import torch
from torch import nn
from d2l import torch as d2l
import os
os.environ["KMP_DUPLICATE_LIB_OK"] = "TRUE"
# 23 经典卷积神经网络 LeNet
net = nn.Sequential(
nn.Conv2d(1, 6, kernel_size=5, padding=2), nn.Sigmoid(),
nn.AvgPool2d(kernel_size=2, stride=2),
nn.Conv2d(6, 16, kernel_size=5), nn.Sigmoid(),
nn.AvgPool2d(kernel_size=2, stride=2),
nn.Flatten(), # 将特征图(二维数组)展平为一维数组,为全连接层做准备
nn.Linear(16 * 5 * 5, 120), nn.Sigmoid(), # 全连接层
nn.Linear(120, 84), nn.Sigmoid(),
nn.Linear(84, 10))
# 检查模型
X = torch.rand(size=(1, 1, 28, 28), dtype=torch.float32)
for layer in net:
X = layer(X)
print(layer.__class__.__name__, 'output shape:\t', X.shape)
# 模型训练
batch_size = 256
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size=batch_size)
def evaluate_accuracy_gpu(net, data_iter, device=None): # net(模型),data_iter(数据迭代器),以及可选参数 device(用于指定设备,如GPU)
"""使用GPU计算模型在数据集上的精度"""
if isinstance(net, nn.Module): # 检查传入的模型 net 是否为 nn.Module 的实例
net.eval() # 设置为评估模式
"""如果是,则将模型设置为评估模式,
这会关闭诸如dropout和batch normalization等模块的特定特性,
这些特性在训练阶段使用,但在评估阶段不需要。"""
if not device:
device = next(iter(net.parameters())).device # 获取模型参数中第一个元素的设备,以此作为默认的 device
# 正确预测的数量,总预测的数量
metric = d2l.Accumulator(2) # 用于累加正确预测的样本数量和总预测的样本数量
with torch.no_grad(): # torch.no_grad() 告诉PyTorch不计算梯度,这通常会在评估模式下使用,以减少计算量
for X, y in data_iter:
if isinstance(X, list):
# BERT微调所需的(之后将介绍)
X = [x.to(device) for x in X] # 如果X是一个List,则把每个元素都移到device上
else:
X = X.to(device) # 如果X是tensor,则只用移动一次,把X直接移到device上
y = y.to(device)
metric.add(d2l.accuracy(net(X), y), d2l.size(y))
return metric[0] / metric[1] # 最终返回正确预测数量除以总预测数量的比值,即准确度
# 训练函数
def train_ch6(net, train_iter, test_iter, num_epochs, lr, device):
"""用GPU训练模型"""
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)}')
# 训练和评估lenet模型
lr, num_epochs = 0.9, 10
d2l.train_ch6(net, train_iter, test_iter, num_epochs, lr, d2l.try_gpu())
d2l.plt.show() # 完全跑完后,可视化的图突然消失,加一句这个
23 经典卷积神经网络 LeNet(pycharm版)
最新推荐文章于 2024-05-01 12:41:56 发布