from nimblenet.cost_functions import cross_entropy_cost
from nimblenet.learning_algorithms import *
from nimblenet.neuralnet import NeuralNet
from nimblenet.preprocessing import construct_preprocessor, standarize
from nimblenet.data_structures import Instance
from nimblenet.tools import print_test
# Training set
dataset = [
Instance([0, 0], [0]),
Instance([1, 0], [1]),
Instance([0, 1], [1]),
Instance([1, 1], [1])
]
preprocess = construct_preprocessor(dataset, [standarize])
training_data = preprocess(dataset)
test_data = preprocess(dataset)
cost_function = cross_entropy_cost
settings = {
# Required settings
"n_inputs": 2, # Number of network input signals
"layers": [(3, sigmoid_function), (1, sigmoid_function)],
# [ (number_of_neurons, activation_function) ]
# The last pair in the list dictate the number of output signals
# Optional settings
"initial_bias_value": 0.0,
"weights_low": -0.1, # Lower bound on the initial weight value
"weights_high": 0.1, # Upper bound on the initial weight value
accel_scaled_z)
last_x = K * (last_x + gyro_x_delta) + (K1 * rotation_x)
last_y = K * (last_y + gyro_y_delta) + (K1 * rotation_y)
#[X1,Y1,X2,Y2]
nSlice.append(last_x)
nSlice.append(last_y)
#When N values have been recorded
if len(nSlice) == N:
##----------Predictions------------
#Throws nSlice to Belle
inData = [Instance(nSlice)]
preprocess = construct_preprocessor(inData, [standarize])
prediction_set = preprocess(inData)
#Prints a prediction!
#HIGH LOW = Bicep Curl!
#LOW HIGH = Trash!
#print(str(nSlice[0]) + ", " + str(nSlice[1]))
neuralOut = network.predict(inData)
print(neuralOut)
exponents = np.floor(np.log10(np.abs(neuralOut)))
##----------Total Movement Calculation--------
temp_x = nSlice[0]
temp_y = nSlice[1]
total = 0
for i in range(len(nSlice)):
if i % 2 == 0:
from nimblenet.activation_functions import sigmoid_function, tanh_function, linear_function, LReLU_function, ReLU_function, elliot_function, symmetric_elliot_function, softmax_function, softplus_function, softsign_function
from nimblenet.cost_functions import sum_squared_error, cross_entropy_cost, hellinger_distance, softmax_neg_loss
from nimblenet.learning_algorithms import backpropagation, scaled_conjugate_gradient, scipyoptimize, resilient_backpropagation
from nimblenet.evaluation_functions import binary_accuracy
from nimblenet.neuralnet import NeuralNet
from nimblenet.preprocessing import construct_preprocessor, standarize, replace_nan, whiten
from nimblenet.data_structures import Instance
from nimblenet.tools import print_test
# Training sets
dataset = [ Instance( [0,0], [0] ), Instance( [1,0], [1] ), Instance( [0,1], [1] ), Instance( [1,1], [0] ) ]
preprocess = construct_preprocessor( dataset, [standarize] )
training_data = preprocess( dataset )
test_data = preprocess( dataset )
cost_function = cross_entropy_cost
settings = {
# Required settings
"n_inputs" : 2, # Number of network input signals
"layers" : [ (3, sigmoid_function), (1, sigmoid_function) ],
# [ (number_of_neurons, activation_function) ]
# The last pair in the list dictate the number of output signals
# Optional settings
"weights_low" : -0.1, # Lower bound on the initial weight value
"weights_high" : 0.1, # Upper bound on the initial weight value
}