VAE_model_path = 'models/VAE_600-600-0.0003-50.cpkt'
min_std = 0.1 #Dimensions with std < min_std are removed before training with GC
data_lab, data_ulab, data_valid, data_test = encode_dataset( VAE_model_path, min_std )
dim_x = data_lab.shape[1] / 2
dim_y = y_lab.shape[1]
num_examples = data_lab.shape[0] + data_ulab.shape[0]
###################################
''' Train Generative Classifier '''
###################################
GC = GenerativeClassifier( dim_x, dim_z, dim_y,
num_examples, num_lab, num_batches,
hidden_layers_px = hidden_layers_px,
hidden_layers_qz = hidden_layers_qz,
hidden_layers_qy = hidden_layers_qy,
alpha = alpha )
GC.train( x_labelled = data_lab, y = y_lab, x_unlabelled = data_ulab,
x_valid = data_valid, y_valid = y_valid,
epochs = epochs,
learning_rate = learning_rate,
seed = seed,
print_every = 10,
load_path = None )
############################
''' Evaluate on Test Set '''
############################
data_lab, data_ulab, data_valid, data_test = encode_dataset(
VAE_model_path, min_std)
dim_x = data_lab.shape[1] / 2
dim_y = y_lab.shape[1]
num_examples = data_lab.shape[0] + data_ulab.shape[0]
#%%
###################################
''' Train Generative Classifier '''
###################################
GC = GenerativeClassifier(dim_x,
dim_z,
dim_y,
num_examples,
num_lab,
num_batches,
hidden_layers_px=hidden_layers_px,
hidden_layers_qz=hidden_layers_qz,
hidden_layers_qy=hidden_layers_qy,
alpha=alpha)
GC.train(x_labelled=data_lab,
y=y_lab,
x_unlabelled=data_ulab,
x_valid=data_valid,
y_valid=y_valid,
epochs=epochs,
learning_rate=learning_rate,
seed=seed,
print_every=10,
load_path=None)
def main(flags, data):
#############################
''' Experiment Parameters '''
#############################
num_lab_ratio = flags.labeled
num_batches = 100 #Number of minibatches in a single epoch
dim_z = 50 #Dimensionality of latent variable (z)
epochs = flags.epochs #Number of epochs through the full dataset
learning_rate = 3e-4 #Learning rate of ADAM
alpha = 0.1 #Discriminatory factor (see equation (9) of http://arxiv.org/pdf/1406.5298v2.pdf)
seed = 31415 #Seed for RNG
#Neural Networks parameterising p(x|z,y), q(z|x,y) and q(y|x)
hidden_layers_px = [500]
hidden_layers_qz = [500]
hidden_layers_qy = [500]
####################
''' Load Dataset '''
####################
#Uses anglpy module from original paper (linked at top) to split the dataset for semi-supervised training
train_x, train_y, valid_x, valid_y, test_x, test_y = data.load_numpy_split(
binarize_y=True)
x_l, y_l, x_u, y_u, num_lab = data.create_semisupervised(
train_x, train_y, num_lab_ratio)
x_lab, y_lab = x_l.T, y_l.T
x_ulab, y_ulab = x_u.T, y_u.T
x_valid, y_valid = valid_x.T, valid_y.T
x_test, y_test = test_x.T, test_y.T
################
''' Load VAE '''
################
VAE_model_path = flags.vaemodel
min_std = 0.1 #Dimensions with std < min_std are removed before training with GC
data_lab, data_ulab, data_valid, data_test = encode_dataset(
VAE_model_path, x_lab, x_ulab, x_valid, x_test, min_std)
dim_x = data_lab.shape[1] // 2
dim_y = y_lab.shape[1]
num_examples = data_lab.shape[0] + data_ulab.shape[0]
###################################
''' Train Generative Classifier '''
###################################
GC = GenerativeClassifier(dim_x,
dim_z,
dim_y,
num_examples,
num_lab,
num_batches,
hidden_layers_px=hidden_layers_px,
hidden_layers_qz=hidden_layers_qz,
hidden_layers_qy=hidden_layers_qy,
alpha=alpha)
GC.train(x_labelled=data_lab,
y=y_lab,
x_unlabelled=data_ulab,
x_valid=data_valid,
y_valid=y_valid,
epochs=epochs,
learning_rate=learning_rate,
seed=seed,
print_every=10,
load_path=None)
############################
''' Evaluate on Test Set '''
############################
GC_eval = GenerativeClassifier(dim_x, dim_z, dim_y, num_examples, num_lab,
num_batches)
with GC_eval.session:
GC_eval.saver.restore(GC_eval.session, GC.save_path)
return GC_eval.predict_labels(data_test, y_test)