def backward(self, x, d, z1, z2, y):
grad = {}
W1, W2, W3 = network['W1'], network['W2'], network['W3']
b1, b2, b3 = network['b1'], network['b2'], network['b3']
# 出力層でのデルタ
delta3 = functions.d_softmax_with_loss(d, y)
# b3の勾配
grad['b3'] = np.sum(delta3, axis=0)
# W3の勾配
grad['W3'] = np.dot(z2.T, delta3)
# 活性化関数の導関数 Relu関数
delta2 = np.dot(delta3, W3.T) * functions.d_sigmoid(z2)
# b2の勾配
grad['b2'] = np.sum(delta2, axis=0)
# W2の勾配
grad['W2'] = np.dot(z1.T, delta2)
# 活性化関数の導関数 Relu関数
delta1 = np.dot(delta2, W2.T) * functions.d_sigmoid(z1)
# b1の勾配
grad['b1'] = np.sum(delta1, axis=0)
# W1の勾配
grad['W1'] = np.dot(x.T, delta1)
return grad
def backward(x, d, z1, z2, y):
grad = {}
W1, W2, W3 = network['W1'], network['W2'], network['W3']
b1, b2, b3 = network['b1'], network['b2'], network['b3']
########### 変更箇所 ##############
hidden_d_f = functions.d_relu
#################################
# 出力層でのデルタ
delta3 = functions.d_softmax_with_loss(d, y)
# b3の勾配
grad['b3'] = np.sum(delta3, axis=0)
# W3の勾配
grad['W3'] = np.dot(z2.T, delta3)
# 2層でのデルタ
delta2 = np.dot(delta3, W3.T) * hidden_d_f(z2)
# b2の勾配
grad['b2'] = np.sum(delta2, axis=0)
# W2の勾配
grad['W2'] = np.dot(z1.T, delta2)
# 1層でのデルタ
delta1 = np.dot(delta2, W2.T) * hidden_d_f(z1)
# b1の勾配
grad['b1'] = np.sum(delta1, axis=0)
# W1の勾配
grad['W1'] = np.dot(x.T, delta1)
return grad
def backward(x, d, z1, y):
grad = {}
W1, W2 = network['W1'], network['W2']
b1, b2 = network['b1'], network['b2']
# 出力層でのデルタ
delta2 = functions.d_softmax_with_loss(d, y)
# b2の勾配
grad['b2'] = np.sum(delta2, axis=0)
# W2の勾配
grad['W2'] = np.dot(z1.T, delta2)
# 1層でのデルタ
delta1 = np.dot(delta2, W2.T) * functions.d_relu(z1)
# b1の勾配
grad['b1'] = np.sum(delta1, axis=0)
# W1の勾配
grad['W1'] = np.dot(x.T, delta1)
return grad
