def main():
capture_layer = CaptureLayer()
input_layer = InputLayer()
control_layer = ControlLayer()
main_loop = True
capture_thread = Process(target=capture_layer.run_capture)
serial_thread = Process(target=serial_control)
capture_thread.start()
serial_thread.start()
last_busy = 1
while main_loop:
shape = capture_layer.marker_shape[:]
input_layer.update(shape, motor_busy.value)
control_layer.update(input_layer)
control_vector[0:3] = control_layer.get_control_vector()
if last_busy != motor_busy.value:
last_busy = motor_busy.value
print("BUSY" if motor_busy.value else "FREE")
if control_vector[1] != 0:
print("%d cm, %.1f deg" % (input_layer.distance_cm, input_layer.angle_deg)," "*8)
print("desired %d cm = %d steps" % (control_layer.desired_cm, control_vector[1]),
"conf: %.2f" % input_layer.distance_filter.confidence())
sleep(0.020)
def __init__(self, userid):
self.inputLayer = InputLayer()
self.hiddenLayers = []
self.outputLayer = OutputLayer()
self.userid = userid
self.outputs = []
def __init__(self, train_x, train_y, test_x, test_y):
self.train_x = train_x
self.train_y = train_y
self.test_x = test_x
self.test_y = test_y
self.preprocess()
self.input_layer = InputLayer(self.train_x.shape[1])
self.output_layer = OutputLayer(len(self.train_y), self.input_layer)
self.input_layer.prev_layer = self.output_layer
self.accuracy = 0
self.loss = 0
self.add_layer(LayerDense(self.train_x.shape[1], 64))
self.add_layer(LayerDense(64, 32))
self.add_layer(LayerDense(32, len(self.train_y)))
self.optimizer = OptimizerAdam(learning_rate=0.05, decay=5e-7)
def build_neural_network(opencl_context, inputs, targets, layers,
learning_rate, regulization):
input_layer = InputLayer(inputs, opencl_context)
model_layers = []
model_layers.append(input_layer)
for i in range(len(layers) - 1):
layer = Layer(layers[i], np.tanh, learning_rate, regulization,
opencl_context)
layer.link_prev(model_layers[-1])
model_layers.append(layer)
#add output layer
layer = Layer(layers[-1], np.exp, learning_rate, regulization,
opencl_context)
layer.link_prev(model_layers[-1])
model_layers.append(layer)
return model_layers
def __init__(self,
layers,
l2_decay=0.001,
debug=False,
learning_rate=0.001):
super(Network, self).__init__()
mapping = {
"input": lambda x: InputLayer(x),
"fc": lambda x: FullyConnectedLayer(x),
"convolution": lambda x: ConvLayer(x),
"pool": lambda x: MaxPoolLayer(x),
"squaredloss": lambda x: SquaredLossLayer(x),
"softmax": lambda x: SoftmaxLayer(x),
"relu": lambda x: ReLULayer(x),
"dropout": lambda x: DropoutLayer(x)
}
self.layers = []
self.l2_decay = l2_decay
self.debug = debug
self.learning_rate = learning_rate
def __init__(self, n_input, n_output):
self.input_layer = InputLayer(n_input)
self.output_layer = OutputLayer(n_output, self.input_layer)
self.input_layer.prev_layer = self.output_layer
self.accuracy = 0
self.loss = 0
round((random.uniform(0.4, 0.6)), 5) for _ in range(QUANTITY_INPUT)
]
weight_relation_vector.append(t)
return weight_relation_vector
if __name__ == '__main__':
epoch = 10
size_sample = 100
quantity_cluster = 5
output_layer = OutputLayer(form_weight_relation(quantity_cluster),
quantity_cluster)
input_layer = InputLayer(form_sample(size_sample),
output_layer,
size_sample=size_sample)
help_epoch = []
help_function = []
speed_function_start = 0.5
delta_function_start = 0.5
for i in range(epoch):
delta_function = (-i / (epoch + 1) + 1)
#delta_function = 1
speed_function = speed_function_start * e**(i / epoch)
k = input_layer.epoch(output_layer.weight_relation_vector,
output_layer.quantity_cluster, delta_function,
speed_function)
def __init__(self, num_units):
self.layers = [InputLayer(num_units)]
}
graph = topological_sort(feed_dict)
output = forward_pass(f, graph)
logging.info(output)
print(output)
# Layer
import numpy as np
from input_layer import InputLayer
from linear_layer import LinearLayer
from helper_layer import *
print("Layer Linear Transform")
inputs, weights, bias = InputLayer(), InputLayer(), InputLayer()
f = LinearLayer(inputs, weights, bias)
x = np.array([[-1., -2.], [-1, -2]])
w = np.array([[2., -3], [2., -3]])
b = np.array([-3., -5])
feed_dict = {inputs: x, weights: w, bias: b}
graph = topological_sort_layer(feed_dict)
output = forward_pass_layer(f, graph)
logging.info(output)
print(output)
# Sigmoid
from sigmoid import Sigmoid
from neural_network import NeuralNetwork
from input_layer import InputLayer
from output_layer import OutputLayer
from hidden_layer import HiddenLayer
# test train xor function
model = NeuralNetwork(InputLayer(2), HiddenLayer(2, "sigmoid"),
OutputLayer(1, "sigmoid"))
train_input = [[1, 1], [1, 0], [0, 1], [0, 0]]
train_output = [0, 1, 1, 0]
model.train(train_input, train_output, 1, 0.1, 20)
model.predict([1, 1])
model.predict([1, 0])
model.predict([0, 1])
model.predict([0, 0])
