def compute_loss(y, t):
# softmax cross entropy
score = chx.log_softmax(y, axis=1)
mask = (t[:, chx.newaxis] == chx.arange(
10, dtype=t.dtype)).astype(score.dtype)
# TODO(beam2d): implement mean
return -(score * mask).sum() * (1 / y.shape[0])
def compute_loss(y, t):
# softmax cross entropy
score = chx.log_softmax(y, axis=1)
mask = (t[:, chx.newaxis] == chx.arange(1000,
dtype=t.dtype)).astype(score.dtype)
# TODO(beam2d): implement mean
return -(score * mask).sum() * (1 / y.shape[0])
def forward_xp(self, inputs, xp):
x, = inputs
axis = self.axis
if xp is chainerx:
return chainerx.log_softmax(x, axis=axis),
x = x.astype(self.out_dtype)
axis = axis if axis is not None else 1
return x - numpy.log(numpy.exp(x).sum(axis=axis, keepdims=True)),
def forward_chainerx(self, inputs):
# TODO(niboshi): Current implementation is only intended to support
# MNIST example.
x, t = inputs
num_classes = x.shape[1]
score = chainerx.log_softmax(x, axis=1)
mask = (t[:, chainerx.newaxis] == chainerx.arange(
num_classes, dtype=t.dtype, device=x.device)).astype(score.dtype)
# TODO(beam2d): implement mean
y = -(score * mask).sum() * (1 / x.shape[0])
return y,
def forward_chainerx(self, inputs):
# TODO(niboshi): Current implementation is only intended to support
# MNIST example.
x, t = inputs
num_classes = x.shape[1]
score = chainerx.log_softmax(x, axis=1)
mask = (t[:, chainerx.newaxis] == chainerx.arange(
num_classes, dtype=t.dtype, device=x.device)).astype(score.dtype)
# TODO(beam2d): implement mean
y = -(score * mask).sum() * (1 / x.shape[0])
return y,
def forward_chainerx(self, inputs):
if self.reduce == 'mean' and self.normalize:
x, t = inputs
n_classes = x.shape[1]
score = chainerx.log_softmax(x, axis=1)
mask = (t[:, chainerx.newaxis] == chainerx.arange(
n_classes, dtype=t.dtype, device=x.device)).astype(score.dtype)
y = (score * mask).sum() * (-1 / mask.sum())
return y,
x, t = inputs
y = chainerx.softmax_cross_entropy(x, t)
if self.reduce == 'mean':
return y.mean(),
return y,
def test_log_softmax_invalid(device, a_shape, axis, dtype):
a = array_utils.create_dummy_ndarray(chainerx, a_shape, dtype)
with pytest.raises(chainerx.DimensionError):
return chainerx.log_softmax(a, axis=axis)
def forward_chainerx(self, xs):
return chainerx.log_softmax(xs[0], axis=self.axis),
def compute_loss(y, t): score = chx.log_softmax(y, axis=1) mask = (t[:, chx.newaxis]==chx.arange(10, dtype=t.dtype)).astype(score.dtype) return -(score * mask).sum() * (1 / y.shape[0])
def test_log_softmax_invalid(device, a_shape, axis, float_dtype):
a = array_utils.create_dummy_ndarray(chainerx, a_shape, float_dtype)
with pytest.raises(chainerx.DimensionError):
return chainerx.log_softmax(a, axis=axis)
def forward_chainerx(self, xs):
return chainerx.log_softmax(xs[0], axis=self.axis),
