def test_forward_backward(self):
l = NormalizationLayer(np.array([0.0, 0.0, -5.0, -2.0]),
np.array([5.0, 5.0, 5.0, 2.0]),
np.array([-1.0, -1.0, -1.0, -1.0]),
np.array([1.0, 1.0, 1.0, 1.0]))
y = l.forward(np.array([5.0, 4.0, -5.0, -1.0]))
self.assertEqual(y.shape, (4, ))
assert_almost_equal(y, np.array([1.0, 0.6, -1.0, -0.5]))
x = np.random.rand(4)
gradient = l.numeric_gradient(x)
l.forward(x)
d = l.backward([1, 1, 1, 1])
self.assertEqual(d.shape, (4, ))
assert_almost_equal(np.diag(gradient), d, decimal=5)
return
p.draw_decision_surface(10, agent.Q, np.array([[0, 0], [5.0, 5.0]]))
plt.show()
else:
# norm = NormalizationLayer(
# np.array([0.0,0.0,0.0,-3.0,-3.0]),
# np.array([5.0,5.0,5.0,3.0,3.0]),
# np.array([-1.0,-1.0,-1.0,-1.0,-1.0]),
# np.array([1.0,1.0,1.0,1.0,1.0])
# )
# norm = NormalizationLayer(
# np.array([0.0,0.0,0.0,-3.0]),
# np.array([5.0,5.0,5.0,3.0]),
# np.array([-1.0,-1.0,-1.0,-1.0]),
# np.array([1.0,1.0,1.0,1.0])
# )
norm = NormalizationLayer(np.array([0.0, 0.0]), np.array([5.0, 5.0]),
np.array([0.0, 0.0]), np.array([1.0, 1.0]))
W1 = utils.SharedWeights('gaussian', 2 + 1, 2)
W2 = utils.SharedWeights('gaussian', 2 + 1, 3)
Q = Sequential(
norm,
LinearLayer(2, 2, weights=W1),
TanhLayer,
LinearLayer(2, 3, weights=W2),
# TanhLayer
)
W3 = utils.SharedWeights('gaussian', 2 + 1, 2)
W4 = utils.SharedWeights('gaussian', 2 + 1, 3)
# W3 = utils.SharedWeights(np.array([[10.0,-10.0,0.0],[-10.0,10.0,0.0]]),2+1,2)
#W2 = utils.SharedWeights('gaussian',2+1,2)
Q_hat = Sequential(
norm,
img1 = ax.imshow(image1, cmap=plt.get_cmap('Greys'))
ax1 = fig.add_subplot(1, 2, 2)
img2 = ax1.imshow(image2, cmap=plt.get_cmap('Greys'))
plt.show()
train = load_mnist_dataset("training", "mnist")
mean_val = [np.zeros(784) for i in range(10)]
tot_val = np.zeros(10)
for x, t in train:
mean_val[np.argmax(t)] += x
tot_val[np.argmax(t)] += 1
normalization_net = Sequential(
NormalizationLayer(0, 255, -1, 1),
SignLayer,
)
for i in range(10):
mean_val[i] = mean_val[i] / tot_val[i]
num = mean_val[i].reshape(28, 28)
plt.imshow(normalization_net.forward(num), cmap=plt.get_cmap('Greys'))
# plt.imshow(num))
plt.show()
hop_net = Hopfield(784)
stored_numers = [0, 1] #numbers stored in the network
for i in stored_numers:
err = 0
for (img, target) in test:
#print str(np.argmax(model.forward(test_data[ind])))+' '+str(np.argmax(test_targets[ind]))
if np.argmax(model.forward(img)) != np.argmax(target):
err += 1
print(1.0 - err / float(len(test))) * 100.0
if load_net:
print "Load Network"
model = StoreNetwork.load(name_net)
else:
print "New Network"
#Two layer network
model = Sequential([
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,
784,
[
{
"size": 32,
"output_layer": TanhLayer,
"weights": W
},
{
"size": 784,
"output_layer": TanhLayer
} #, "weights": W.T()}
])
ae.choose_network([0, 1])
#ae.choose_network()
model = Sequential([
NormalizationLayer(0, 255, -0.1, 0.1),
ae,
NormalizationLayer(-1, 1, 0, 255),
])
plt.figure(12)
plt.figure(13)
train = [(t / 255.0, t / 255.0) for (t, v) in train[:100]]
# train = [(t,t) for (t,v) in train[:100]]
display = ShowTraining(epochs_num=epochs)
trainer = Trainer(show_training=True, show_function=display.show)
J_list, dJdy_list = trainer.learn(