def test_03(self):
lmbda = 1e-1
opt = parcnsdl.ConvBPDNDictLearn_Consensus.Options({'MaxMainIter': 10})
try:
b = parcnsdl.ConvBPDNDictLearn_Consensus(self.D0, self.S, lmbda,
opt=opt, nproc=0)
b.solve()
except Exception as e:
print(e)
assert(0)
def test_04(self):
N = 16
Nc = 3
Nd = 5
M = 4
K = 3
D0 = np.random.randn(Nd, Nd, Nc, M)
S = np.random.randn(N, N, Nc, K)
lmbda = 1e-1
opt = parcnsdl.ConvBPDNDictLearn_Consensus.Options({'MaxMainIter': 10})
try:
b = parcnsdl.ConvBPDNDictLearn_Consensus(D0, S, lmbda, opt=opt,
nproc=2)
b.solve()
except Exception as e:
print(e)
assert(0)
def test_05(self):
lmbda = 1e-1
Nit = 10
opts = cbpdndl.ConvBPDNDictLearn.Options(
{'MaxMainIter': Nit, 'AccurateDFid': True,
'CBPDN': {'RelaxParam': 1.0, 'AutoRho': {'Enabled': False}},
'CCMOD': {'RelaxParam': 1.0, 'AutoRho': {'Enabled': False}}})
bs = cbpdndl.ConvBPDNDictLearn(self.D0, self.S, lmbda, opt=opts,
method='cns')
Ds = bs.solve()
optp = parcnsdl.ConvBPDNDictLearn_Consensus.Options(
{'MaxMainIter': Nit})
bp = parcnsdl.ConvBPDNDictLearn_Consensus(self.D0, self.S, lmbda,
opt=optp, nproc=2)
Dp = bp.solve()
assert(np.linalg.norm(Ds - Dp) < 1e-7)
assert(np.abs(bs.getitstat().ObjFun[-1] - bp.getitstat().ObjFun[-1])
< 1e-7)
"""
Set regularization parameter and options for dictionary learning solver.
"""
lmbda = 0.2
opt = parcnsdl.ConvBPDNDictLearn_Consensus.Options({'Verbose': True,
'MaxMainIter': 200,
'CBPDN': {'rho': 50.0*lmbda + 0.5},
'CCMOD': {'rho': 1.0, 'ZeroMean': True}})
"""
Create solver object and solve.
"""
d = parcnsdl.ConvBPDNDictLearn_Consensus(D0, sh, lmbda, opt)
D1 = d.solve()
print("ConvBPDNDictLearn_Consensus solve time: %.2fs" %
d.timer.elapsed('solve'))
"""
Display initial and final dictionaries.
"""
D1 = D1.squeeze()
fig = plot.figure(figsize=(14, 7))
plot.subplot(1, 2, 1)
plot.imview(util.tiledict(D0), fig=fig, title='D0')
plot.subplot(1, 2, 2)
plot.imview(util.tiledict(D1), fig=fig, title='D1')