def global_transform(X_batch, pad_data, encoder_, n_atoms, nonneg):
X_batch = X_batch.swapaxes(0, 1).swapaxes(1, 2)
h, w, n = X_batch.shape
# Fourier transform
X_new = _cdl.patches_to_vectors(X_batch, pad_data=pad_data)
# Encode
X_new = encoder_(X_new)
X_new = _cdl.real2_to_complex(X_new)
X_new = X_new.reshape((-1, X_new.shape[1] * n_atoms), order='F')
X_new = _cdl.complex_to_real2(X_new)
X_new = _cdl.vectors_to_patches(X_new, w, pad_data=pad_data, real=True)
X_new = X_new.reshape((X_new.shape[0], X_new.shape[1], n_atoms, n),
order='F')
X_new = X_new.swapaxes(3, 0).swapaxes(3, 2).swapaxes(3, 1)
if nonneg:
X_new = np.maximum(X_new, 0.0)
return X_new
def global_transform(X_batch, pad_data, encoder_, n_atoms, nonneg):
X_batch = X_batch.swapaxes(0, 1).swapaxes(1, 2)
h, w, n = X_batch.shape
# Fourier transform
X_new = _cdl.patches_to_vectors(X_batch, pad_data=pad_data)
# Encode
X_new = encoder_(X_new)
X_new = _cdl.real2_to_complex(X_new)
X_new = X_new.reshape( (-1, X_new.shape[1] * n_atoms), order='F')
X_new = _cdl.complex_to_real2(X_new)
X_new = _cdl.vectors_to_patches(X_new, w,
pad_data=pad_data,
real=True)
X_new = X_new.reshape( (X_new.shape[0], X_new.shape[1],
n_atoms, n),
order='F')
X_new = X_new.swapaxes(3, 0).swapaxes(3, 2).swapaxes(3, 1)
if nonneg:
X_new = np.maximum(X_new, 0.0)
return X_new
def fit(self, X):
'''Fit the model to the data in X.
Parameters
----------
X : array-like, shape [n_samples, n_features_y, n_features_x]
Training data patches.
Returns
-------
self: object
Returns the instance itself.
'''
width = X.shape[2]
extra_args = {}
if self.penalty == 'l1_space':
extra_args['height'] = X.shape[1]
extra_args['width'] = X.shape[2]
extra_args['pad_data'] = self.pad_data
extra_args['nonneg'] = self.nonneg
encoder, D, diagnostics = _cdl.learn_dictionary(
self.data_generator(X),
self.n_atoms,
reg = self.penalty,
alpha = self.alpha,
max_steps = self.n_iter,
verbose = self.verbose,
D = self.fft_components_,
**extra_args)
self.fft_components_ = D
D = _cdl.diags_to_columns(D)
D = _cdl.vectors_to_patches(D, width,
pad_data=self.pad_data)
self.components_ = D.swapaxes(1, 2).swapaxes(0, 1)
self.encoder_ = encoder
self.diagnostics_ = diagnostics
return self
def fit(self, X):
'''Fit the model to the data in X.
Parameters
----------
X : array-like, shape [n_samples, n_features_y, n_features_x]
Training data patches.
Returns
-------
self: object
Returns the instance itself.
'''
width = X.shape[2]
extra_args = {}
if self.penalty == 'l1_space':
extra_args['height'] = X.shape[1]
extra_args['width'] = X.shape[2]
extra_args['pad_data'] = self.pad_data
extra_args['nonneg'] = self.nonneg
encoder, D, diagnostics = _cdl.learn_dictionary(self.data_generator(X),
self.n_atoms,
reg=self.penalty,
alpha=self.alpha,
max_steps=self.n_iter,
verbose=self.verbose,
D=self.fft_components_,
**extra_args)
self.fft_components_ = D
D = _cdl.diags_to_columns(D)
D = _cdl.vectors_to_patches(D, width, pad_data=self.pad_data)
self.components_ = D.swapaxes(1, 2).swapaxes(0, 1)
self.encoder_ = encoder
self.diagnostics_ = diagnostics
return self
