def check_forward(self, x_data, t_data, w_data, samples_data):
x = chainer.Variable(x_data)
t = chainer.Variable(t_data)
w = chainer.Variable(w_data)
samples = chainer.Variable(samples_data)
y = functions.black_out(x, t, w, samples, self.reduce)
expect_y = numpy.empty((self.batch_size), dtype=numpy.float32)
for b in range(self.batch_size):
z = 0
for i in range(self.n_samples):
w = self.samples[b, i]
z += numpy.exp(self.W[w].dot(self.x[b]))
y0 = self.W[self.t[b]].dot(self.x[b])
z += numpy.exp(y0)
l = y0 - numpy.log(z)
for i in range(self.n_samples):
w = self.samples[b, i]
l += numpy.log(1 - numpy.exp(self.W[w].dot(self.x[b])) / z)
expect_y[b] = l
if self.reduce == 'mean':
loss = -numpy.sum(expect_y) / self.batch_size
else:
loss = -expect_y
testing.assert_allclose(y.data, loss, atol=1.e-4)
def check_forward(self, x_data, t_data, w_data, samples_data):
x = chainer.Variable(x_data)
t = chainer.Variable(t_data)
w = chainer.Variable(w_data)
samples = chainer.Variable(samples_data)
y = functions.black_out(x, t, w, samples, self.reduce)
expect_y = numpy.empty((self.batch_size), dtype=numpy.float32)
for b in range(self.batch_size):
z = 0
for i in range(self.n_samples):
w = self.samples[b, i]
z += numpy.exp(self.W[w].dot(self.x[b]))
y0 = self.W[self.t[b]].dot(self.x[b])
z += numpy.exp(y0)
l = y0 - numpy.log(z)
for i in range(self.n_samples):
w = self.samples[b, i]
l += numpy.log(1 - numpy.exp(self.W[w].dot(self.x[b])) / z)
expect_y[b] = l
if self.reduce == 'mean':
loss = -numpy.sum(expect_y) / self.batch_size
else:
loss = -expect_y
testing.assert_allclose(y.data, loss, atol=1.e-4)
def _black_out(x, t, W, samples):
return functions.black_out(x, t, W, samples, self.reduce)
def _black_out(x, t, W, samples):
return functions.black_out(x, t, W, samples, self.reduce)