计算机视觉知识点-基础网络-LeNet

LeNet是基础网络中的基础网络。

LeNet有两个卷积层，作为特征提取器，3个FC层，作为非线性分类器， LeNet跟近代的网络的区别是1)pooling使用avepool， 近代网络，比如alexnet使用maxpool, 2)激活函数Lenet使用的是sigmoid， alexnet使用的是relu. 

使用mxnet进行一下代码演示。mxnet的安装方法

pip install d2l==0.14.3
pip install -U mxnet-cu101mkl==1.6.0.post0  
pip install gluoncv

创建一个lenet网络

from d2l import mxnet as d2l
from mxnet import autograd, gluon, init, np, npx
from mxnet.gluon import nn
npx.set_np()

net = nn.Sequential()
net.add(nn.Conv2D(channels=6, kernel_size=5, padding=2, activation='sigmoid'),
        nn.AvgPool2D(pool_size=2, strides=2),
        nn.Conv2D(channels=16, kernel_size=5, activation='sigmoid'),
        nn.AvgPool2D(pool_size=2, strides=2),
        # `Dense` will transform an input of the shape (batch size, number of
        # channels, height, width) into an input of the shape (batch size,
        # number of channels * height * width) automatically by default
        nn.Dense(120, activation='sigmoid'),
        nn.Dense(84, activation='sigmoid'),
        nn.Dense(10))

网络的输入尺寸是28*28.

打印一下输出

X = np.random.uniform(size=(1, 1, 28, 28))
net.initialize()
for layer in net:
    X = layer(X)
    print(layer.name, 'output shape:\t', X.shape)

conv0 output shape:  (1, 6, 28, 28)
pool0 output shape:  (1, 6, 14, 14)
conv1 output shape:  (1, 16, 10, 10)
pool1 output shape:  (1, 16, 5, 5)
dense0 output shape:         (1, 120)
dense1 output shape:         (1, 84)
dense2 output shape:         (1, 10)

加载fashion_mnist训练数据

batch_size=128
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size, resize=224)

训练代码

def evaluate_accuracy_gpu(net, data_iter, device=None):  #@save
    """Compute the accuracy for a model on a dataset using a GPU."""
    if not device:  # Query the first device where the first parameter is on
        device = list(net.collect_params().values())[0].list_ctx()[0]
    # No. of correct predictions, no. of predictions
    metric = d2l.Accumulator(2)
    for X, y in data_iter:
        X, y = X.as_in_ctx(device), y.as_in_ctx(device)
        metric.add(d2l.accuracy(net(X), y), y.size)
    return metric[0]/metric[1]

#@save
def train_ch6(net, train_iter, test_iter, num_epochs, lr,
              device=d2l.try_gpu()):
    """Train a model with a GPU (defined in Chapter 6)."""
    net.initialize(force_reinit=True, ctx=device, init=init.Xavier())
    loss = gluon.loss.SoftmaxCrossEntropyLoss()
    trainer = gluon.Trainer(net.collect_params(),
                            'sgd', {'learning_rate': lr})
    animator = d2l.Animator(xlabel='epoch', xlim=[0, num_epochs],
                            legend=['train loss', 'train acc', 'test acc'])
    timer = d2l.Timer()
    for epoch in range(num_epochs):
        # Sum of training loss, sum of training accuracy, no. of examples
        metric = d2l.Accumulator(3)
        for i, (X, y) in enumerate(train_iter):
            timer.start()
            # Here is the major difference compared with `d2l.train_epoch_ch3`
            X, y = X.as_in_ctx(device), y.as_in_ctx(device)
            with autograd.record():
                y_hat = net(X)
                l = loss(y_hat, y)
            l.backward()
            trainer.step(X.shape[0])
            metric.add(l.sum(), d2l.accuracy(y_hat, y), X.shape[0])
            timer.stop()
            train_loss = metric[0] / metric[2]
            train_acc = metric[1] / metric[2]
            if (i + 1) % 50 == 0:
                animator.add(epoch + i / len(train_iter),
                             (train_loss, train_acc, None))
        test_acc = evaluate_accuracy_gpu(net, test_iter)
        animator.add(epoch + 1, (None, None, test_acc))
    print(f'loss {train_loss:.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)

在T4下训练大概2分钟就可以完成了

训练结果

loss 0.471, train acc 0.822, test acc 0.824
49576.0 examples/sec on gpu(0)

训练使用 Xavier进行网络初始化，loss为 cross-entropy，使用sgd进行优化。

最后的话:

这篇文章发布在CSDN/蓝色的杯子, 没事多留言,让我们一起爱智求真吧.我的邮箱wisdomfriend@126.com