def bprop(self, delta, momentum=0.0):
op.streams[2].synchronize() # make sure layer above is done
self.dfunc(delta, self.A, self.Z, stream=op.streams[0])
op.streams[0].synchronize()
op.add_dot(delta,
self.X,
self.dW,
True,
False,
alpha=1.0 / delta.shape[0],
beta=momentum,
stream=op.streams[0])
m = op.mean(delta, axis=0, stream=op.streams[1])
op.add_vec(self.db, 1.0, m, beta=momentum, stream=op.streams[1])
if self.l2_penalty > 0:
op.add_vec(self.dW, self.l2_penalty, self.W, stream=op.streams[0])
if not self.is_input_layer:
if self.dropout > 0.0 and self.activation not in ("relu",
"sigmoid"):
return op.dot(delta, self.W) * self.M
else:
return op.dot(delta, self.W)
else:
return 0.0
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 bprop(self, delta, momentum=0.0):
op.streams[2].synchronize() # make sure layer above is done
self.dfunc(delta, self.A, self.Z, stream=op.streams[0])
op.streams[0].synchronize()
op.add_dot(delta, self.X, self.dW, True, False,
alpha=1.0/delta.shape[0], beta=momentum, stream=op.streams[0])
m = op.mean(delta, axis=0, stream=op.streams[1])
op.add_vec(self.db, 1.0, m, beta=momentum, stream=op.streams[1])
if self.l2_penalty > 0:
op.add_vec(self.dW, self.l2_penalty, self.W, stream=op.streams[0])
if not self.is_input_layer:
if self.dropout > 0.0 and self.activation not in ("relu", "sigmoid"):
return op.dot(delta, self.W)*self.M
else:
return op.dot(delta, self.W)
else:
return 0.0
def test_csrmm_bug():
''' the 2nd call might crash'''
from scipy.sparse import csr_matrix
W = np.random.normal(size=(5, 3)).astype(np.float32, order="c")
X = np.random.laplace(size=(6, 3)).astype(np.float32)
X[X<0.1] = 0
X = csr_matrix(X, dtype=np.float32)
Xd = GPUCSRArray(X)
Wd = op.to_gpu(W)
Cd = op.dot(Xd, Wd, False, True, out=None, stream=op.streams[0])
op.add_dot(Cd, Xd, Wd, True, False, alpha=-0.3, beta=1.0, stream=op.streams[0])
op.mean(Cd, axis=0, stream=op.streams[1])
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
def test_csrmm_bug():
''' the 2nd call might crash'''
from scipy.sparse import csr_matrix
W = np.random.normal(size=(5, 3)).astype(np.float32, order="c")
X = np.random.laplace(size=(6, 3)).astype(np.float32)
X[X < 0.1] = 0
X = csr_matrix(X, dtype=np.float32)
Xd = GPUCSRArray(X)
Wd = op.to_gpu(W)
Cd = op.dot(Xd, Wd, False, True, out=None, stream=op.streams[0])
op.add_dot(Cd,
Xd,
Wd,
True,
False,
alpha=-0.3,
beta=1.0,
stream=op.streams[0])
op.mean(Cd, axis=0, stream=op.streams[1])
