def regularized_inverse3(svd, L=1e-3):
"""Unbiased version of regularized_inverse2"""
if svd.__class__.__name__=='SvdTuple' or svd.__class__.__name__=='SvdWrapper':
(s, u, v) = (svd.s, svd.u, svd.v)
else:
assert False, "Unknown type"
if L.__class__.__name__=='Var':
L = L.var
max_eigen = tf.reduce_max(s)
# max_eigen = tf.Print(max_eigen, [max_eigen], "max_eigen")
#si = 1/(s + L*tf.ones_like(s)/max_eigen)
si = (1+L*tf.ones_like(s))/(s+L*tf.ones_like(s))
return u @ tf.diag(si) @ tf.transpose(v)
python类diag()的实例源码
def regularized_inverse4(svd, L=1e-3):
"""Uses relative norm"""
if svd.__class__.__name__=='SvdTuple' or svd.__class__.__name__=='SvdWrapper':
(s, u, v) = (svd.s, svd.u, svd.v)
else:
assert False, "Unknown type"
if L.__class__.__name__=='Var':
L = L.var
max_eigen = tf.reduce_max(s)
L = L/max_eigen
si = (1+L*tf.ones_like(s))/(s+L*tf.ones_like(s))
# si = tf.ones_like(s)
return u @ tf.diag(si) @ tf.transpose(v)
def Identity(n, dtype=None, name=None):
"""Identity matrix of size n."""
if hasattr(n, "shape"): # got a Tensor
nn = fix_shape(n.shape)
assert nn[0] == nn[1]
n = nn[0]
if not dtype:
dtype = default_dtype
return tf.diag(tf.ones((n,), dtype=dtype), name=name)
def symsqrt(mat, eps=1e-7):
"""Symmetric square root."""
s, u, v = tf.svd(mat)
# sqrt is unstable around 0, just use 0 in such case
print("Warning, cutting off at eps")
si = tf.where(tf.less(s, eps), s, tf.sqrt(s))
return u @ tf.diag(si) @ tf.transpose(v)
def pseudo_inverse_sqrt(mat, eps=1e-7):
"""half pseduo-inverse"""
s, u, v = tf.svd(mat)
# zero threshold for eigenvalues
si = tf.where(tf.less(s, eps), s, 1./tf.sqrt(s))
return u @ tf.diag(si) @ tf.transpose(v)
def pseudo_inverse_sqrt2(svd, eps=1e-7):
"""half pseduo-inverse, accepting existing values"""
# zero threshold for eigenvalues
if svd.__class__.__name__=='SvdTuple':
(s, u, v) = (svd.s, svd.u, svd.v)
elif svd.__class__.__name__=='SvdWrapper':
(s, u, v) = (svd.s, svd.u, svd.v)
else:
assert False, "Unknown type"
si = tf.where(tf.less(s, eps), s, 1./tf.sqrt(s))
return u @ tf.diag(si) @ tf.transpose(v)
def pseudo_inverse2(svd, eps=1e-7):
"""pseudo-inverse, accepting existing values"""
# use float32 machine precision as cut-off (works for MKL)
# https://www.wolframcloud.com/objects/927b2aa5-de9c-46f5-89fe-c4a58aa4c04b
if svd.__class__.__name__=='SvdTuple':
(s, u, v) = (svd.s, svd.u, svd.v)
elif svd.__class__.__name__=='SvdWrapper':
(s, u, v) = (svd.s, svd.u, svd.v)
else:
assert False, "Unknown type"
max_eigen = tf.reduce_max(s)
si = tf.where(s/max_eigen<eps, 0.*s, 1./s)
return u @ tf.diag(si) @ tf.transpose(v)
def pseudo_inverse_stable(svd, eps=1e-7):
"""pseudo-inverse, accepting existing values"""
# use float32 machine precision as cut-off (works for MKL)
# https://www.wolframcloud.com/objects/927b2aa5-de9c-46f5-89fe-c4a58aa4c04b
if svd.__class__.__name__=='SvdTuple':
(s, u, v) = (svd.s, svd.u, svd.v)
elif svd.__class__.__name__=='SvdWrapper':
(s, u, v) = (svd.s, svd.u, svd.v)
else:
assert False, "Unknown type"
max_eigen = tf.reduce_max(s)
si = tf.where(s/max_eigen<eps, 0.*s, tf.pow(s, -0.9))
return u @ tf.diag(si) @ tf.transpose(v)
# todo: rename l to L
def regularized_inverse3(svd, L=1e-3):
"""Unbiased version of regularized_inverse2"""
if svd.__class__.__name__=='SvdTuple' or svd.__class__.__name__=='SvdWrapper':
(s, u, v) = (svd.s, svd.u, svd.v)
else:
assert False, "Unknown type"
if L.__class__.__name__=='Var':
L = L.var
max_eigen = tf.reduce_max(s)
# max_eigen = tf.Print(max_eigen, [max_eigen], "max_eigen")
#si = 1/(s + L*tf.ones_like(s)/max_eigen)
si = (1+L*tf.ones_like(s))/(s+L*tf.ones_like(s))
return u @ tf.diag(si) @ tf.transpose(v)
def regularized_inverse4(svd, L=1e-3):
"""Uses relative norm"""
if svd.__class__.__name__=='SvdTuple' or svd.__class__.__name__=='SvdWrapper':
(s, u, v) = (svd.s, svd.u, svd.v)
else:
assert False, "Unknown type"
if L.__class__.__name__=='Var':
L = L.var
max_eigen = tf.reduce_max(s)
L = L/max_eigen
si = (1+L*tf.ones_like(s))/(s+L*tf.ones_like(s))
# si = tf.ones_like(s)
return u @ tf.diag(si) @ tf.transpose(v)
def Identity(n, dtype=None, name=None):
"""Identity matrix of size n."""
