nnadl=True)
from pymri.model import FNN
# create Classifier
cls = FNN(type='FNN simple',
input_layer_size=784,
hidden_layer_size=46,
output_layer_size=2,
epochs=100,
mini_batch_size=11,
learning_rate=3.0,
verbose=True)
# split dataset
training_data, test_data, valid_data = dataset.split_data(sizes=(0.75, 0.25))
# train and test classifier
cls.train_and_test(training_data, test_data)
accuracy = cls.get_accuracy()
print('accuracy = %0.2f' % accuracy)
##############################################################################
#
# FITNESS FUCNTION
#
##############################################################################
from pymri.genetic_algorithm import get_prob_class
# the goal ('fitness') function to be maximized
import numpy as np
accuracies = np.zeros(shape=(n_times_LeavePOut,))
for i in range(n_times_LeavePOut):
print('testing iteration: %d' % i)
###########################################################################
#
# SPLIT DATA
#
###########################################################################
# get training, validation and test datasets for specified roi
# training_data, validation_data, test_data = ds.split_data()
training_data, test_data, vd = ds.split_data(sizes=(0.75,0.25))
###########################################################################
#
# CREATE MODEL
#
###########################################################################
# artificial neural network
from pymri.model import fnn
net = fnn.Network([k_features, hidden_neurons, 2])
# train and test network
net.SGD(training_data, epochs, minibatch_size, eta, test_data=test_data)
# record the best result
accuracies[i] = net.best_score/float(len(test_data))
import numpy as np
accuracies = np.zeros(shape=(n_times_LeavePOut, ))
for i in range(n_times_LeavePOut):
print('testing iteration: %d' % i)
###########################################################################
#
# SPLIT DATA
#
###########################################################################
# get training, validation and test datasets for specified roi
# training_data, validation_data, test_data = ds.split_data()
training_data, test_data, vd = ds.split_data(sizes=(0.75, 0.25))
###########################################################################
#
# CREATE MODEL
#
###########################################################################
# artificial neural network
from pymri.model import fnn
net = fnn.Network([k_features, hidden_neurons, 2])
# train and test network
net.SGD(training_data, epochs, minibatch_size, eta, test_data=test_data)
# record the best result
accuracies[i] = net.best_score / float(len(test_data))
# create Classifier
cls = FNN(
type='FNN simple',
input_layer_size=k_features,
hidden_layer_size=46,
output_layer_size=2,
epochs=100,
# epochs=10,
mini_batch_size=11,
learning_rate=3.0,
verbose=True
)
# split dataset
training_data, test_data, valid_data = dataset.split_data(
sizes=(0.75, 0.25)
)
# train and test classifier
cls.train_and_test(training_data, test_data)
accuracy = cls.get_accuracy()
print('accuracy = %0.2f' % accuracy)
##############################################################################
#
# GENETIC ALGORITHM SETUP
#
##############################################################################
