BATCH_SIZE = 20 H_SIZE = 128 encoder = HiddenLayer(rng, (128, H_SIZE)) encode_igate = HiddenLayer(rng, (128, H_SIZE)) encode_fgate = HiddenLayer(rng, (128, H_SIZE)) recoder = HiddenLayer(rng, (H_SIZE, H_SIZE)) recode_igate = HiddenLayer(rng, (H_SIZE, H_SIZE)) recode_fgate = HiddenLayer(rng, (H_SIZE, H_SIZE)) activation = ActivationLayer(rng, f='elu') dropout = DropoutLayer(rng, 0.2) encoder_network = Network( Conv1DLayer(rng, (64, 63, 25), (BATCH_SIZE, 63, 240)), Pool1DLayer(rng, (2, ), (BATCH_SIZE, 64, 240)), ActivationLayer(rng, f='elu'), Conv1DLayer(rng, (256, 64, 25), (BATCH_SIZE, 64, 120)), Pool1DLayer(rng, (2, ), (BATCH_SIZE, 256, 120)), ActivationLayer(rng, f='elu'), ) encoder_network.load([ '../models/vae_lstm/3_vae_lstm_layer_0.npz', None, None, '../models/vae_lstm/3_vae_lstm_layer_1.npz', None, None, ])
from nn.ActivationLayer import ActivationLayer from nn.DropoutLayer import DropoutLayer from nn.Pool1DLayer import Pool1DLayer from nn.Conv1DLayer import Conv1DLayer from nn.VariationalLayer import VariationalLayer from nn.Network import Network, AutoEncodingNetwork, InverseNetwork rng = np.random.RandomState(23455) BATCH_SIZE = 1 network = Network( Network( DropoutLayer(rng, 0.25), Conv1DLayer(rng, (64, 66, 25), (BATCH_SIZE, 66, 240)), Pool1DLayer(rng, (2,), (BATCH_SIZE, 64, 240)), ActivationLayer(rng), DropoutLayer(rng, 0.25), Conv1DLayer(rng, (128, 64, 25), (BATCH_SIZE, 64, 120)), Pool1DLayer(rng, (2,), (BATCH_SIZE, 128, 120)), ActivationLayer(rng), ), Network( VariationalLayer(rng), ), Network( InverseNetwork(Pool1DLayer(rng, (2,), (BATCH_SIZE, 64, 120))),
test_split = int(X.shape[0] * 0.8) X, Y = map(np.array, zip(*shuffled)) X_train = theano.shared(np.array(X)[:cv_split], borrow=True) Y_train = theano.shared(np.array(Y)[:cv_split], borrow=True) X_valid = theano.shared(np.array(X)[cv_split:test_split], borrow=True) Y_valid = theano.shared(np.array(Y)[cv_split:test_split], borrow=True) X_test = theano.shared(np.array(X)[test_split:], borrow=True) Y_test = theano.shared(np.array(Y)[test_split:], borrow=True) batchsize = 10 network = Network( Conv1DLayer(rng, (64, 66, 25), (batchsize, 66, 240)), # For stable computation using batchnorm layer, # please ensure to normalize the features of the data # (3rd axis for style transfer data) BatchNormLayer(rng, (batchsize, 64, 240), axes=( 0, 2, )), ActivationLayer(rng, f='ReLU'), Pool1DLayer(rng, (2, ), (batchsize, 64, 240)), Conv1DLayer(rng, (128, 64, 25), (batchsize, 64, 120)), BatchNormLayer(rng, (batchsize, 128, 120), axes=( 0, 2, )), ActivationLayer(rng, f='ReLU'),