def main(train, test, out):
TRAIN_FILE = train
TEST_FILE = test
OUT_FILE = out
img = Image.open(TRAIN_FILE) # read double moons image from .png file
pixels = img.load() # generate pixel map
width = img.size[0]
height = img.size[1]
training_set = dict()
for i in range(width):
for j in range(height):
if pixels[i,j] == BLUE: # if pixel is blue
training_set[i,j] = BOT # set value to bottom
elif pixels[i,j] == RED: # if pixel is red
training_set[i,j] = TOP # set value to top
# create neuron with 2 input nodes
n = Neuron(2) # x-input, y-input
print "Neuron created."
# training
print "Training..."
counter = 0
while True:
errors = 0
for p in training_set:
errors += n.train_step(p, training_set[p])
counter += 1
print "====="
if errors < n.get_margin() * len(training_set):
break
print "Length of training set: " + str(len(training_set))
print "Iterations: " + str(counter)
# test cases
img = Image.open(TEST_FILE)
pixels = img.load()
width = img.size[0]
height = img.size[1]
for i in range(width):
for j in range(height):
if pixels[i,j] == BLACK:
n.set_input(0, i)
n.set_input(1, j)
n.activate()
ans = n.get_output()
if ans == TOP:
pixels[i,j] = RED
elif ans == BOT:
pixels[i,j] = BLUE
img.save(OUT_FILE, "PNG")
def main(train, test, out):
TRAIN_FILE = train
TEST_FILE = test
OUT_FILE = out
img = Image.open(TRAIN_FILE) # read double moons image from .png file
pixels = img.load() # generate pixel map
width = img.size[0]
height = img.size[1]
training_set = dict()
for i in range(width):
for j in range(height):
if pixels[i, j] == BLUE: # if pixel is blue
training_set[i, j] = BOT # set value to bottom
elif pixels[i, j] == RED: # if pixel is red
training_set[i, j] = TOP # set value to top
# create neuron with 2 input nodes
n = Neuron(2) # x-input, y-input
print "Neuron created."
# training
print "Training..."
counter = 0
while True:
errors = 0
for p in training_set:
errors += n.train_step(p, training_set[p])
counter += 1
print "====="
if errors < n.get_margin() * len(training_set):
break
print "Length of training set: " + str(len(training_set))
print "Iterations: " + str(counter)
# test cases
img = Image.open(TEST_FILE)
pixels = img.load()
width = img.size[0]
height = img.size[1]
for i in range(width):
for j in range(height):
if pixels[i, j] == BLACK:
n.set_input(0, i)
n.set_input(1, j)
n.activate()
ans = n.get_output()
if ans == TOP:
pixels[i, j] = RED
elif ans == BOT:
pixels[i, j] = BLUE
img.save(OUT_FILE, "PNG")
class OutputLayer:
"""
Represents the output layer of the network.
"""
def __init__(self, inputLayer):
""""
Constructor for OutputLayer class.
:param inputLayer: the input layer in the network.
"""
self.inputLayer = inputLayer
# Initialize weights as zeros
weights = const.INIT_WEIGHTS
if self.inputLayer.bias:
weights.append(0)
# Create output neuron
self.neuron = Neuron(neighbors=inputLayer.neurons,
weights=weights,
output=True)
def add_vector_to_weights(self, vector):
"""
Changes the weights of a neuron by adding a vector to the weights vector.
:param vector: vector to add to the weights
:returns: None
"""
for index in range(len(vector)):
self.neuron.weights[index] += vector[index]
def get_output(self, inputs):
"""
Feeds the inputs to the input layer and then its output to the output layer.
:param inputs: the inputs to the network.
:returns: Returns the networks output.
"""
output = self.inputLayer.get_outputs(inputs)
return self.neuron.get_output(output)
