MLP的两种实现（不同在于forward）

import numpy as np
from sklearn import datasets
import matplotlib.pyplot as plt
from matplotlib.colors import ListedColormap
def sigmoid(x):
    return 1 / (1 + np.exp(-x))

def dsigmoid(y):
    return y * (1 - y)

def tanh(x):
    return np.tanh(x)

def dtanh(y):
    return 1.0 - y ** 2

class MLPClassifier:
    def __init__(self, layers, activation='tanh', epochs=20, learning_rate=0.01):
        # 第一层为输入层, 层数应等于样本特征数
        # 最后一层为输出层
        # 再算上中间层, 所以len(layers)最小为3
        self.epochs = epochs
        self.eta = learning_rate
        self.layers = [np.zeros(layers[0])]
        self.weights = []
        self.biases = []
        for i in range(len(layers) - 1):
            # 这三个者的初始值是随意的
            weight = np.random.random((layers[i + 1], layers[i]))
            layer = np.ones(layers[i + 1])
            bias = np.random.random(layers[i + 1])
            self.weights.append(weight)
            self.layers.append(layer)
            self.biases.append(bias)
        if activation == 'tanh':
            self.activation = tanh
            self.dactivation = dtanh
        elif activation == 'sigmoid':
            self.activation = sigmoid
            self.dactivation = dsigmoid
    def fit(self, X, y):
        for _ in range(self.epochs):
            # 随机梯度下降
            indexes = np.random.permutation(X.shape[0])
            for i in range(X.shape[0]):
                self.forward(X[indexes[i]])
                self.backward(y[indexes[i]])
        return self
    # 方便二维图像的可视化, 实际预测的结果可能不止有一个维度, 不一定能和数值进行比较
    def predict(self, X):
        return np.where(self.predict_prob(X) >= 0.5, 1, 0)
    def predict_prob(self, X):
        y = np.empty((X.shape[0], len(self.layers[-1])))
        for i in range(X.shape[0