def _mean_visibles(self, h):
"""Computes the probabilities P(v=1|h).
Parameters
----------
h : array-like, shape (n_samples, n_components)
Values of the hidden layer to sample from.
Returns
-------
v : array-like, shape (n_samples, n_features)
Values of the visible layer.
"""
p = op.dot(h, self.W, False, False)
p = op.add_matvec(p, self.bv, out=p)
return op.sigmoid(p, out=p)
def _mean_hiddens(self, v):
"""Computes the probabilities P(h=1|v).
Parameters
----------
v : array-like, shape (n_samples, n_features)
Values of the visible layer.
Returns
-------
h : array-like, shape (n_samples, n_components)
Corresponding mean field values for the hidden layer.
"""
p = op.dot(v, self.W, False, True)
p = op.add_matvec(p, self.bh, out=p)
return op.sigmoid(p, out=p)
def _mean_visibles(self, h):
"""Computes the probabilities P(v=1|h).
Parameters
----------
h : array-like, shape (n_samples, n_components)
Values of the hidden layer to sample from.
Returns
-------
v : array-like, shape (n_samples, n_features)
Values of the visible layer.
"""
p = op.dot(h, self.W, False, False)
p = op.add_matvec(p, self.bv, out=p)
return op.sigmoid(p, out=p)
def _mean_hiddens(self, v):
"""Computes the probabilities P(h=1|v).
Parameters
----------
v : array-like, shape (n_samples, n_features)
Values of the visible layer.
Returns
-------
h : array-like, shape (n_samples, n_components)
Corresponding mean field values for the hidden layer.
"""
p = op.dot(v, self.W, False, True)
p = op.add_matvec(p, self.bh, out=p)
return op.sigmoid(p, out=p)
def test_nan_in_toplayer_delta():
size = (200, 10)
X = np.random.normal(size=size).astype(np.float32, order="c")
A = op.sigmoid(X)
Y = np.random.binomial(1.0, p=0.5, size=size).astype(np.float32)
M = np.random.binomial(1.0, p=0.9, size=size).astype(np.float32)
Y[~M.astype(np.bool)] = np.nan
Y_orig = Y.copy()
D = M * (A - Y)
D[~M.astype(np.bool)] = 0.0
Y = op.toplayer_delta(A, Y, X)
assert_allclose(Y, D)
Yd = op.to_gpu(Y_orig)
Ad = op.to_gpu(A)
Xd = op.to_gpu(X)
Yd = op.toplayer_delta(Ad, Yd, Xd)
assert_allclose(Yd.get(), D)
def test_nan_in_toplayer_delta():
size = (200, 10)
X = np.random.normal(size=size).astype(np.float32, order="c")
A = op.sigmoid(X)
Y = np.random.binomial(1.0, p=0.5, size=size).astype(np.float32)
M = np.random.binomial(1.0, p=0.9, size=size).astype(np.float32)
Y[~M.astype(np.bool)] = np.nan
Y_orig = Y.copy()
D = M * (A - Y)
D[~M.astype(np.bool)] = 0.0
Y = op.toplayer_delta(A, Y, X)
assert_allclose(Y, D)
Yd = op.to_gpu(Y_orig)
Ad = op.to_gpu(A)
Xd = op.to_gpu(X)
Yd = op.toplayer_delta(Ad, Yd, Xd)
assert_allclose(Yd.get(), D)
