def _conv1x1_forward(conv, x, is_incremental):
"""Conv1x1 forward
"""
if is_incremental:
x = conv.incremental_forward(x)
else:
x = conv(x)
return x
def main():
move_old = load("move")
auto_old = load("auto")
on_old = load("on")
superdecorate("CONVOLUTIONAL MAZE RUNNER ROBOT")
imp(None, on_old)
imp(auto_old, None)
while(1):
# Check if there is any change in mode or status
on, auto = load("on"), load("auto")
if(on != on_old):
imp(None, on)
if(auto != auto_old):
imp(auto, None)
while (load("on")=="1" and load("auto")=="1"):
# Load Data
decorate("Loading Data")
coord = load("coord").split(' ')
x0, y0 = int(coord[0]), int(coord[1])
x1, y1 = int(coord[2]), int(coord[3])
print("Starting Point: (" + str(x0) + "," + str(y0) + ")")
print("Ending Point: (" + str(x1) + "," + str(y1) + ")")
# Conv Neural Network
decorate("Running Convolutional Neural Network")
maze = conv(0)
print("Walls detected:")
print(maze)
# A* Pathfinding Algorithm
decorate("Running A* Pathfinding Algorithm")
start = (x0, y0)
end = (x1, y1)
path = astar(maze, start, end)
print("Shortest path found: " + str(path))
# Encoder
decorate("Encoding Data")
orders = encoder(path)
print("Orders encoded: " + str(orders))
# Send orders via Bluetooth
decorate("Sending orders to Robot")
blue_auto(orders)
print("Orders sent")
# Change mode to OFF
write("on",0)
while (load("on")=="1" and load("auto")=="0"):
# Load manual control
move = load("move")
if (move != move_old):
imp(move, None)
# Send orther via bluetoooth
blue_manual(move)
t.sleep(0.5)
move_old = move
t.sleep(0.5)
on_old, auto_old = on, auto
#!/usr/bin/python from fft import * from conv import * from test import rnd_data import time n = 2**11 t0 = time.time() conv(rnd_data(n), rnd_data(n)) t1 = time.time() print t1-t0 t0 = time.time() conv_simple(rnd_data(n), rnd_data(n)) t1 = time.time() print t1-t0
def test_conv_returns_keras_sequential_model():
assert isinstance(conv(3, (28, 28, 1)), keras.engine.sequential.Sequential)
def test_conv_and_conv_simple_return_the_same(self):
c1 = conv_simple(self.a, self.b)
c2 = conv (self.a, self.b)
for i in range(self.n):
self.assertAlmostEqual(c1[i], c2[i])
train_and_adjust(training_inputs, training_outputs, training_epochs)
## THIS IS THE PLACE WHERE THE AI IS TESTED ###########################################
==================================================================================="""
l1_filter = numpy.zeros((2, 3, 3)) # Creates 2 number filters, each with 3 rows and 3 columns
l1_filter[0, :, :] = numpy.array([[[-1, 0, 1, ], # creates the first array detecting vertical edges
[-1, 0, 1, ],
[-1, 0, 1, ]]])
l1_filter[1, :, :] = numpy.array([[[1, 1, 1], # creates the second array detecting horizontal edges
[0, 0, 0],
[-1, -1, -1]]])
l1_feature_map = conv(image, l1_filter) # Convolves image according to conv function and the l1 filter
l1_feature_map_relu = relu(l1_feature_map)
l1_feature_map_relu_pool = pooling(l1_feature_map_relu, 2, 2)
# Second conv layer
l2_filter = numpy.random.rand(3, 5, 5, l1_feature_map_relu_pool.shape[-1])
print("\n**Working with conv layer 2**")
l2_feature_map = conv(l1_feature_map_relu_pool, l2_filter)
print("\n**ReLU**")
l2_feature_map_relu = relu(l2_feature_map)
print("\n**Pooling**")
img_gauss = np.zeros((img.shape[0], img.shape[1], 3))
if mode_conv == "valid":
img_gauss = np.zeros(
(img.shape[0] - len(kernel) + 1, img.shape[1] - len(kernel) + 1, 3))
sep_filter_0 = np.zeros((size, 1))
for i in range(size):
sep_filter_0[i, 0] = Gauss_fun(sigma, i - size // 2)
sep_filter_0 = sep_filter_0 / np.sum(sep_filter_0)
sep_filter_1 = sep_filter_0.T
img_gauss1d = img_gauss.copy()
img_sharp = img_gauss.copy()
img_bi = img_gauss.copy()
for i in range(3):
img_gauss[:, :, i] = conv(image=img[:, :, i],
kernel=kernel,
mode_conv=mode_conv,
mode_padding=mode_padding)
for i in range(3):
img_bi[:, :, i] = Bilateral_Filter(image=img[:, :, i],
sigma_s=sigma,
sigma_r=sigma_r,
size=size,
mode_conv=mode_conv,
mode_padding=mode_padding)
for i in range(3):
img_gauss1d[:, :, i] = conv(image=img[:, :, i],
kernel=sep_filter_0,
mode_conv=mode_conv,
mode_padding=mode_padding)
for i in range(3):
