String1995
卒业写真
2021-03-01 00:35

神经网络反向传播法梯度错误和Loss上升问题

照着书打的代码。。。
一直不对。。还请大佬帮忙解惑


'''对应误差反向传播法的神经网络的实现'''
import numpy as np
from collections import OrderedDict
from dataset.mnist import load_mnist
import matplotlib.pyplot as plt

class SoftmaxWithLoss:
    def __init__(self):
        self.loss = None  # 损失
        self.y = None  # softmax的输出
        self.t = None  # 监督数据(one-hot vector)

    def softmax(self, x):
        x = x - np.max(x)
        exp_x = np.exp(x)
        softmax_x = exp_x / np.sum(exp_x)
        return softmax_x

    def cross_entropy_error(self, y, t):
        if y.ndim == 1:
            t = t.reshape(1, t.size)
            y = y.reshape(1, y.size)
        batch_size = y.shape[0]
        cee = -np.sum(t * np.log(y + 1e-7) / batch_size)

        return cee

    def forward(self, x, t):
        self.t = t
        self.y = self.softmax(x)
        self.loss = self.cross_entropy_error(self.y, self.t)

        return self.loss

    def backward(self, dout=1):
        batch_size = self.t.shape[0]
        dx = (self.y - self.t) / batch_size

        return dx


class Affine:
    """定义仿射层(矩阵乘积)"""

    def __init__(self, W, b):
        self.W = W
        self.b = b
        self.x = None
        self.dW = None
        self.db = None

    def forward(self, x):
        self.x = x
        out = np.dot(x, self.W) + self.b

        return out

    def backward(self, dout):
        dx = np.dot(dout, self.W.T)
        self.dW = np.dot(self.x.T, dout)
        self.db = np.sum(dout, axis=0)
        return dx

class Relu:
    def __init(self):
        self.mask = None

    def forward(self, x):
        self.mask = (x <= 0)
        out = x.copy()
        out[self.mask] = 0

        return out

    def backward(self, dout):
        dout[self.mask] = 0
        dx = dout

        return dx


class TwoLayerNet:
    def __init__(self, input_size, hidden_size, output_size, weight_init_std=0.01):
        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 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'] = self.layers['Affine1'].dW
        grads['b1'] = self.layers['Affine1'].db
        grads['W2'] = self.layers['Affine2'].dW
        grads['b2'] = self.layers['Affine2'].db

        return grads


(x_train, t_train), (x_test, t_test) = load_mnist(normalize=True, one_hot_label=True)

network = TwoLayerNet(input_size=784, hidden_size=50, output_size=10)

iters_num = 10000
train_size = x_train.shape[0]
batch_size = 100
learning_rate = 0.1

train_loss_list = []
train_acc_list = []
test_acc_list = []

iter_per_epoch = max(train_size / batch_size, 1)

for i in range(iters_num):
    batch_mask = np.random.choice(train_size, batch_size)
    x_batch = x_train[batch_mask]
    t_batch = t_train[batch_mask]

    # 通过误差反向传播求梯度
    grad = network.gradient(x_batch, t_batch)

    # 更新
    for key in ('W1', 'b1', 'W2', 'b2'):
        network.params[key] -=  learning_rate * grad[key]

    loss = network.loss(x_batch, t_batch)
    train_loss_list.append(loss)


    if i % iter_per_epoch == 0:
        train_acc = network.accuracy(x_train, t_train)
        test_acc = network.accuracy(x_test, t_test)
        train_acc_list.append(train_acc)
        test_acc_list.append(test_acc)
        print(train_acc, test_acc)

plt.plot(train_loss_list)
plt.show()
  • 点赞
  • 写回答
  • 关注问题
  • 收藏
  • 复制链接分享
  • 邀请回答