def verifier(transmitted_message, g):
# 1-Doing XOR between transmitted message and generator
r = XOR(transmitted_message, g)
if(int(r) > 0):
verification = "Message is transmitted incorrectly, there is an error."
else:
verification = "Message is transmitted correctly."
return verification
def generator(message, g):
# 1-Adding necessary zeros to the message
original_message = message
appendedZerosLength = len(g) - 1
for x in range(appendedZerosLength):
message = message + "0"
# 2-Doing XOR between message and generator
r = XOR(message, g)
print("Part appended to message before transmitting: " + r)
transmittedMessage = original_message + r
return {'transmitted_message': transmittedMessage, 'r': r}
input_indices.append(gate[4])
# E7na hena bn3ml objects mn el classes elly 3ndna
for i in range(len(connected_gates)):
if connected_gates[i][3] == 0:
Gates.append(
AND(connected_gates[i][0], connected_gates[i][1],
connected_gates[i][2], connected_gates[i][3]))
elif connected_gates[i][3] == 1:
Gates.append(
OR(connected_gates[i][0], connected_gates[i][1],
connected_gates[i][2], connected_gates[i][3]))
elif connected_gates[i][3] == 2:
Gates.append(
XOR(connected_gates[i][0], connected_gates[i][1],
connected_gates[i][2], connected_gates[i][3]))
elif connected_gates[i][3] == 3:
Gates.append(
NOT(connected_gates[i][0], connected_gates[i][2],
connected_gates[i][3]))
# Hena bn7dd 3ndna kam input
gate_index = 0
for index in input_indices:
if Gates[index].gtype == 3:
if Gates[index].input1 == None:
input_counter += 1
starting_gates.append(gate_index)
names_of_inputs.append(gate_type[Gates[index].gtype] + " inp1")
def halfAdder(x1, x2):
c = AND(x1, x2)
s = XOR(x1, x2)
return s, c # return sum carryout
"""
class RnnRbm(RnnRbm):
def __init__(self, n_hidden=150, n_hidden_recurrent=100, lr=0.001, dt=0.3):
v, v_sample, cost, monitor, params, updates_train, v_t,updates_generate = build_rnnrbm(2, n_hidden, n_hidden_recurrent)
self.dt = dt
gradient = T.grad(cost, params, consider_constant=[v_sample])
updates_train.update(((p, p - lr * g) for p, g in zip(params, gradient)))
self.train_function = theano.function([v], monitor, updates=updates_train)
self.generate_function = theano.function([], v_t, updates=updates_generate)
def train(self, files, batch_size=100, num_epochs=200):
"""
###############################
#### Setting for dataset ####
###############################
dataset = XOR(size=30, type='seq')
train_data = dataset.get_batch_design(10)
print len(train_data)
########################
#### Pre training ####
########################
### First layer ###
rbm = RnnRbm(nvis=2, nhid=4, nhid_recurrent=3)
# rbm = RnnRbm(n_hidden=4, n_hidden_recurrent=3)
print ''
# for param in rbm.get_params():
# print '------ ' + str(param) + ' -----'
# print param.get_value()