def forward(self, x, t):
self.t = t
self.y = softmax(x)
# 教師ラベルがone-hotベクトルの場合、正解のインデックスに変換
if self.t.size == self.y.size:
self.t = self.t.argmax(axis=1)
loss = cross_entropy_error(self.y, self.t)
return loss
def predict(network, x):
w1, w2, w3 = network['W1'], network['W2'], network['W3']
b1, b2, b3 = network['b1'], network['b2'], network['b3']
a1 = np.dot(x, w1) + b1
z1 = sigmoid(a1)
a2 = np.dot(z1, w2) + b2
z2 = sigmoid(a2)
a3 = np.dot(z2, w3) + b3
y = softmax(a3)
return y
def generate(self, start_id, skip_ids=None, sample_size=100):
word_ids = [start_id]
x = start_id
while len(word_ids) < sample_size:
x = np.array(x).reshape(1, 1)
score = self.predict(x).flatten()
p = softmax(score).flatten()
sampled = np.random.choice(len(p), size=1, p=p)
if (skip_ids is None) or (sampled not in skip_ids):
x = sampled
word_ids.append(int(x))
return word_ids
def forward(self, xs, ts):
N, T, V = xs.shape
if ts.ndim == 3: # 教師ラベルがone-hotベクトルの場合
ts = ts.argmax(axis=2)
mask = (ts != self.ignore_label)
# バッチ分と時系列分をまとめる（reshape）
xs = xs.reshape(N * T, V)
ts = ts.reshape(N * T)
mask = mask.reshape(N * T)
ys = softmax(xs)
ls = np.log(ys[np.arange(N * T), ts])
ls *= mask # ignore_labelに該当するデータは損失を0にする
loss = -np.sum(ls)
loss /= mask.sum()
self.cache = (ts, ys, mask, (N, T, V))
return loss
def forward(self, x):
self.out = softmax(x)
return self.out
def loss(self, x, t):
z = self.predict(x)
y = softmax(z)
loss = cross_entropy_error(y, t)
return loss