def __call__(self, x, target, bf=False):
self.reset()
n_step = self.n_step
num_lm = x.shape[0]
loss_func = 0
if chainer.config.train:
r_buf = 0
l, s, b = self.first_forward(x, num_lm)
for i in range(n_step):
if i + 1 == n_step:
xm, lm, sm = self.make_img(x, l, s, num_lm, random=1)
l1, s1, y, b1 = self.recurrent_forward(xm, lm, sm)
loss, size_p = self.cul_loss(y, target, l, s, lm, sm)
loss_func += self.r_recognize * loss
r = xp.where(
xp.argmax(y.data, axis=1) == xp.argmax(target, axis=1),
1, 0).reshape((num_lm, 1)).astype(xp.float32)
loss_func += F.sum((r - b) * (r - b)) # loss baseline
k = self.r * (r - b.data) # calculate r
loss_func += F.sum(k * size_p)
return loss_func / num_lm
else:
xm, lm, sm = self.make_img(x, l, s, num_lm, random=1)
l1, s1, y, b1 = self.recurrent_forward(xm, lm, sm)
loss, size_p = self.cul_loss(y, target, l, s, lm, sm)
loss_func += loss
r = xp.where(
xp.argmax(y.data, axis=1) == xp.argmax(target, axis=1),
1, 0).reshape((num_lm, 1)).astype(xp.float32)
loss_func += F.sum((r - b) * (r - b)) # loss baseline
k = self.r * (r - b.data) # calculate r
loss_func += F.sum(k * size_p)
l = l1
s = s1
b = b1
else:
l, s, b1 = self.first_forward(x, num_lm)
for i in range(n_step):
if i + 1 == n_step:
if bf:
self.b_log += xp.sum(b1.data)
xm, lm, sm = self.make_img(x, l, s, num_lm, random=0)
l1, s1, y, b = self.recurrent_forward(xm, lm, sm)
accuracy = xp.sum(y.data * target)
if self.use_gpu:
accuracy = chainer.cuda.to_cpu(accuracy)
return accuracy
else:
xm, lm, sm = self.make_img(x, l, s, num_lm, random=0)
l1, s1, y, b = self.recurrent_forward(xm, lm, sm)
l = l1
s = s1
def __call__(self, x, target, mode=0):
self.reset()
n_step = self.n_step
num_lm = x.shape[0]
if chainer.config.train:
r_buf = 0
l, s, b = self.first_forward(x, num_lm)
for i in range(n_step):
if i + 1 == n_step:
xm, lm, sm = self.make_img(x, l, s, num_lm, random=1)
l1, s1, y, b1 = self.recurrent_forward(xm, lm, sm)
loss, size_p = self.cul_loss(y, target, l, s, lm, sm)
r_buf += size_p
r = xp.where(
xp.argmax(y.data, axis=1) == xp.argmax(target, axis=1),
1, 0).reshape((num_lm, 1)).astype(xp.float32)
loss += F.sum((r - b) * (r - b))
k = self.r * (r - b.data)
loss += F.sum(k * r_buf)
return loss / num_lm
else:
xm, lm, sm = self.make_img(x, l, s, num_lm, random=1)
l1, s1, y, b1 = self.recurrent_forward(xm, lm, sm)
loss, size_p = self.cul_loss(y, target, l, s, lm, sm)
r_buf += size_p
l = l1
s = s1
b = b1
else:
l, s, b1 = self.first_forward(x, num_lm)
for i in range(n_step):
if i + 1 == n_step:
xm, lm, sm = self.make_img(x, l, s, num_lm, random=0)
l1, s1, y, b = self.recurrent_forward(xm, lm, sm)
accuracy = xp.sum(y.data * target)
if self.use_gpu:
accuracy = chainer.cuda.to_cpu(accuracy)
return accuracy
else:
xm, lm, sm = self.make_img(x, l, s, num_lm, random=0)
l1, s1, y, b = self.recurrent_forward(xm, lm, sm)
l = l1
s = s1
def cul_loss(self, y, target, l, lm, num_lm, b):
l1, l2 = F.split_axis(l, indices_or_sections=2, axis=1)
m1, m2 = F.split_axis(lm, indices_or_sections=2, axis=1)
