def flowBuilder(n,numFlow,innerBuilder=None,typeLayer=3,relax=False,shift=False):
nn = n*2
op = source.Gaussian([nn]).to(torch.float64)
if innerBuilder is None:
raise Exception("innerBuilder is None")
if relax:
f3 = flow.DiagScaling(nn,initValue=0.1*np.random.randn(nn),fix=[0]*n+[0]*n,shift=shift)
else:
f3 = flow.DiagScaling(nn,initValue=0.1*np.random.randn(nn),fix=[0]*n+[1]*n,shift=shift)
layers=[f3]
if typeLayer == 0:
layers.append(flow.Symplectic(nn))
else:
for d in range(numFlow):
if typeLayer == 3:
layers.append(flow.PointTransformation(innerBuilder(n)))
layers.append(flow.Symplectic(nn))
elif typeLayer ==2:
layers.append(flow.Symplectic(nn))
elif typeLayer ==1:
layers.append(flow.PointTransformation(innerBuilder(n)))
elif typeLayer!=0:
raise Exception("No such type")
return flow.FlowNet(layers,op).double()
def test_fix():
p = source.Gaussian([4])
f = flow.DiagScaling(4, initValue=[2, 3, 4, 5], fix=[1, 0, 1, 0], prior=p)
t = torch.tensor([2, 3, 4, 5], dtype=torch.float32)
x, p = f.inverse(t)
assert_array_almost_equal(
x.detach().numpy(), t * torch.exp(torch.tensor([0.0, 3.0, 0.0, 5.0])))
assert_almost_equal(p.item(), 3 + 5)
def extractPPrior(flowCon):
layers = []
_diag = flowCon.layerList[0]
nn = _diag.shift.shape[0] // 2
_op = source.Gaussian([nn]).to(torch.float64)
assert _diag.shift.sum() == 0
assert _diag.fix.sum() == nn
layers.append(
flow.DiagScaling(nn, initValue=_diag.elements.clone().detach()[nn:]))
return flow.FlowNet(layers, _op).to(torch.float64)
def extractFlow(flowCon):
from copy import deepcopy
layers = []
_op = deepcopy(flowCon.prior)
_rnvp = deepcopy(flowCon.layerList[1].flow)
_diag = flowCon.layerList[0]
nn = _diag.shift.shape[0]//2
layers.append(flow.DiagScaling(nn,initValue=_diag.elements.clone().detach()[:nn]))
layers.append(_rnvp)
return flow.FlowNet(layers,_op).double()
def extractFlow(flowCon):
from copy import deepcopy
layers = []
_rnvp = deepcopy(flowCon.layerList[1].flow)
_diag = flowCon.layerList[0]
nn = _diag.shift.shape[0] // 2
_op = source.Gaussian([nn]).to(torch.float64)
assert _diag.shift.sum() == 0
assert _diag.fix.sum() == nn
layers.append(
flow.DiagScaling(nn, initValue=_diag.elements.clone().detach()[:nn]))
layers.append(_rnvp)
return flow.FlowNet(layers, _op).double()
def test_saveload():
p = source.Gaussian([4])
f = flow.DiagScaling(4, initValue=[0.01, 0.02, 0.03, 0.04], prior=p)
blankf = flow.DiagScaling(4, prior=p)
saveload(f, blankf, decimal=5)
def test_bijective():
p = source.Gaussian([4])
f = flow.DiagScaling(4, prior=p)
bijective(f)
