误差反向传播(ANN人工神经网络)

import numpy as np from collections import OrderedDict from net_layer import * from deeplearning.fuction import numerical_gradient class TwoLayerNet: def __init__(self,input_size,hidden_size,output_size, weight_init_std=0.01): #初始化权重 self.params = {} self.params['W1'] = weight_init_std*np.random.randn(input_size,hidden_size) self.params['b1'] = np.zeros(hidden_size) self.params['W2'] = weight_init_std*np.random.randn(hidden_size,output_size) self.params['b2'] = np.zeros(output_size) """ OrderedDict是有序字典 """ #生成层 self.layers = OrderedDict() self.layers['Affine1'] = Affine(self.params['W1'],self.params['b1']) self.layers['Relu1'] = Relu() self.layers['Affine2'] = Affine(self.params['W2'],self.params['b2']) self.lastLayer = SoftMaxTithLoss() #有序字典的作用 体现在向前传播 def predict(self,x): for layer in self.layers.values(): x = layer.forward(x) return x #损失函数 我们以前得到的y是softmax之后的，现在的predict并没有经过softmax def loss(self,x,t): y = self.predict(x) return self.lastLayer.forward(y,t) def accuracy(self,x,t): y = self.predict(x) #y获得得分情况 y = np.argmax(y,axis = 1) #没经过softmax y获得最高得分 if t.ndim != 1 : #如果t是1维 axis=1会出错,mini_batch不会是1维 t = np.argmax(t,axis = 1) acuracy = np.sum((y==t)/float(x.shape[0])) return acuracy #数值微分法求梯度 def numerical_gradient(self,x,t): loss_W = lambda W:self.loss(x,t) grads = {} grads['W1'] = numerical_gradient(loss_W,self.params['W1']) grads['b1'] = numerical_gradient(loss_W, self.params['b1']) grads['W2'] = numerical_gradient(loss_W, self.params['W2']) grads['b2'] = numerical_gradient(loss_W, self.params['b2']) return grads #误差反向传播求梯度 def gradient(self,x,t): #forward 向前传播就是获取损失函数值的过程 self.loss(x,t) #backward dout = 1 dout = self.lastLayer.backward(dout) layers = list(self.layers.values()) layers.reverse() for layer in layers: dout = layer.backward(dout) grads = {} grads['W1'] = self.layers['Affine1'].dW grads['b1'] = self.layers['Affine1'].db grads['W2'] = self.layers['Affine2'].dW grads['b2'] = self.layers['Affine2'].db return grads