from conceptors.net import ConceptorNetwork;
from conceptors.dataset import read_jpv_data;
from conceptors.dataset import normalize_jap_data;
from conceptors.dataset import transform_jap_data;
train_inputs, train_outputs, test_inputs, test_outputs=read_jpv_data("/home/arlmaster/workspace/conceptors/conceptors/data/ae.train",
"/home/arlmaster/workspace/conceptors/conceptors/data/ae.test");
train_data, shifts, scales=normalize_jap_data(train_inputs);
test_data=transform_jap_data(test_inputs, shifts, scales);
# Create conceptor network
net=ConceptorNetwork(2, 200);
# Prepare testing data
p1=np.asarray(xrange(2000));
p1=np.sin(2*np.pi*p1/np.sqrt(75));
p2=np.asarray(xrange(2000));
#p2=0.5*np.sin(2*np.pi*p2/np.sqrt(20))+np.sin(2*np.pi*p2/np.sqrt(40));
p2=np.sin(2*np.pi*p2/np.sqrt(40));
ps=np.vstack((p1[None], p2[None]));
p=[];
p.append(ps);
#p.append(p1[None]);
#p.append(p2[None]);
# training
if not x_temp.size:
x_temp=Xtrain[idx,1:];
else:
x_temp=np.vstack((x_temp, Xtrain[idx,1:]));
idx+=1;
print "Class %i is generated" % i;
X.append(x_temp.T);
n_in=X[0].shape[0];
num_neuron=500;
net=ConceptorNetwork(num_in=n_in,
num_neuron=num_neuron,
washout_length=200,
learn_length=700);
print "the network is created";
net.train(X);
print "the network is trained";
conceptors=net.Cs[0];
img=Xtest[1];
pos_evidence=np.zeros((1, len(conceptors)));
for i in xrange(len(conceptors)):
from conceptors.net import ConceptorNetwork;
from conceptors.dataset import read_jpv_data;
from conceptors.dataset import normalize_jap_data;
from conceptors.dataset import transform_jap_data;
#train_inputs, train_outputs, test_inputs, test_outputs=read_jpv_data("/home/arlmaster/workspace/conceptors/conceptors/data/ae.train",
# "/home/arlmaster/workspace/conceptors/conceptors/data/ae.test");
#train_data, shifts, scales=normalize_jap_data(train_inputs);
#test_data=transform_jap_data(test_inputs, shifts, scales);
# Create conceptor network
net=ConceptorNetwork(2, 200);
# Prepare testing data
p1=np.asarray(xrange(2000));
p1=np.sin(2*np.pi*p1/np.sqrt(75));
p2=np.asarray(xrange(2000));
#p2=0.5*np.sin(2*np.pi*p2/np.sqrt(20))+np.sin(2*np.pi*p2/np.sqrt(40));
p2=np.sin(2*np.pi*p2/np.sqrt(40));
ps=np.vstack((p1[None], p2[None]));
p=[];
p.append(ps);
#p.append(p1[None]);
#p.append(p2[None]);
# training
while idx != num_train and Xtrain[idx, 0] == i:
if not x_temp.size:
x_temp = Xtrain[idx, 1:]
else:
x_temp = np.vstack((x_temp, Xtrain[idx, 1:]))
idx += 1
print "Class %i is generated" % i
X.append(x_temp.T)
n_in = X[0].shape[0]
num_neuron = 500
net = ConceptorNetwork(num_in=n_in,
num_neuron=num_neuron,
washout_length=200,
learn_length=700)
print "the network is created"
net.train(X)
print "the network is trained"
conceptors = net.Cs[0]
img = Xtest[1]
pos_evidence = np.zeros((1, len(conceptors)))
for i in xrange(len(conceptors)):