def __init__(self, config, proc_type='standardize', **kwargs):
'''
config: dictionary with partition configuration information
proc_type: type of preprocessing (either standardize or pca_whiten)
if proc_type='standardize' no extra arguments required
if proc_type='pca_whiten' the following keyword arguments are required:
ncomponents = x where x is an integer
epsilon = y where y is a float (regularization parameter)
'''
recognized_types = ['standardize', 'pca_whiten']
assert proc_type in recognized_types
# load parition information
self.mean = config['mean']
self.mean = self.mean.reshape((np.prod(self.mean.shape),))
self.istd = np.reciprocal(np.sqrt(config['var']))
self.istd = self.istd.reshape((np.prod(self.istd.shape),))
self.tframes = config['tframes']
nvis = len(self.mean)
if proc_type == 'standardize':
dim = nvis
mask = (self.istd < 20) # in order to ignore near-zero variance inputs
self.biases = np.array(-self.mean * self.istd * mask, dtype=np.float32)
self.weights = np.array(np.diag(self.istd * mask), dtype=np.float32) #!!!gives memory error for convnet (because diag not treated as sparse mat)
if proc_type == 'pca_whiten':
raise NotImplementedError(
'''PCA whitening not yet implemented as a layer.
Use audio_dataset2d.AudioDataset2d to perform whitening from the dataset iterator''')
# dim = kwargs['ncomponents']
# S = config['S'][:dim] # eigenvalues
# U = config['U'][:,:dim] # eigenvectors
# self.pca = np.diag(1./(np.sqrt(S) + epsilon)).dot(U.T)
# self.biases = np.array(-self.mean.dot(self.pca.transpose()), dtype=np.float32)
# self.weights = np.array(self.pca.transpose(), dtype=np.float32)
# Autoencoder with linear units
pre_layer = Autoencoder(nvis=nvis, nhid=dim, act_enc=None, act_dec=None, irange=0)
# Set weights for pre-processing
params = pre_layer.get_param_values()
params[1] = self.biases
params[2] = self.weights
pre_layer.set_param_values(params)
super(PreprocLayer, self).__init__(layer_name='pre', layer_content=pre_layer, freeze_params=True)
