AI测试之 TestGPT-CFANZ编程社区

文章目录

在这里插入图片描述

1.如何写一个神经网络进行训练?

1.1创建一个子类,搭建你需要的神经网络结构

# @File: 241008LeNet.py
# @Author: chen_song
# @Time: 2024/10/8 上午8:31

import torch
from torch import nn
from d2l import torch as d2l

net = nn.Sequential(
 # 进行卷积操作以后,
 nn.Conv2d(1,6,kernel_size=5,padding=2),nn.Sigmoid(),
 nn.AvgPool2d(2,stride=2),
 nn.Conv2d(6,16,kernel_size=5),nn.Sigmoid(),
 nn.AvgPool2d(2,stride=2),
 nn.Flatten(),
 nn.Linear(16*5*5,120),nn.Sigmoid(),
 nn.Linear(120,84),nn.Sigmoid(),
 nn.Linear(84,10)
)
print(net)
print("===============================")
X = torch.rand(size=(1,1,28,28),dtype=torch.float32)
Y  = X.copy_(X)
for layer in net:
 X = layer(X)
 print(layer.__class__.__name__,X.shape)

print("============================")
# 输入给定以后,会进行一系列张量乘法计算
A = net(Y)
# print the last result
print(A)

result below:

1.2 加载数据集

batch_size = 256
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)

打断点调试:
在这里插入图片描述
你会发现:
train_iter和test_iter都是一个torch.utils.dataLoader对象,里面包含几个成员变量,住关键的是dataset对象以及sample对象,仔细研究你就会发现,为啥需要数据加载器了,因为你用神经网络进行训练,数据格式总得对吧,再就是要给个label吧,也就是目标值target吧,所以有余力朋友可以自己设计一个数据加载器…

1.3 自定义一些指标评估函数

def evaluate_accuracy_gpu(net, data_iter, device=None):  # @save
 """使用GPU计算模型在数据集上的精度"""
 if isinstance(net, nn.Module):
  net.eval()  # 设置为评估模式
  if not device:
   device = next(iter(net.parameters())).device
 # 正确预测的数量，总预测的数量
 metric = d2l.Accumulator(2)
 with torch.no_grad():
  for X, y in data_iter:
   if isinstance(X, list):
    # BERT微调所需的（之后将介绍）=== 自然语言处理
    X = [x.to(device) for x in X]
   else:
    X = X.to(device)
   y = y.to(device)
   metric.add(d2l.accuracy(net(X), y), y.numel())
 return metric[0] / metric[1]

注意一下里面net.eval()和net.train()

1.4训练

def train_ch6(net, train_iter, test_iter, num_epochs, lr, device):
    """用GPU训练模型(在第六章定义)"""
    def init_weights(m):
        if type(m) == nn.Linear or type(m) == nn.Conv2d:
            nn.init.xavier_uniform_(m.weight)
    net.apply(init_weights)
    print('training on', device)
    net.to(device)
    optimizer = torch.optim.SGD(net.parameters(), lr=lr)
    loss = nn.CrossEntropyLoss()
    animator = d2l.Animator(xlabel='epoch', xlim=[1, num_epochs],
                            legend=['train loss', 'train acc', 'test acc'])
    timer, num_batches = d2l.Timer(), len(train_iter)
    for epoch in range(num_epochs):
        # 训练损失之和，训练准确率之和，样本数
        metric = d2l.Accumulator(3)
        net.train()
        for i, (X, y) in enumerate(train_iter):
            timer.start()
            optimizer.zero_grad()
            X, y = X.to(device), y.to(device)
            y_hat = net(X)
            l = loss(y_hat, y)
            l.backward()
            optimizer.step()
            with torch.no_grad():
                metric.add(l * X.shape[0], d2l.accuracy(y_hat, y), X.shape[0])
            timer.stop()
            train_l = metric[0] / metric[2]
            train_acc = metric[1] / metric[2]
            if (i + 1) % (num_batches // 5) == 0 or i == num_batches - 1:
                animator.add(epoch + (i + 1) / num_batches,
                             (train_l, train_acc, None))
        test_acc = evaluate_accuracy_gpu(net, test_iter)
        animator.add(epoch + 1, (None, None, test_acc))
    print(f'loss {train_l:.3f}, train acc {train_acc:.3f}, '
          f'test acc {test_acc:.3f}')
    print(f'{metric[2] * num_epochs / timer.sum():.1f} examples/sec '
          f'on {str(device)}')

lr, num_epochs = 0.9, 10
train_ch6(net, train_iter, test_iter, num_epochs, lr, d2l.try_gpu())
d2l.plt.show()