if hasattr(n, "shape"): # got a Tensor
nn = fix_shape(n.shape)
assert nn[0] == nn[1]
n = nn[0]
if not dtype:
dtype = default_dtype
return tf.diag(tf.ones((n,), dtype=dtype), name=name)
def cachedGpuIdentityRegularizer(n, Lambda):
global regularizer_cache
n = int(n)
if (n, Lambda) not in regularizer_cache:
numpy_diag = Lambda*np.diag(np.ones([n]))
numpy_diag = numpy_diag.astype(default_np_dtype)
with tf.device("/gpu:0"):
regularizer_cache[(n, Lambda)] = tf.constant(numpy_diag)
return regularizer_cache[(n, Lambda)]
# helper utilities
def symsqrt(mat, eps=1e-7):
"""Symmetric square root."""
s, u, v = tf.svd(mat)
# sqrt is unstable around 0, just use 0 in such case
print("Warning, cutting off at eps")
si = tf.where(tf.less(s, eps), s, tf.sqrt(s))
return u @ tf.diag(si) @ tf.transpose(v)
def pseudo_inverse_sqrt(mat, eps=1e-7):
"""half pseduo-inverse"""
s, u, v = tf.svd(mat)
# zero threshold for eigenvalues
si = tf.where(tf.less(s, eps), s, 1./tf.sqrt(s))
return u @ tf.diag(si) @ tf.transpose(v)
def pseudo_inverse_sqrt2(svd, eps=1e-7):
"""half pseduo-inverse, accepting existing values"""
# zero threshold for eigenvalues
if svd.__class__.__name__=='SvdTuple':
(s, u, v) = (svd.s, svd.u, svd.v)
elif svd.__class__.__name__=='SvdWrapper':
(s, u, v) = (svd.s, svd.u, svd.v)
else:
assert False, "Unknown type"
si = tf.where(tf.less(s, eps), s, 1./tf.sqrt(s))
return u @ tf.diag(si) @ tf.transpose(v)
def pseudo_inverse2(svd, eps=1e-7):
"""pseudo-inverse, accepting existing values"""
# use float32 machine precision as cut-off (works for MKL)
# https://www.wolframcloud.com/objects/927b2aa5-de9c-46f5-89fe-c4a58aa4c04b
if svd.__class__.__name__=='SvdTuple':
(s, u, v) = (svd.s, svd.u, svd.v)
elif svd.__class__.__name__=='SvdWrapper':
(s, u, v) = (svd.s, svd.u, svd.v)
else:
assert False, "Unknown type"
max_eigen = tf.reduce_max(s)
si = tf.where(s/max_eigen<eps, 0.*s, 1./s)
return u @ tf.diag(si) @ tf.transpose(v)
def pseudo_inverse_stable(svd, eps=1e-7):
"""pseudo-inverse, accepting existing values"""
# use float32 machine precision as cut-off (works for MKL)
# https://www.wolframcloud.com/objects/927b2aa5-de9c-46f5-89fe-c4a58aa4c04b
if svd.__class__.__name__=='SvdTuple':
(s, u, v) = (svd.s, svd.u, svd.v)
elif svd.__class__.__name__=='SvdWrapper':
(s, u, v) = (svd.s, svd.u, svd.v)
else:
assert False, "Unknown type"
max_eigen = tf.reduce_max(s)
si = tf.where(s/max_eigen<eps, 0.*s, tf.pow(s, -0.9))
return u @ tf.diag(si) @ tf.transpose(v)
# todo: rename l to L
def regularized_inverse3(svd, L=1e-3):
"""Unbiased version of regularized_inverse2"""
if svd.__class__.__name__=='SvdTuple' or svd.__class__.__name__=='SvdWrapper':
(s, u, v) = (svd.s, svd.u, svd.v)
else:
assert False, "Unknown type"
if L.__class__.__name__=='Var':
L = L.var
max_eigen = tf.reduce_max(s)
# max_eigen = tf.Print(max_eigen, [max_eigen], "max_eigen")
#si = 1/(s + L*tf.ones_like(s)/max_eigen)
si = (1+L*tf.ones_like(s))/(s+L*tf.ones_like(s))
return u @ tf.diag(si) @ tf.transpose(v)
def regularized_inverse4(svd, L=1e-3):
"""Uses relative norm"""
if svd.__class__.__name__=='SvdTuple' or svd.__class__.__name__=='SvdWrapper':
(s, u, v) = (svd.s, svd.u, svd.v)
else:
assert False, "Unknown type"
if L.__class__.__name__=='Var':
L = L.var
max_eigen = tf.reduce_max(s)
L = L/max_eigen
si = (1+L*tf.ones_like(s))/(s+L*tf.ones_like(s))
# si = tf.ones_like(s)
return u @ tf.diag(si) @ tf.transpose(v)
def Identity(n, dtype=None, name=None):
"""Identity matrix of size n."""
if hasattr(n, "shape"): # got a Tensor
nn = fix_shape(n.shape)
assert nn[0] == nn[1]
n = nn[0]
if not dtype:
dtype = default_dtype
return tf.diag(tf.ones((n,), dtype=dtype), name=name)
