动手从零实现一个多层感知机（前馈神经网络）
1.首先需要一个数据迭代器用来制造网络的输入部分
import random
import torchtorch.manual_seed(42) # 设置随机数种子# 生成输入输出值X,Y
def synthetic_data(w, b, num_examples): # @saveX, Y = [], []for i in range(num_examples):x = torch.normal(0, 1, (1, len(w)))y = torch.matmul(x, w) + bif (y > torch.tensor([0])) == torch.tensor([True]):y = torch.tensor([1, 0])else:y = torch.tensor([0, 1])# y += torch.normal(0, 0.01, y.shape)x = x.tolist()y = y.tolist()X.append(x[0])Y.append(y)return torch.tensor(X), torch.tensor(Y)true_w = torch.tensor([2, -3.4, 5])
true_b = 4.2features, labels = synthetic_data(true_w, true_b, 1000)
test_features, test_labels = synthetic_data(true_w, true_b, 100)# 数据迭代器
def data_iter(batch_size, features, labels):num_examples = len(features)indices = list(range(num_examples))# 这些样本是随机读取的，没有特定的顺序random.shuffle(indices)for i in range(0, num_examples, batch_size):batch_indices = torch.tensor(indices[i: min(i + batch_size, num_examples)])yield features[batch_indices], labels[batch_indices]2. 设置一个网络结构，具体是一个有3维输入层，4，5，4维的隐藏层，2维的输出层，代码如下
class FNN:"""前馈神经网络"""def __init__(self, input_odes, hidden_nodes, output_nodes, lr):self.inodes = input_odes # 第一层节点数量，即输入层节点数量self.hnodes1, self.hnodes2, self.hnodes3 = hidden_nodes # 隐藏层节点数量self.onodes = output_nodes # 输出层节点数量self.wih = torch.normal(0.0, 1, (self.hnodes1, self.inodes)) # 输入层到隐藏层矩阵self.whh1 = torch.normal(0.0, 1, (self.hnodes2, self.hnodes1)) # 隐藏层到隐藏层矩阵self.whh2 = torch.normal(0.0, 1, (self.hnodes3, self.hnodes2))self.who = torch.normal(0.0, 1, (self.onodes, self.hnodes3)) # 隐藏层到输出层矩阵# print("self.wih.shape", self.wih.shape)# print("self.whh1.shape", self.whh1.shape)# print("self.whh2.shape", self.whh2.shape)# print("self.who.shape", self.who.shape)self.lr = lr # 学习率self.activation = lambda x: torch.relu(x) # 激活函数def ff_bp(self, inputs, targets):"""实现前馈和反向传播算法"""inputs = inputs.T # 输入转置targets = targets.T # gold标签转置# 以下是神经网络的前馈计算过程hidden1 = torch.matmul(self.wih, inputs)hidden1_output = self.activation(hidden1)hidden2 = torch.matmul(self.whh1, hidden1_output)hidden2_output = self.activation(hidden2)hidden3 = torch.matmul(self.whh2, hidden2_output)hidden3_output = self.activation(hidden3)final = torch.matmul(self.who, hidden3_output)final_output = self.activation(final)# 反向传播算法部分# 计算误差output_error = targets - final_outputhidden3_error = torch.matmul(self.who.T, output_error)hidden2_error = torch.matmul(self.whh2.T, hidden3_error)hidden1_error = torch.matmul(self.whh1.T, hidden2_error)# 根据学习率进行误差回传self.who += self.lr * torch.matmul((output_error * final_output * (1.0 - final_output)), hidden3_output.T)self.whh2 += self.lr * torch.matmul((hidden3_error * hidden3_output * (1.0 - hidden3_output)), hidden2_output.T)self.whh1 += self.lr * torch.matmul((hidden2_error * hidden2_output * (1.0 - hidden2_output)), hidden1_output.T)self.wih += self.lr * torch.matmul((hidden1_error * hidden1_output * (1.0 - hidden1_output)), inputs.T)def query(self, inputs):# 用于测试，相当于model.eval()模式inputs = inputs.Thidden1 = torch.matmul(self.wih, inputs)hidden1_output = self.activation(hidden1)hidden2 = torch.matmul(self.whh1, hidden1_output)hidden2_output = self.activation(hidden2)hidden3 = torch.matmul(self.whh2, hidden2_output)hidden3_output = self.activation(hidden3)final = torch.matmul(self.who, hidden3_output)final_output = self.activation(final)return final_output3. 具体实现
# 网络的实例化
nn = FNN(3, (4, 5, 4), 2, 0.001)
epochs = 15 # 迭代次数
# 进行训练
for epoch in range(epochs):for x, y in data_iter(1, features, labels):nn.ff_bp(x, y)result = [] # 输出的结果表
# 进行查询和最后的结果转换
for x, y in data_iter(1, test_features, test_labels):label = nn.query(x)pos = torch.argmax(label)# print(y.shape)if pos == 0:label = torch.tensor([[1, 0]])else:label = torch.tensor([[0, 1]])# print(label, y)if torch.equal(label, y):result.append(1)else:result.append(0)total = 0for ele in range(0, len(result)):total = total + result[ele]
print("正确率为：{:.2f}".format(total / len(result)))本文来自互联网用户投稿，文章观点仅代表作者本人，不代表本站立场，不承担相关法律责任。如若转载，请注明出处。 如若内容造成侵权/违法违规/事实不符，请点击【内容举报】进行投诉反馈！