def __call__(self, nn, train_history):
current_valid = train_history[-1]['valid_loss']
current_epoch = train_history[-1]['epoch']
if current_valid < self.best_valid:
self.best_valid = current_valid
self.best_valid_epoch = current_epoch
self.best_weights = nn.get_all_params_values()
elif self.best_valid_epoch + self.patience < current_epoch:
print("Early stopping.")
print("Best valid loss was {:.6f} at epoch {}.".format(
self.best_valid, self.best_valid_epoch))
nn.load_params_from(self.best_weights)
raise StopIteration()
dense_num_units=512,
dense_nonlinearity=lasagne.nonlinearities.rectify,
# dropout2
dropout2_p=0.5,
# output
output_nonlinearity=lasagne.nonlinearities.softmax,
output_num_units=2,
# optimization method params
update=nesterov_momentum,
update_learning_rate=0.05,
update_momentum=0.9,
max_epochs=10,
verbose=1)
# Train the network
nn = net1.fit(X, Y)
# Train the network
nn = net1.fit(X, Y)
#Visualize the feature
visualize.plot_conv_weights(net1.layers_['conv2d2'])
#Get weight
result = net1.get_all_params_values()
conv2d1 = result['conv2d1']
maxpool1 = result['maxpool1']
conv2d2 = result['conv2d2']
maxpool2 = result['maxpool2']
X_test = data_preprocess_test(X_test)
total_test_time_points = len(X_test) // NO_TIME_POINTS
remainder_test_points = len(X_test) % NO_TIME_POINTS
no_rows = total_test_time_points * NO_TIME_POINTS
X_test = X_test[0:no_rows, :]
X_test = X_test.transpose()
X_test_Samples = np.split(X_test, total_test_time_points, axis=1)
X_test = np.asarray(X_test_Samples)
###########################################################################
#######get predictions and write to files for series 9 and series 10#######
print("Testing subject%d...." %(subject))
params = net.get_all_params_values()
learned_weights = net.load_params_from(params)
probabilities = net.predict_proba(X_test)
sub9 = 'subj{0}_series{1}'.format(subject, 9)
data_len9 = test_dict[sub9]
total_time_points9 = data_len9 // NO_TIME_POINTS
remainder_data9 = data_len9 % NO_TIME_POINTS
sub10 = 'subj{0}_series{1}'.format(subject, 10)
data_len10 = test_dict[sub10]
total_time_points10 = data_len10 // NO_TIME_POINTS
remainder_data10 = data_len10 % NO_TIME_POINTS
total_test_points = total_time_points9+total_time_points10
X_test = data_preprocess_test(X_test)
total_test_time_points = len(X_test) // NO_TIME_POINTS
remainder_test_points = len(X_test) % NO_TIME_POINTS
no_rows = total_test_time_points * NO_TIME_POINTS
X_test = X_test[0:no_rows, :]
X_test = X_test.transpose()
X_test_Samples = np.split(X_test, total_test_time_points, axis=1)
X_test = np.asarray(X_test_Samples)
###########################################################################
#######get predictions and write to files for series 9 and series 10#######
print("Testing subject%d...." %(subject))
params = net.get_all_params_values()
learned_weights = net.load_params_from(params)
probabilities = net.predict_proba(X_test)
sub9 = 'subj{0}_series{1}'.format(subject, 9)
data_len9 = test_dict[sub9]
total_time_points9 = data_len9 // NO_TIME_POINTS
remainder_data9 = data_len9 % NO_TIME_POINTS
sub10 = 'subj{0}_series{1}'.format(subject, 10)
data_len10 = test_dict[sub10]
total_time_points10 = data_len10 // NO_TIME_POINTS
