pytorch深度学习笔记13
目录
摘要
反向传播代码实现
摘要
本篇文章继续学习尚硅谷深度学习教程，学习内容是反向传播代码实现
反向传播代码实现
在之前手写数字识别案例的基础上，对SGD的计算过程进行优化。核心就是使用误差的反向传播法来计算梯度，而不是使用差分数值计算；这将大大提升学习的效率。
对于二层网络TwoLayerNet，隐藏层由一个Affine层和一个ReLU层组成，输出层则由一个Affine层和一个Softmax-with-Loss层组成。由于之前已经实现了各层的类，现在只要用“搭积木”的方式将它们拼接在一起就可以了。
将TwoLayerNet类的代码实现改进如下：
import numpy as np from common.layers import * from common.gradient import numerical_gradient from collections import OrderedDict 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) # 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 = SoftmaxWithLoss() def predict(self, x): for layer in self.layers.values(): x = layer.forward(x) return x # x:输入数据, t:监督数据 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 = np.argmax(y, axis=1) if t.ndim != 1 : t = np.argmax(t, axis=1) accuracy = np.sum(y == t) / float(x.shape[0]) return accuracy # x:输入数据, t:监督数据 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 def gradient(self, x, t): # forward 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) # 设定 grads = {} grads['W1'], grads['b1'] = self.layers['Affine1'].dW, self.layers['Affine1'].db grads['W2'], grads['b2'] = self.layers['Affine2'].dW, self.layers['Affine2'].db return grads