else:
tf_regloss = muscat.tf_lambda_reg * (tf_regloss_real)
tf_regloss_tv, tf_my_tv_loss_map = reg.Reg_TV_RH(
1e3 * muscat.TF_obj, Eps=muscat.tf_eps
) #Alernatively tf_total_variation_regularization # total_variation
tf_regloss += muscat.tf_lambda_reg * tf_regloss_tv
if (is_absorption):
tf_regloss += muscat.tf_lambda_reg * reg.Reg_TV_RH(
muscat.TF_obj_absorption, Eps=muscat.tf_eps)
elif (experiments.regularizer == 'GR'):
# Goods roughness rgularizer
print('We are using GR - Regularization')
tf_regloss += muscat.tf_lambda_reg * reg.Reg_GR(
muscat.TF_obj, muscat.tf_eps, muscat.tf_eps
) #, eps1=muscat.tf_eps, eps2=muscat.tf_eps) #Alernatively tf_total_variation_regularization # total_variation
if is_absorption:
tf_regloss += muscat.tf_lambda_reg * reg.Reg_GR(
muscat.TF_obj_absorption, muscat.tf_eps, muscat.tf_eps)
elif (experiments.regularizer == 'L1'):
# L1 rgularizer
print('We are using L1 - Regularization')
tf_regloss += muscat.tf_lambda_reg * (
reg.Reg_L1(muscat.TF_obj) + reg.Reg_L1(muscat.TF_obj_absorption))
elif (experiments.regularizer == 'L2'):
# L1 rgularizer
print('We are using L2 - Regularization')
tf_regloss = muscat.tf_lambda_reg * (
reg.Reg_L2(muscat.TF_obj) + reg.Reg_L2(muscat.TF_obj_absorption))
# tf_regloss += muscat.tf_lambda_reg*reg.Reg_TV(muscat.TF_obj, BetaVals = [muscat.myparams.dz,muscat.myparams.dx,muscat.myparams.dy], epsR=muscat.tf_eps, is_circ = True, is_xy=False) #Alernatively tf_total_variation_regularization # total_variation
# if(is_absorption):
# tf_regloss += muscat.tf_lambda_reg*reg.Reg_TV(muscat.TF_obj_absorption, BetaVals = [muscat.myparams.dz,muscat.myparams.dx,muscat.myparams.dy], epsR=muscat.tf_eps, is_circ = True, is_xy=False) #Alernatively tf_total_variation_regularization # total_variation
tf_regloss += muscat.tf_lambda_reg * reg.Reg_TV_RH(
muscat.TF_obj, Eps=muscat.tf_eps
) #Alernatively tf_total_variation_regularization # total_variation
if (is_absorption):
tf_regloss += muscat.tf_lambda_reg * reg.Reg_TV_RH(
muscat.TF_obj_absorption, Eps=muscat.tf_eps)
elif (experiments.regularizer == 'GR'):
# Goods roughness rgularizer
print('We are using GR - Regularization')
tf_regloss += muscat.tf_lambda_reg * (
reg.Reg_GR(muscat.TF_obj) +
reg.Reg_GR(muscat.TF_obj_absorption)
) #, eps1=muscat.tf_eps, eps2=muscat.tf_eps) #Alernatively tf_total_variation_regularization # total_variation
elif (experiments.regularizer == 'L1'):
# L1 rgularizer
print('We are using L1 - Regularization')
tf_regloss += muscat.tf_lambda_reg * (reg.Reg_L1(
muscat.TF_obj) + reg.Reg_L1(muscat.TF_obj_absorption))
elif (experiments.regularizer == 'L2'):
# L1 rgularizer
print('We are using L2 - Regularization')
tf_regloss = muscat.tf_lambda_reg * (reg.Reg_L2(
muscat.TF_obj) + reg.Reg_L2(muscat.TF_obj_absorption))
if (0):
tf_zernloss = experiments.lambda_zernike * reg.Reg_L2(
muscat.TF_obj,
BetaVals=[muscat.dx, muscat.dy, muscat.dz],
epsR=muscat.tf_eps,
is_circ=True
) #Alernatively tf_total_variation_regularization # total_variation
tf_tvloss += muscat.tf_lambda_tv * reg.Reg_TV(
muscat.TF_obj_absorption,
BetaVals=[muscat.dx, muscat.dy, muscat.dz],
epsR=muscat.tf_eps,
is_circ=True
) #Alernatively tf_total_variation_regularization # total_variation
else:
# Goods Roughness
print('We are using GOODS ROUGHNESS - Regularization')
tf_tvloss = muscat.tf_lambda_tv * reg.Reg_GR(
muscat.TF_obj
) #Alernatively tf_total_variation_regularization # total_variation
tf_tvloss += muscat.tf_lambda_tv * reg.Reg_GR(muscat.TF_obj_absorption)
'''Negativity Constraint'''
tf_negsqrloss = lambda_neg * reg.Reg_NegSqr(muscat.TF_obj)
tf_negsqrloss += lambda_neg * reg.Reg_NegSqr(muscat.TF_obj_absorption)
# Correc the fwd model - not good here!
tf_fwd_corrected = tf_fwd / tf.cast(
tf.abs(tf_global_abs), tf.complex64) * tf.exp(
1j * tf.cast(tf_global_phase, tf.complex64))
'''Define Loss-function'''
if (0):
print('-------> ATTENTION Losstype is L1')
tf_fidelity = tf.reduce_mean(
(tf.abs(muscat.tf_meas - tf_fwd_corrected)
