def forward(self, x, t):
self.t = t
self.y = softmax(x)
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(self, x):
W1, W2 = self.params['W1'], self.params['W2']
b1, b2 = self.params['b1'], self.params['b2']
a1 = np.dot(x, W1) + b1
z1 = sigmoid(a1)
a2 = np.dot(z1, W2) + b2
y = softmax(a2)
return y
def loss(self, x, t):
"""
计算损失函数
:param x:
:param t: 正确标签
:return:
"""
z = self.predict(x)
y = softmax(z)
loss = cross_entropy_error(y, t)
return loss
def get_result_matrix(self, x):
"""
Возвращает матрицу активаций выходного слоя
:param x: Матрица входов, (n, m)
:return: Матрица выходных активаций, (n, N)
"""
next_layer_input = np.append(np.ones((x.shape[0], 1), dtype=int), x, axis=1)
for layer in self.layers[:-1]:
activations = layer.process_input(next_layer_input)
next_layer_input = np.append(np.ones((len(activations), 1), dtype=int), activations, axis=1)
self.layers[-1].process_input(next_layer_input)
sums = self.layers[-1].intermediate_sums
res = []
for vect in sums:
res.append(softmax(vect))
return np.array(res)
def predict(network, x):
"""
各个标签对应的概率
:return:
"""
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