def test_exponent_logarithm_operators():
a = 2 * nd.ones(shape=LARGE_X)
# exponent
result = nd.exp(a)
assert result[-1] == 7.389056
assert result.shape == a.shape
# exponent minus 1
result = nd.expm1(a)
assert result[-1] == 6.389056
assert result.shape == a.shape
# log2
result = nd.log2(a)
assert result[-1] == 1
assert result.shape == a.shape
# log10
result = nd.log10(a)
assert result[-1] == 0.30103
assert result.shape == a.shape
# log1p
result = nd.log1p(a)
assert result[-1] == 1.0986123
assert result.shape == a.shape
# log
result = nd.log(a)
assert result[-1] == 0.6931472
assert result.shape == a.shape
def loss(x):
d = x + 3 * 1.0
predict = nd.array([[0, x / d, 1 / d, 1 / d, 1 / d],])
return crit( nd.log1p(predict), nd.array([1]))
true_dist = nd.where(target_mask, nd.zeros_like(true_dist) + self.confidence, true_dist)
true_dist[:, self.padding_idx] = 0
mask = nd.equal(target,self.padding_idx)
if len(mask.shape) > 0:
true_dist = nd.where( nd.squeeze(mask), nd.zeros_like(true_dist) ,true_dist )
self.true_dist = true_dist
return self.criterion(x, true_dist.as_in_context(cfg.ctx))
if cfg.DEBUG_ON:
crit = LabelSmoothing(5, 0, 0.4)
predict = nd.array([[0, 0.2, 0.7, 0.1, 0],
[0, 0.2, 0.7, 0.1, 0],
[0, 0.2, 0.7, 0.1, 0]])
v = crit( nd.log1p(predict), nd.array([2,1,0]))
# Show the target distributions expected by the system.
plt.imshow(crit.true_dist.asnumpy())
if cfg.DEBUG_ON:
crit = LabelSmoothing(5, 0, 0.1)
def loss(x):
d = x + 3 * 1.0
predict = nd.array([[0, x / d, 1 / d, 1 / d, 1 / d],])
return crit( nd.log1p(predict), nd.array([1]))
plt.figure()
L = [loss(x).asnumpy()[0] for x in range(1, 100)]
plt.plot(np.arange(1, 100),L)
