, test_targets, ['gray','gray','gray','gray'], classes)
# print_data(1, train_data, y1, colors, ['x','x','x','x'])
# print_data(1, train_data, y2, colors, ['x','x','x','x'])
#plt.title('Before Training')
display = ShowTraining(epochs_num=epochs)
trainer = Trainer(show_training=True, show_function=display.show)
t = time.time()
J_train_list, dJdy_list, J_test_list = trainer.learn(
model=model,
train=train,
test=test,
loss=NegativeLogLikelihoodLoss(),
# loss = CrossEntropyLoss(),
# loss = SquaredLoss(),
# optimizer = GradientDescent(learning_rate = 0.15/110),
optimizer=GradientDescentMomentum(learning_rate=0.005, momentum=0.8),
batch_size=100,
epochs=epochs)
elapsed = time.time() - t
print 'Training time: ' + str(elapsed)
y1 = []
for i, (x, target) in enumerate(train):
y1.append(model.forward(x))
#
y2 = []