def test_add_matvec():
X = np.random.randn(3, 4).astype(np.float32)
b1 = np.random.randn(4, 1).astype(np.float32)
b2 = np.random.randn(3, 1).astype(np.float32)
Y_expected1 = X + b1.T
Y_expected2 = X + b2
assert_allclose(Y_expected1, op.add_matvec(X, b1, 1))
assert_allclose(Y_expected2, op.add_matvec(X, b2, 0))
Xd = op.to_gpu(X)
b1d = op.to_gpu(b1)
b2d = op.to_gpu(b2)
assert_allclose(Y_expected1, op.to_cpu(op.add_matvec(Xd, b1d, 1)))
assert_allclose(Y_expected2, op.to_cpu(op.add_matvec(Xd, b2d, 0)))
def test_add_matvec():
X = np.random.randn(3, 4).astype(np.float32)
b1 = np.random.randn(4, 1).astype(np.float32)
b2 = np.random.randn(3, 1).astype(np.float32)
Y_expected1 = X + b1.T
Y_expected2 = X + b2
assert_allclose(Y_expected1, op.add_matvec(X, b1, 1))
assert_allclose(Y_expected2, op.add_matvec(X, b2, 0))
Xd = op.to_gpu(X)
b1d = op.to_gpu(b1)
b2d = op.to_gpu(b2)
assert_allclose(Y_expected1, op.to_cpu(op.add_matvec(Xd, b1d, 1)))
assert_allclose(Y_expected2, op.to_cpu(op.add_matvec(Xd, b2d, 0)))
def fprop(self, X, stream=None):
''' Forward propagation.
NOTE: If we do dropout, X will get mutated. Usually, X == lowerlayer.A.
Thus, we don't need to multiply by a dropout mask in bprop.'''
self.X, self.M = self._corrupt_input(X, stream=stream)
self.Z = op.dot(self.X, self.W, False, True, stream=stream)
self.Z = op.add_matvec(self.Z, self.b, out=self.Z, stream=stream)
self.A = self.func(self.Z, stream=stream)
return self.A
def fprop(self, X, stream=None):
''' Forward propagation.
NOTE: If we do dropout, X will get mutated. Usually, X == lowerlayer.A.
Thus, we don't need to multiply by a dropout mask in bprop.'''
self.X, self.M = self._corrupt_input(X, stream=stream)
self.Z = op.dot(self.X, self.W, False, True, stream=stream)
self.Z = op.add_matvec(self.Z, self.b, out=self.Z, stream=stream)
self.A = self.func(self.Z, stream=stream)
return self.A
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 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 p
