def test_adjust_gradient(self):
X = dot(randn(5, 5), randn(5, 1000)) + randn(5, 1)
Y = dot(randn(2, 2), randn(2, 1000)) + dot(randn(2, 5), X)
meanIn = randn(5, 1)
meanOut = randn(2, 1)
preIn = randn(5, 5)
preOut = randn(2, 2)
predictor = randn(2, 5)
pre = AffinePreconditioner(meanIn, meanOut, preIn, preOut, predictor)
f = lambda X, Y: sum(hstack([p.ravel() for p in pre(X, Y)]))
# compute analytic gradient
dfdX, dfdY = pre.adjust_gradient(ones_like(X), ones_like(Y))
# compute numerical gradient
h = 0.1
dfdXn = zeros_like(X)
X_copy = X.copy()
for i in range(X.shape[0]):
for j in range(X.shape[1]):
X_copy[i, j] = X[i, j] + h
fp = f(X_copy, Y)
X_copy[i, j] = X[i, j] - h
fn = f(X_copy, Y)
dfdXn[i, j] = (fp - fn) / (2. * h)
X_copy[i, j] = X[i, j]
self.assertLess(max(abs(dfdXn - dfdX)), 1e-7)
def test_affine_preconditioner_logjacobian(self):
meanIn = randn(5, 1)
meanOut = randn(2, 1)
preIn = randn(5, 5)
preOut = randn(2, 2)
predictor = randn(2, 5)
pre = AffinePreconditioner(meanIn, meanOut, preIn, preOut, predictor)
self.assertAlmostEqual(
mean(pre.logjacobian(randn(5, 10), randn(2, 10))),
slogdet(preOut)[1])
def test_affine_preconditioner_logjacobian(self): meanIn = randn(5, 1) meanOut = randn(2, 1) preIn = randn(5, 5) preOut = randn(2, 2) predictor = randn(2, 5) pre = AffinePreconditioner( meanIn, meanOut, preIn, preOut, predictor) self.assertAlmostEqual(mean(pre.logjacobian(randn(5, 10), randn(2, 10))), slogdet(preOut)[1])
def test_affine_preconditioner_pickle(self):
meanIn = randn(5, 1)
meanOut = randn(2, 1)
preIn = randn(5, 5)
preOut = randn(2, 2)
predictor = randn(2, 5)
pre0 = AffinePreconditioner(meanIn, meanOut, preIn, preOut, predictor)
tmp_file = mkstemp()[1]
# store transformation
with open(tmp_file, 'w') as handle:
dump({'pre': pre0}, handle)
# load transformation
with open(tmp_file) as handle:
pre1 = load(handle)['pre']
X, Y = randn(5, 100), randn(2, 100)
X0, Y0 = pre0(X, Y)
X1, Y1 = pre1(X, Y)
# make sure linear transformation hasn't changed
self.assertLess(max(abs(X0 - X1)), 1e-20)
self.assertLess(max(abs(Y0 - Y1)), 1e-20)
# test inverse after pickling
Xp, Yp = pre1(X, Y)
Xr, Yr = pre1.inverse(Xp, Yp)
self.assertLess(max(abs(Xr - X)), 1e-10)
self.assertLess(max(abs(Yr - Y)), 1e-10)
def test_affine_preconditioner(self): X = dot(randn(5, 5), randn(5, 1000)) + randn(5, 1) Y = dot(randn(2, 2), randn(2, 1000)) + dot(randn(2, 5), X) meanIn = randn(5, 1) meanOut = randn(2, 1) preIn = randn(5, 5) preOut = randn(2, 2) predictor = randn(2, 5) pre = AffinePreconditioner( meanIn, meanOut, preIn, preOut, predictor) # test inverse Xp, Yp = pre(X, Y) Xr, Yr = pre.inverse(Xp, Yp) # check that preconditioner does what it's expected to do self.assertEqual(pre.dim_in, X.shape[0]) self.assertEqual(pre.dim_out, Y.shape[0]) self.assertLess(max(abs(Xp - dot(preIn, X - meanIn))), 1e-10) self.assertLess(max(abs(Yp - dot(preOut, Y - meanOut - dot(predictor, Xp)))), 1e-10) # check that inverse works self.assertLess(max(abs(Xr - X)), 1e-10) self.assertLess(max(abs(Yr - Y)), 1e-10) # reference counts should not change Xrc = sys.getrefcount(X) Yrc = sys.getrefcount(Y) for i in range(10): pre(X, Y) self.assertEqual(sys.getrefcount(X), Xrc) self.assertEqual(sys.getrefcount(Y), Yrc)
def test_affine_preconditioner(self): X = dot(randn(5, 5), randn(5, 1000)) + randn(5, 1) Y = dot(randn(2, 2), randn(2, 1000)) + dot(randn(2, 5), X) meanIn = randn(5, 1) meanOut = randn(2, 1) preIn = randn(5, 5) preOut = randn(2, 2) predictor = randn(2, 5) pre = AffinePreconditioner( meanIn, meanOut, preIn, preOut, predictor) # test inverse Xp, Yp = pre(X, Y) Xr, Yr = pre.inverse(Xp, Yp) # check that preconditioner does what it's expected to do self.assertEqual(pre.dim_in, X.shape[0]) self.assertEqual(pre.dim_out, Y.shape[0]) self.assertLess(max(abs(Xp - dot(preIn, X - meanIn))), 1e-10) self.assertLess(max(abs(Yp - dot(preOut, Y - meanOut - dot(predictor, Xp)))), 1e-10) # check that inverse works self.assertLess(max(abs(Xr - X)), 1e-10) self.assertLess(max(abs(Yr - Y)), 1e-10) # reference counts should not change Xrc = sys.getrefcount(X) Yrc = sys.getrefcount(Y) for i in range(10): pre(X, Y) self.assertEqual(sys.getrefcount(X), Xrc) self.assertEqual(sys.getrefcount(Y), Yrc)
def test_adjust_gradient(self): X = dot(randn(5, 5), randn(5, 1000)) + randn(5, 1) Y = dot(randn(2, 2), randn(2, 1000)) + dot(randn(2, 5), X) meanIn = randn(5, 1) meanOut = randn(2, 1) preIn = randn(5, 5) preOut = randn(2, 2) predictor = randn(2, 5) pre = AffinePreconditioner( meanIn, meanOut, preIn, preOut, predictor) f = lambda X, Y: sum(hstack([p.ravel() for p in pre(X, Y)])) # compute analytic gradient dfdX, dfdY = pre.adjust_gradient(ones_like(X), ones_like(Y)) # compute numerical gradient h = 0.1 dfdXn = zeros_like(X) X_copy = X.copy() for i in range(X.shape[0]): for j in range(X.shape[1]): X_copy[i, j] = X[i, j] + h fp = f(X_copy, Y) X_copy[i, j] = X[i, j] - h fn = f(X_copy, Y) dfdXn[i, j] = (fp - fn) / (2. * h) X_copy[i, j] = X[i, j] self.assertLess(max(abs(dfdXn - dfdX)), 1e-7)
