def forward_cpu(self, inputs):
x, t = inputs
self.y, = sigmoid.Sigmoid().forward_cpu((x,))
# stable computation of the cross entropy.
loss = -numpy.sum(
x * (t - (x >= 0)) - numpy.log1p(numpy.exp(-numpy.abs(x))))
return numpy.array(loss / t.shape[0], dtype=x.dtype),
def forward_gpu(self, inputs):
x, t = inputs
self.y, = sigmoid.Sigmoid(self.use_cudnn).forward_gpu((x, ))
loss = -cuda.reduce(
'int* t, float* x',
'x[i] * (t[i] - (x[i] >= 0)) - log1pf(expf(-fabsf(x[i])))', 'a+b',
'0', 'sigmoid_crossent_fwd', numpy.float32)(t, x)
return loss / t.shape[0],
def forward_gpu(self, inputs):
x, t = inputs
self.y, = sigmoid.Sigmoid(self.use_cudnn).forward_gpu((x, ))
loss = cuda.reduce('T x, S t, T inv_cnt', 'T out',
'x * (t - (x >= 0)) - log1p(exp(-fabs(x)))',
'a + b', 'out = a * inv_cnt', 0,
'sigmoid_crossent_fwd')(x, t, -1.0 / t.shape[0])
return loss,
def backward(self, inputs, grad_outputs):
x, t = inputs
gloss = grad_outputs[0]
y, = sigmoid.Sigmoid(self.use_cudnn).forward((x,))
dtype = y.dtype
gx = (gloss * self.ignore_mask * (y - t.astype(dtype)) /
dtype.type(self.count))
return gx, None
def backward(self, inputs, grad_outputs):
xp = cuda.get_array_module(*inputs)
x, t = inputs
gloss = grad_outputs[0]
y, = sigmoid.Sigmoid(self.use_cudnn).forward((x, ))
gx = xp.divide(gloss * self.ignore_mask * (y - t),
self.count,
dtype=y.dtype)
return gx, None