remainder_data10 = data_len10 % NO_TIME_POINTS
total_test_points = total_time_points9+total_time_points10
def build_dbn():
cols = ['Start']
t = 1
channels = 14
batch_size = None #None = arbitary batch size
hidden_layer_size = 100
N_EVENTS = 1
max_epochs = 500
NO_TIME_POINTS = 177
ids_tot = []
pred_tot = []
test_dict = dict()
test_total = 0
net = NeuralNet(
layers=[
('input', layers.InputLayer),
('conv1', layers.Conv1DLayer),
('conv2', layers.Conv1DLayer),
('pool1', layers.MaxPool1DLayer),
('dropout2', layers.DropoutLayer),
('hidden4', layers.DenseLayer),
('dropout3', layers.DropoutLayer),
('hidden5', layers.DenseLayer),
('dropout4', layers.DropoutLayer),
('output', layers.DenseLayer),
],
input_shape=(batch_size, channels, NO_TIME_POINTS),
conv1_num_filters=4, conv1_filter_size=1,
conv1_nonlinearity=None,
conv2_num_filters=8, conv2_filter_size=5,
pool1_pool_size=4,
dropout2_p=0.5, hidden4_num_units=hidden_layer_size,
dropout3_p=0.3, hidden5_num_units=hidden_layer_size,
dropout4_p=0.2, output_num_units=N_EVENTS,
output_nonlinearity=sigmoid,
batch_iterator_train = BatchIterator(batch_size=1000),
batch_iterator_test = BatchIterator(batch_size=1000),
y_tensor_type=theano.tensor.matrix,
update=nesterov_momentum,
update_learning_rate=theano.shared(float(0.03)),
update_momentum=theano.shared(float(0.9)),
objective_loss_function=loss,
regression=True,
on_epoch_finished=[
AdjustVariable('update_learning_rate', start=0.03,stop=0.0001),
AdjustVariable('update_momentum', start=0.9, stop=0.999),
EarlyStopping(patience=100),
],
max_epochs=max_epochs,
verbose=1,
)
# load trial dataset
dic = pickle.load(open('datapickled/traildata.pickle', 'rb'))
X = dic['X']
y = dic['y']
# process training data
total_time_points = len(X) // NO_TIME_POINTS
no_rows = total_time_points * NO_TIME_POINTS
X = X[0:no_rows, :]
X = X.transpose()
X_Samples = np.split(X, total_time_points, axis=1)
X = np.asarray(X_Samples)
y = y[0:no_rows, :]
y = y[::NO_TIME_POINTS, :]
y = y.astype('float32')
net.fit(X,y)
tip = datetime.now().strftime("%Y-%m-%d-%H-%M-%S")
# Save the net
with open('net/net'+tip+'.pickle', 'wb') as f:
pickle.dump(net, f, -1)
plot(net)
# Load test data
dic = pickle.load(open('datapickled/testdata2.pickle', 'rb'))
X_test = dic['X_test']
ids_tot = dic['ids_tot']
test_dict = dic['test_dict']
test_total = dic['test_total']
####process test data####
print("Creating prediction file ... ")
X_test = X_test
total_test_len = len(X_test)
total_test_time_points = len(X_test) // NO_TIME_POINTS
remainder_test_points = len(X_test) % NO_TIME_POINTS
no_rows = total_test_time_points * NO_TIME_POINTS
X_test = X_test[0:no_rows, :]
X_test = X_test.transpose()
X_test_Samples = np.split(X_test, total_test_time_points, axis=1)
X_test = np.asarray(X_test_Samples)
# Evaluate test data
print("Testing subject 0....")
params = net.get_all_params_values()
learned_weights = net.load_params_from(params)
probabilities = net.predict_proba(X_test)
total_test_points = total_test_len // NO_TIME_POINTS
remainder_data = total_test_len % NO_TIME_POINTS
for i, p in enumerate(probabilities):
if i != total_test_points:
for j in range(NO_TIME_POINTS):
pred_tot.append(p)
# create prediction file
print('Creating submission(prediction) file...')
