def createNet(X, Y, ln, loadFile = ""):
net1 = NeuralNet(
layers=[ # four layers: two hidden layers
('input', layers.InputLayer),
('hidden', layers.DenseLayer),
('hidden1', layers.DenseLayer),
('hidden2', layers.DenseLayer),
('hidden3', layers.DenseLayer),
('output', layers.DenseLayer),
],
# layer parameters: Best 400 400
input_shape=(None, numInputs), # 31 inputs
hidden_num_units=400, # number of units in hidden layer
hidden1_num_units=400,
hidden2_num_units=400,
hidden3_num_units=400,
output_nonlinearity=None, # output layer uses identity function
output_num_units=numOutputs, # 4 outputs
# optimization method:
update=nesterov_momentum,
update_learning_rate=ln,
update_momentum=0.9,
regression=True, # flag to indicate we're dealing with regression problem
max_epochs=1500, # we want to train this many epochs
verbose=1,
)
#if (loadFile != ""):
#net1.load_params_from(loadFile)
net1.max_epochs = 50
net1.update_learning_rate = ln;
return net1
print(('train_labels_file = %s' % (train_labels_file)))
print(('trained_net_file = %s' % (trained_net_file)))
if retrain:
print('retraining net...')
data, labels = load2d(train_data_file, train_labels_file)
train_net(data, labels, net13, trained_net_file)
plot_loss(net13, outfile=join(root, 'plots', 'net13_loss.png'))
elif test:
print('loading net from disk...')
with open(trained_net_file, 'rb') as ifile:
net13 = pickle.load(ifile)
print('loading test data...')
data, _ = load2d(test_data_file)
names = np.load(test_names_file)
print('generating kaggle submission...')
generate_submission(data, names, net13, submission_file, header_file, N=50)
elif finetune:
print('loading pre-trained net from disk...')
with open(trained_net_file, 'rb') as ifile:
net13 = pickle.load(ifile)
print('loading training data...')
data, labels = load2d(train_data_file, train_labels_file)
net13.batch_iterator_train = BatchIterator(batch_size=128)
net13.update_learning_rate = 0.00001
net13.max_epochs = 1
#net13.on_training_finished = [early_stopping.load_best_weights]
train_net(data, labels, net13, finetuned_net_file)
