LeNet,它是最早发布的卷积神经网络之一,因其在计算机视觉任务中的高效性能而受到广泛关注。 这个模型是由AT&T贝尔实验室的研究员Yann LeCun在1989年提出的(并以其命名),目的是识别图像中的手写数字。
总体来看,LeNet由两个部分组成:
-
卷积编码器:由两个卷积层组成;
-
全连接层密集块:由三个全连接层组成。
使用pytorch框架实现此类模型非常简单,只需要用Sequential实例化一个块就行了。
import torch from torch import nn from d2l import torch as d2l 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(), nn.Linear(16 * 5 * 5, 120), nn.Sigmoid(), nn.Linear(120, 84), nn.Sigmoid(), nn.Linear(84, 10))
LeNet各层的形状如下图所示:
我们使用下面的代码逐一打印各层的输出的形状,以确保是否和我们预期的一致:
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)
输出:
下面在fashion_mnist数据集上面训练和评估LeNet,将计算放在GPU上。
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): #@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) 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] #@save 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())
这代码与之前的区别基本上就在于,将每一个小批量数据移动到了我们指定的设备(如GPU)上。
训练结果:
标签:nn,卷积,metric,iter,6.6,train,LeNet,device,net From: https://www.cnblogs.com/pkuqcy/p/17595672.html