为什么我在声明这个数组时遇到语法错误？

import numpy as np def train(self, data, all_y_trues): ''' - data is a (n x 3) numpy array, n = # of samples in the dataset. - all_y_trues is a numpy array with n elements. Elements in all_y_trues correspond to those in data. ''' learn_rate = 0.1 epochs = 1000 # number of times to loop through the entire dataset for epoch in range(epochs): for x, y_true in zip(data, all_y_trues): # --- Do a feedforward (we'll need these values later) h1 = sigmoid(np.dot(x, self.wforh1) + self.b1) h2 = sigmoid(np.dot(x, self.wforh2) + self.b2) h3 = sigmoid(np.dot(x, self.wforh3) + self.b3) h4 = sigmoid(np.dot(x, self.wforh4) + self.b4) h5 = sigmoid(np.dot(x, self.wforh5) + self.b5) sum_h1 = np.dot(x, self.wforh1) + self.b1 sum_h2 = np.dot(x, self.wforh2) + self.b2 sum_h3 = np.dot(x, self.wforh3) + self.b3 sum_h4 = np.dot(x, self.wforh4) + self.b4 sum_h5 = np.dot(x, self.wforh5) + self.b5 y = self.feedforward(x) hi1 = sigmoid(np.dot(y, self.wforhi1) + self.b6) hi2 = sigmoid(np.dot(y, self.wforhi2) + self.b7) hi3 = sigmoid(np.dot(y, self.wforhi3) + self.b8) hi4 = sigmoid(np.dot(y, self.wforhi4) + self.b9) hi5 = sigmoid(np.dot(y, self.wforhi5) + self.b10) sum_hi1 = np.dot(y, self.wforhi1) + self.b6 sum_hi2 = np.dot(y, self.wforhi2) + self.b7 sum_hi3 = np.dot(y, self.wforhi3) + self.b8 sum_hi4 = np.dot(y, self.wforhi4) + self.b9 sum_hi5 = np.dot(y, self.wforhi5) + self.b10 z = np.array([hi1,hi2,hi3,hi4,hi5]) h = np.array([h1,h2,h3,h4,h5]) o1 = self.feedforward2(y) sum_o1 = np.dot(z, self.wforo1) + self.b11 y_pred = o1 # --- Calculate partial derivatives. # --- Naming: d_L_d_w1 represents "partial L / partial w1" d_L_d_ypred = -2 * (y_true - y_pred) # Neuron o1 NEW d_ypred_d_w = [] for i in range(5): d_ypred_d_w.append(z[i] * deriv_sigmoid(sum_o1)) #d_ypred_d_w41 = hi1 * deriv_sigmoid(sum_o1) #d_ypred_d_w42 = hi2 * deriv_sigmoid(sum_o1) #d_ypred_d_w43 = hi3 * deriv_sigmoid(sum_o1) #d_ypred_d_w44 = hi4 * deriv_sigmoid(sum_o1) #d_ypred_d_w45 = hi5 * deriv_sigmoid(sum_o1) d_ypred_d_b11 = deriv_sigmoid(sum_o1) d_ypred_d_hi = [] for i in range(5): d_ypred_d_hi.append(self.wforo1[i] * deriv_sigmoid(sum_o1)) d_ypred_d_h = [] for i in range(5): d_ypred_d_h.append(deriv_sigmoid(sum_o1) * (self.wforo1[0] * deriv_sigmoid(sum_hi1) * self.wforhi1[i] + self.wforo1[1] * deriv_sigmoid(sum_hi2) * self.wforhi2[i] + self.wforo1[2] * deriv_sigmoid(sum_hi3) * self.wforhi3[i] + self.wforo1[3] * deriv_sigmoid(sum_hi4) * self.wforhi4[i] + self.wforo1[4] * deriv_sigmoid(sum_hi5) * self.wforhi5[i]) #d_ypred_d_h1 = deriv_sigmoid(sum_o1) * (self.wforo1[0] * deriv_sigmoid(sum_hi1) * self.wforhi1[0] + self.wforo1[1] * deriv_sigmoid(sum_hi2) * self.wforhi2[0] + self.wforo1[2] * deriv_sigmoid(sum_hi3) * self.wforhi3[0] + self.wforo1[3] * deriv_sigmoid(sum_hi4) * self.wforhi4[0] + self.wforo1[4] * deriv_sigmoid(sum_hi5) * self.wforhi5[0]) #d_ypred_d_h2 = deriv_sigmoid(sum_o1) * (self.wforo1[0] * deriv_sigmoid(sum_hi1) * self.wforhi1[1] + self.wforo1[1] * deriv_sigmoid(sum_hi2) * self.wforhi2[1] + self.wforo1[2] * deriv_sigmoid(sum_hi3) * self.wforhi3[1] + self.wforo1[3] * deriv_sigmoid(sum_hi4) * self.wforhi4[1] + self.wforo1[4] * deriv_sigmoid(sum_hi5) * self.wforhi5[1]) #d_ypred_d_h3 = deriv_sigmoid(sum_o1) * (self.wforo1[0] * deriv_sigmoid(sum_hi1) * self.wforhi1[2] + self.wforo1[1] * deriv_sigmoid(sum_hi2) * self.wforhi2[2] + self.wforo1[2] * deriv_sigmoid(sum_hi3) * self.wforhi3[2] + self.wforo1[3] * deriv_sigmoid(sum_hi4) * self.wforhi4[2] + self.wforo1[4] * deriv_sigmoid(sum_hi5) * self.wforhi5[2]) #d_ypred_d_h4 = deriv_sigmoid(sum_o1) * (self.wforo1[0] * deriv_sigmoid(sum_hi1) * self.wforhi1[3] + self.wforo1[1] * deriv_sigmoid(sum_hi2) * self.wforhi2[3] + self.wforo1[2] * deriv_sigmoid(sum_hi3) * self.wforhi3[3] + self.wforo1[3] * deriv_sigmoid(sum_hi4) * self.wforhi4[3] + self.wforo1[4] * deriv_sigmoid(sum_hi5) * self.wforhi5[3]) #d_ypred_d_h5 = deriv_sigmoid(sum_o1) * (self.wforo1[0] * deriv_sigmoid(sum_hi1) * self.wforhi1[4] + self.wforo1[1] * deriv_sigmoid(sum_hi2) * self.wforhi2[4] + self.wforo1[2] * deriv_sigmoid(sum_hi3) * self.wforhi3[4] + self.wforo1[3] * deriv_sigmoid(sum_hi4) * self.wforhi4[4] + self.wforo1[4] * deriv_sigmoid(sum_hi5) * self.wforhi5[4]) # Neuron hi1 NEW d_hi1_d_w = [] for i in range(5): d_hi1_d_w.append(h[i] * deriv_sigmoid(sum_hi1)) d_hi1_d_b6 = deriv_sigmoid(sum_hi1) # Neuron hi2 NEW d_hi2_d_w = [] for i in range(5): d_hi2_d_w.append(h[i] * deriv_sigmoid(sum_hi2)) d_hi2_d_b7 = deriv_sigmoid(sum_hi2) # Neuron hi3 NEW d_hi3_d_w = [] for i in range(5): d_hi3_d_w.append(h[i] * deriv_sigmoid(sum_hi3)) d_hi3_d_b8 = deriv_sigmoid(sum_hi3) # Neuron hi4 NEW d_hi4_d_w = [] for i in range(5): d_hi4_d_w.append(h[i] * deriv_sigmoid(sum_hi4)) d_hi4_d_b9 = deriv_sigmoid(sum_hi4) #Neuron hi5 NEW d_hi5_d_w = [] for i in range(5): d_hi5_d_w.append(h[i] * deriv_sigmoid(sum_hi5)) d_hi5_d_b10 = deriv_sigmoid(sum_hi5) #Neuron h1 NEW d_h1_d_w = [] for i in range(3): d_h1_d_w.append(x[i] * deriv_sigmoid(sum_h1)) d_h1_d_b1 = deriv_sigmoid(sum_h1) #Neuron h2 NEW d_h2_d_w = [] for i in range(3): d_h2_d_w.append(x[i] * deriv_sigmoid(sum_h2)) d_h2_d_b2 = deriv_sigmoid(sum_h2) #Neuron h3 NEW d_h3_d_w = [] for i in range(3): d_h3_d_w.append(x[i] * deriv_sigmoid(sum_h3)) d_h3_d_b3 = deriv_sigmoid(sum_h3) #Neuron h4 NEW d_h4_d_w = [] for i in range(3): d_h4_d_w.append(x[i] * deriv_sigmoid(sum_h4)) d_h4_d_b4 = deriv_sigmoid(sum_h4) #Neuron h5 NEW d_h5_d_w = [] for i in range(3): d_h5_d_w.append(x[i] * deriv_sigmoid(sum_h5)) d_h5_d_b5 = deriv_sigmoid(sum_h5) # --- Update weights and biases # Neuron h1 for i in range(3): self.wforh1[i] = self.wforh1[i]- learn_rate * d_L_d_ypred * d_ypred_d_h[0] * d_h1_d_w[i] self.b1 = self.b1 - learn_rate * d_L_d_ypred * d_ypred_d_h[0] * d_h1_d_b1 # Neuron h2 for i in range(3): self.wforh2[i] = self.wforh2[i] - learn_rate * d_L_d_ypred * d_ypred_d_h[1] * d_h2_d_w[i] self.b2 = self.b2 - learn_rate * d_L_d_ypred * d_ypred_d_h[1] * d_h2_d_b2 # Neuron h3 self.w7 -= learn_rate * d_L_d_ypred * d_ypred_d_h3 * d_h3_d_w7 self.w8 -= learn_rate * d_L_d_ypred * d_ypred_d_h3 * d_h3_d_w8 self.w9 -= learn_rate * d_L_d_ypred * d_ypred_d_h3 * d_h3_d_w9 self.b3 -= learn_rate * d_L_d_ypred * d_ypred_d_h3 * d_h3_d_b3 # Neuron h4 self.w10 -= learn_rate * d_L_d_ypred * d_ypred_d_h4 * d_h4_d_w10 self.w11 -= learn_rate * d_L_d_ypred * d_ypred_d_h4 * d_h4_d_w11 self.w12 -= learn_rate * d_L_d_ypred * d_ypred_d_h4 * d_h4_d_w12 self.b4 -= learn_rate * d_L_d_ypred * d_ypred_d_h4 * d_h4_d_b4 # Neuron h5 self.w13 -= learn_rate * d_L_d_ypred * d_ypred_d_h5 * d_h5_d_w13 self.w14 -= learn_rate * d_L_d_ypred * d_ypred_d_h5 * d_h5_d_w14 self.w15 -= learn_rate * d_L_d_ypred * d_ypred_d_h5 * d_h5_d_w15 self.b5 -= learn_rate * d_L_d_ypred * d_ypred_d_h5 * d_h5_d_b5 # Neuron hi1 self.w16 -= learn_rate * d_L_d_ypred * d_ypred_d_hi1 * d_hi1_d_w16 self.w17 -= learn_rate * d_L_d_ypred * d_ypred_d_hi1 * d_hi1_d_w17 self.w18 -= learn_rate * d_L_d_ypred * d_ypred_d_hi1 * d_hi1_d_w18 self.w19 -= learn_rate * d_L_d_ypred * d_ypred_d_hi1 * d_hi1_d_w19 self.w20 -= learn_rate * d_L_d_ypred * d_ypred_d_hi1 * d_hi1_d_w20 self.b6 -= learn_rate * d_L_d_ypred * d_ypred_d_hi1 * d_hi1_d_b6 # Neuron hi2 self.w21 -= learn_rate * d_L_d_ypred * d_ypred_d_hi2 * d_hi2_d_w21 self.w22 -= learn_rate * d_L_d_ypred * d_ypred_d_hi2 * d_hi2_d_w22 self.w23 -= learn_rate * d_L_d_ypred * d_ypred_d_hi2 * d_hi2_d_w23 self.w24 -= learn_rate * d_L_d_ypred * d_ypred_d_hi2 * d_hi2_d_w24 self.w25 -= learn_rate * d_L_d_ypred * d_ypred_d_hi2 * d_hi2_d_w25 self.b7 -= learn_rate * d_L_d_ypred * d_ypred_d_hi2 * d_hi2_d_b7 # Neuron hi3 self.w26 -= learn_rate * d_L_d_ypred * d_ypred_d_hi3 * d_hi3_d_w26 self.w27 -= learn_rate * d_L_d_ypred * d_ypred_d_hi3 * d_hi3_d_w27 self.w28 -= learn_rate * d_L_d_ypred * d_ypred_d_hi3 * d_hi3_d_w28 self.w29 -= learn_rate * d_L_d_ypred * d_ypred_d_hi3 * d_hi3_d_w29 self.w30 -= learn_rate * d_L_d_ypred * d_ypred_d_hi3 * d_hi3_d_w30 self.b8 -= learn_rate * d_L_d_ypred * d_ypred_d_hi3 * d_hi3_d_b8 # Neuron hi4 self.w31 -= learn_rate * d_L_d_ypred * d_ypred_d_hi4 * d_hi4_d_w31 self.w32 -= learn_rate * d_L_d_ypred * d_ypred_d_hi4 * d_hi4_d_w32 self.w33 -= learn_rate * d_L_d_ypred * d_ypred_d_hi4 * d_hi4_d_w33 self.w34 -= learn_rate * d_L_d_ypred * d_ypred_d_hi4 * d_hi4_d_w34 self.w35 -= learn_rate * d_L_d_ypred * d_ypred_d_hi4 * d_hi4_d_w35 self.b9 -= learn_rate * d_L_d_ypred * d_ypred_d_hi4 * d_hi4_d_b9 # Neuron hi5 NEW self.w36 -= learn_rate * d_L_d_ypred * d_ypred_d_hi5 * d_hi5_d_w36 self.w37 -= learn_rate * d_L_d_ypred * d_ypred_d_hi5 * d_hi5_d_w37 self.w38 -= learn_rate * d_L_d_ypred * d_ypred_d_hi5 * d_hi5_d_w38 self.w39 -= learn_rate * d_L_d_ypred * d_ypred_d_hi5 * d_hi5_d_w39 self.w40 -= learn_rate * d_L_d_ypred * d_ypred_d_hi5 * d_hi5_d_w40 self.b10 -= learn_rate * d_L_d_ypred * d_ypred_d_hi5 * d_hi5_d_b10 # Neuron o1 NEW self.w41 -= learn_rate * d_L_d_ypred * d_ypred_d_w41 self.w42 -= learn_rate * d_L_d_ypred * d_ypred_d_w42 self.w43 -= learn_rate * d_L_d_ypred * d_ypred_d_w43 self.w44 -= learn_rate * d_L_d_ypred * d_ypred_d_w44 self.w45 -= learn_rate * d_L_d_ypred * d_ypred_d_w45 self.b11 -= learn_rate * d_L_d_ypred * d_ypred_d_b11 # --- Calculate total loss at the end of each epoch if epoch % 10 == 0: firstlayer = np.apply_along_axis(self.feedforward, 1, data) y_preds = np.apply_along_axis(self.feedforward2, 1, firstlayer) loss = mse_loss(all_y_trues, y_preds) print("Epoch %d loss: %.3f" % (epoch, loss)) # Define dataset data = np.array([ [-2, -1, 16], # Alice [25, 6, -5], # Bob [17, 4, 20], # Charlie [-15, -6 ,7], # Diana ]) all_y_trues = np.array([ 1, # Alice 0, # Bob 0, # Charlie 1, # Diana ]) # Train our neural network! network = OurNeuralNetwork() network.train(data, all_y_trues)