tip = datetime.now().strftime("%Y-%m-%d-%H-%M-%S")
submission_file = 'res/test_conv_net_push'+tip+'.csv'
# create pandas object
submission = pd.DataFrame(index=ids_tot[:len(pred_tot)],columns=cols,data=pred_tot)
# write file
submission.to_csv(submission_file, index_label='id', float_format='%.6f')
def build_dbn():
cols = ['Start']
t = 1
channels = 14
batch_size = None #None = arbitary batch size
hidden_layer_size = 100 #change to 1024
N_EVENTS = 1
max_epochs = 100
NO_TIME_POINTS = 70 #311
ids_tot = []
pred_tot = []
test_dict = dict()
test_total = 0
X, y = load_dataset()
X_test, ids_tot, test_dict, test_total = load_testdata()
net = NeuralNet(
layers=[
('input', layers.InputLayer),
('dropout1', layers.DropoutLayer),
('conv1', layers.Conv1DLayer),
('conv2', layers.Conv1DLayer),
('pool1', layers.MaxPool1DLayer),
('dropout2', layers.DropoutLayer),
('hidden4', layers.DenseLayer),
('dropout3', layers.DropoutLayer),
('hidden5', layers.DenseLayer),
('dropout4', layers.DropoutLayer),
('output', layers.DenseLayer),
],
input_shape=(None, channels, NO_TIME_POINTS),
dropout1_p=0.5,
conv1_num_filters=4, conv1_filter_size=1,
conv2_num_filters=8, conv2_filter_size=4, pool1_pool_size=4,
dropout2_p=0.5, hidden4_num_units=hidden_layer_size,
dropout3_p=0.5, hidden5_num_units=hidden_layer_size,
dropout4_p=0.5, output_num_units=N_EVENTS, output_nonlinearity=sigmoid,
batch_iterator_train = BatchIterator(batch_size=1000),
batch_iterator_test = BatchIterator(batch_size=1000),
y_tensor_type=theano.tensor.matrix,
update=nesterov_momentum,
update_learning_rate=theano.shared(float(0.03)),
update_momentum=theano.shared(float(0.9)),
objective_loss_function=loss,
regression=True,
max_epochs=max_epochs,
verbose=1,
)
###process training data####
X = data_preprocess(X)
total_time_points = len(X) // NO_TIME_POINTS
no_rows = total_time_points * NO_TIME_POINTS
print X.shape
print total_time_points
print no_rows
X = X[0:no_rows, :]
print X.shape
X = X.transpose()
X_Samples = np.split(X, total_time_points, axis=1)
X = np.asarray(X_Samples)
print X.shape
y = y[0:no_rows, :]
y = y[::NO_TIME_POINTS, :]
print("Training trial %d...." %(t))
net.fit(X,y)
####process test data####
print("Creating prediction file ... ")
X_test = X_test
X_test = data_preprocess(X_test)
total_test_time_points = len(X_test) // NO_TIME_POINTS
remainder_test_points = len(X_test) % NO_TIME_POINTS
no_rows = total_test_time_points * NO_TIME_POINTS
X_test = X_test[0:no_rows, :]
X_test = X_test.transpose()
X_test_Samples = np.split(X_test, total_test_time_points, axis=1)
X_test = np.asarray(X_test_Samples)
###########################################################################
#######get predictions and write to files for series 9 and series 10#######
print("Testing subject 0....")
params = net.get_all_params_values()
learned_weights = net.load_params_from(params)
probabilities = net.predict_proba(X_test)
total_time_points = []
all_remainder_data = []
subs = []
total_test_points = 0
trials = np.array(['01','02','03','04','05','06','07','08','09','10'])
for trial in trials:
sub = 'subj{0}_series{1}'.format('0', trial)
data_len = test_dict[sub]
total_time_point = data_len // NO_TIME_POINTS
remainder_data = data_len % NO_TIME_POINTS
subs.append(sub)
total_time_points.append(total_time_point)
all_remainder_data.append(remainder_data)
total_test_points = np.sum(total_time_points)
print len(ids_tot)
print cols
print len(probabilities)
for i, p in enumerate(probabilities):
for j in range(NO_TIME_POINTS):
pred_tot.append(p)
print len(pred_tot)
# for k in range(np.sum(all_remainder_data)):
# pred_tot.append(pred_tot[-1])
#submission file
print('Creating submission(prediction) file...')
submission_file = './test_conv_net_push.csv'
# create pandas object for sbmission
submission = pd.DataFrame(index=ids_tot[:len(pred_tot)],
columns=cols,
data=pred_tot)
# write file
submission.to_csv(submission_file, index_label='id', float_format='%.6f')