ln_p = ((l1 - m1) * (l1 - m1) + (l2 - m2) * (l2 - m2)) / self.var / 2
accuracy = y * target
loss = -F.sum(accuracy)
r = xp.where(
xp.argmax(y.data, axis=1) == xp.argmax(target.data, axis=1), 1,
0).reshape((num_lm, 1)).astype(xp.float32)
loss += F.sum((r - b) * (r - b))
bb = xp.sum(b.data) / num_lm
lossm = self.r * (r - bb)
loss += F.sum(Variable(lossm) * ln_p)
return loss
def s2_determin(self, x, t, l_list, s_list):
self.reset()
num_lm = x.data.shape[0]
s_list = xp.log10(s_list + 0.001) + 1
self.first_forward(x, num_lm)
xm, lm, sm = self.make_img(x, Variable(l_list[0]), Variable(s_list[0]), num_lm, random=0)
self.recurrent_forward(xm, lm, sm)
xm, lm, sm = self.make_img(x, Variable(l_list[1]), Variable(s_list[1]), num_lm, random=0)
l1, s1, y, b = self.recurrent_forward(xm, lm, sm)
accuracy = y.data * t.data
class_l = xp.argmax(y.data, axis=1)
return xp.sum(accuracy), class_l
def __call__(self,
x,
target,
num_lm,
batch_size=1,
train=1,
debug=0,
n_step=1):
if train == 1:
self.reset()
r_buf = 0
l, s, b = self.first_forward(x, num_lm)
for i in range(n_step):
if i + 1 == n_step:
xm, lm, sm = self.make_img(x, l, s, num_lm, random=1)
l1, s1, y, b1 = self.recurrent_forward(xm, lm, sm)
loss, size_p = self.cul_loss(y, target, l, s, lm, sm)
r_buf += size_p
r = xp.where(
xp.argmax(y.data, axis=1) == xp.argmax(target.data,
axis=1), 1,
0).reshape((num_lm, 1)).astype(xp.float32)
loss += F.sum((r - b) * (r - b))
k = self.r * (r - b.data)
loss += F.sum(k * r_buf)
return loss / num_lm
else:
xm, lm, sm = self.make_img(x, l, s, num_lm, random=1)
l1, s1, y, b1 = self.recurrent_forward(xm, lm, sm)
loss, size_p = self.cul_loss(y, target, l, s, lm, sm)
r_buf += size_p
l = l1
s = s1
b = b1
elif train == 0:
self.reset()
l, s, b1 = self.first_forward(x, num_lm)
for i in range(n_step):
if i + 1 == n_step:
xm, lm, sm = self.make_img(x, l, s, num_lm, random=0)
l1, s1, y, b = self.recurrent_forward(xm, lm, sm)
accuracy = y.data * target.data
return xp.sum(accuracy) / num_lm, y.data / n_step, xp.sum(
accuracy) / num_lm
else:
xm, lm, sm = self.make_img(x, l, s, num_lm, random=0)
l1, s1, y, b = self.recurrent_forward(xm, lm, sm)
l = l1
s = s1
elif train == 2:
sum_accuracy = 0
ydata = xp.zeros((num_lm, self.num_class))
self.reset()
l_list = xp.zeros((n_step, num_lm, 2))
s_list = xp.zeros((n_step, num_lm, 1))
l, s, b1 = self.first_forward(x, num_lm)
l_list[0] = l.data
s_list[0] = s.data
for i in range(n_step):
if i + 1 == n_step:
xm, lm, sm = self.make_img(x, l, s, num_lm, random=0)
l1, s1, y, b = self.recurrent_forward(xm, lm, sm)
accuracy = y.data * target.data
sum_accuracy += xp.sum(accuracy)
ydata += y.data
z = np.power(10, s_list - 1)
return sum_accuracy / (
num_lm * n_step), ydata / n_step, xp.sum(
accuracy, axis=1) / num_lm, l_list, z
else:
xm, lm, sm = self.make_img(x, l, s, num_lm, random=0)
l1, s1, y, b = self.recurrent_forward(xm, lm, sm)
accuracy = y.data * target.data
sum_accuracy += xp.sum(accuracy)
ydata += y.data
l = l1
s = s1
l_list[i + 1] = l.data
s_list[i + 1] = s.data
return False