1条回答

网友

1楼 · 发布于 2024-10-01 13:35:54

您似乎在前一行中缺少(：

d_ypred_d_h.append(deriv_sigmoid(sum_o1) * (self.wforo1[0] * deriv_sigmoid(sum_hi1) * self.wforhi1[i] + self.wforo1[1] * deriv_sigmoid(sum_hi2) * self.wforhi2[i] + self.wforo1[2] * deriv_sigmoid(sum_hi3) * self.wforhi3[i] + self.wforo1[3] * deriv_sigmoid(sum_hi4) * self.wforhi4[i] + self.wforo1[4] * deriv_sigmoid(sum_hi5) * self.wforhi5[i])

更新行，如下所示：

d_ypred_d_h.append(deriv_sigmoid(sum_o1) * (self.wforo1[0] * deriv_sigmoid(sum_hi1) * self.wforhi1[i] + self.wforo1[1] * deriv_sigmoid(sum_hi2) * self.wforhi2[i] + self.wforo1[2] * deriv_sigmoid(sum_hi3) * self.wforhi3[i] + self.wforo1[3] * deriv_sigmoid(sum_hi4) * self.wforhi4[i] + self.wforo1[4] * deriv_sigmoid(sum_hi5) * self.wforhi5[i]))

相关问题更多 >

编程相关推荐

热门问题

热门文章