def run():
net = NeuralNet(2,1)
plotInput(net)
for i in range(5):
print net.getTheta()
plotOutputMap(net,i*2)
net.train()
net.train()
plotOutputMap(net,10)
def initNNController(rs, thetaFile):
'''
Initializes the controller allowing to compute the output from the input and the vector of parameters theta
Input: -rs: ReadSetupFile, parameters
'''
#Initializes the function approximator
fa = NeuralNet(rs.inputDim, rs.outputDim)
fa.loadTheta(thetaFile + ".theta")
return fa
def initNNController(rs,thetaFile):
'''
Initializes the controller allowing to compute the output from the input and the vector of parameters theta
Input: -rs: ReadSetupFile, parameters
'''
#Initializes the function approximator
fa = NeuralNet(rs.inputDim,rs.outputDim)
fa.loadTheta(thetaFile+".theta")
return fa
def runNN(name):
'''
Takes the Brent trajectories as input, shuffles them, and then runs the NN regression algorithm
'''
rs = ReadSetupFile()
#state, command = getStateAndCommandData(BrentTrajectoriesFolder)
#stateAll, commandAll = dicToArray(state), dicToArray(command)
#print ("old:", stateAll[0])
stateAll, commandAll = stateAndCommandDataFromTrajs(
loadStateCommandPairsByStartCoords(pathDataFolder + "TrajRepository/"))
#stateAll, commandAll = stateAndCommandDataFromTrajs(loadStateCommandPairsByStartCoords(BrentTrajectoriesFolder))
#print ("len:", len(commandAll[0]))
stateAll = np.vstack(np.array(stateAll))
commandAll = np.vstack(np.array(commandAll))
#print ("len global:", len(commandAll))
#print ("new:", commandAll[0])
#this works because both shuffles generate the same order, due to the seed
np.random.seed(0)
np.random.shuffle(stateAll)
np.random.seed(0)
np.random.shuffle(commandAll)
print("nombre d'echantillons: ", len(stateAll))
fa = NeuralNet(rs.inputDim, rs.outputDim)
fa.getTrainingData(stateAll, commandAll)
fa.train()
fa.saveTheta(rs.NNpath + name + ".theta")
def runNN(name):
'''
Takes the Brent trajectories as input, shuffles them, and then runs the NN regression algorithm
'''
rs = ReadSetupFile()
#state, command = getStateAndCommandData(BrentTrajectoriesFolder)
#stateAll, commandAll = dicToArray(state), dicToArray(command)
#print ("old:", stateAll[0])
stateAll, commandAll = stateAndCommandDataFromTrajs(loadStateCommandPairsByStartCoords(pathDataFolder + "TrajRepository/"))
#stateAll, commandAll = stateAndCommandDataFromTrajs(loadStateCommandPairsByStartCoords(BrentTrajectoriesFolder))
#print ("len:", len(commandAll[0]))
stateAll = np.vstack(np.array(stateAll))
commandAll = np.vstack(np.array(commandAll))
#print ("len global:", len(commandAll))
#print ("new:", commandAll[0])
#this works because both shuffles generate the same order, due to the seed
np.random.seed(0)
np.random.shuffle(stateAll)
np.random.seed(0)
np.random.shuffle(commandAll)
print("nombre d'echantillons: ", len(stateAll))
fa = NeuralNet(rs.inputDim,rs.outputDim)
fa.getTrainingData(stateAll, commandAll)
fa.train()
fa.saveTheta(rs.NNpath + name+".theta")
def UnitTestNN():
fa = NeuralNet(2,3)
input, output = [], []
for i in range(10000):
x,y = rd.random(), rd.random()
input.append([x,y])
output.append([x*y, x-y, x+y])
fa.getTrainingData(np.vstack(np.array(input)), np.vstack(np.array(output)))
fa.train()
fa.saveTheta("test.theta")
fa.loadTheta("test.theta")
for i in range(20):
x,y = 3*rd.random(), 3*rd.random()
approx = fa.computeOutput(np.array([x,y]))
print("in:", [x,y])
print(" out:", approx)
print(" real:", [x*y, x-y, x+y])
def run():
net = NeuralNet(2, 1)
plotInput(net)
for i in range(5):
print net.getTheta()
plotOutputMap(net, i * 2)
net.train()
net.train()
plotOutputMap(net, 10)
def UnitTestNN():
fa = NeuralNet(2, 3)
input, output = [], []
for i in range(10000):
x, y = rd.random(), rd.random()
input.append([x, y])
output.append([x * y, x - y, x + y])
fa.getTrainingData(np.vstack(np.array(input)), np.vstack(np.array(output)))
fa.train()
fa.saveTheta("test.theta")
fa.loadTheta("test.theta")
for i in range(20):
x, y = 3 * rd.random(), 3 * rd.random()
approx = fa.computeOutput(np.array([x, y]))
print("in:", [x, y])
print(" out:", approx)
print(" real:", [x * y, x - y, x + y])
def saveRandomNN():
rs = ReadSetupFile()
fa = NeuralNet(rs.inputDim, rs.outputDim)
fa.saveTheta(rs.NNpath + "Random.theta")
def createNN(name):
rs = ReadSetupFile()
fa = NeuralNet(rs.inputDim,rs.outputDim)
fa.saveTheta(rs.NNpath + name+".theta")
def saveRandomNN():
rs = ReadSetupFile()
fa = NeuralNet(rs.inputDim,rs.outputDim)
fa.saveTheta(rs.NNpath+"Random.theta")
def createNN(name):
rs = ReadSetupFile()
fa = NeuralNet(rs.inputDim, rs.outputDim)
fa.saveTheta(rs.NNpath + name + ".theta")