pytorch-CNN、BatchNorm、残差网络

import torch
from torch.nn import functional as F #导入函数
from torch import nn #神经网络

layer = nn.Conv2d(1, 3, kernel_size=3, stride=1, padding=0)
layer

x = torch.rand(1, 1, 28, 28)
x

out = layer.forward(x)
print("stride=1,padding=0:out.shape = ",out.shape)
layer = nn.Conv2d(1, 3, kernel_size=3, stride=1,padding=1)
out = layer.forward(x)
print("stride=1,padding=1:out.shape = ",out.shape)
layer = nn.Conv2d(1, 3, kernel_size=3, stride=2,padding=1)
out = layer.forward(x)
print("stride=2,padding=1:out.shape = ",out.shape)
print("-----Inner weight $ bias -----")
print("layer.weight = \n", layer.weight)
print("layer.weight.shape=",layer.weight.shape)
print("layer.bias.shape=",layer.bias.shape)

print("-----F.conv2d-----")
w = torch.rand(16, 3, 5, 5)
b = torch.rand(16)
x = torch.randn(1, 3, 28, 28)
out = F.conv2d(x, w, b, stride=1, padding=1 )
print("F.conv2d, stride=1, padding=1: out.shape =",out.shape)
out = F.conv2d(x, w, b, stride=2, padding=1 )
print("F.conv2d, stride=2, padding=1: out.shape =",out.shape)

总结

这个展示的部分主要是想表达stride与padding的用法以及之后产生了什么效果，cnn本身可解释性就不好，通过展示出来的shape从而知道发生了什么。

BatchNorm

Batch Normalization(简称BN)中的batch就是批量数据，即每一次优化时的样本数目，通常BN网络层用在卷积层后，用于重新调整数据分布。假设神经网络某层一个batch的输入为X=[x1,x2,…,xn]，其中xi代表一个样本，n为batch size。

我们能看到BatchNorm1d的最基本属性。

同时我们也看得到layer的中位数与平均值的初始值都是一样的

但是经历了100轮的迭代后，中位数跟平均值发生了变化

残差网络

import torch
from torch.nn import functional as F
from torch.utils.data import DataLoader
from torchvision import datasets
from torchvision import transforms
from torch import nn, optim

#from torchvision.models import vgg13_bn

class ResBlk(nn.Module):
    """
    resnet block
    """
    def __init__(self, ch_in, ch_out):
        super(ResBlk, self).__init__()

        self.conv1 = nn.Conv2d(ch_in, ch_out, kernel_size=3, stride=1, padding=1)
        self.bn1 = nn.BatchNorm2d(ch_out)
        self.conv2 = nn.Conv2d(ch_out, ch_out, kernel_size=3, stride=1, padding=1)
        self.bn2 = nn.BatchNorm2d(ch_out)

        self.extra = nn.Sequential()
        if ch_out != ch_in:
            # [b, ch_in, h, w] => [b, ch_out, h, w]
            self.extra = nn.Sequential(
                nn.Conv2d(ch_in, ch_out, kernel_size=1, stride=1),
                nn.BatchNorm2d(ch_out)
            )

    def forward(self, x):
        """
        :param x: [b, ch, h, w]
        :return:
        """
        out = F.relu(self.bn1(self.conv1(x)))
        out = self.bn2(self.conv2(out))
        # short cut.
        # extra module: [b, ch_in, h, w] => [b, ch_out, h, w]
        # element-wise add:
        out = self.extra(x) + out

        return out


class ResNet18(nn.Module):
    def __init__(self):
        super(ResNet18, self).__init__()

        self.conv1 = nn.Sequential(
            nn.Conv2d(3, 16, kernel_size=3, stride=1, padding=1),
            nn.BatchNorm2d(16)
        )
        # followed 4 blocks
        # [b, 64, h, w] => [b, 128, h ,w]
        self.blk1 = ResBlk(16, 16)
        # [b, 128, h, w] => [b, 256, h, w]
        self.blk2 = ResBlk(16, 32)
        # # [b, 256, h, w] => [b, 512, h, w]
        # self.blk3 = ResBlk(128, 256)
        # # [b, 512, h, w] => [b, 1024, h, w]
        # self.blk4 = ResBlk(256, 512)
        self.outlayer = nn.Linear(32 * 32 * 32, 10)

    def forward(self, x):
        x = F.relu(self.conv1(x))

        # [b, 64, h, w] => [b, 1024, h, w]
        x = self.blk1(x)
        x = self.blk2(x)
        # x = self.blk3(x)
        # x = self.blk4(x)

        # print(x.shape)
        x = x.view(x.size(0), -1)
        x = self.outlayer(x)

        return x


def main():
    batchsz = 32

    cifar_test, cifar_train = load_data(batchsz)

    x, label = iter(cifar_train).next()
    print('x:', x.shape, 'label:', label.shape)

    device = torch.device('cuda')
    # model = Lenet5().to(device)
    model = ResNet18().to(device)

    criteon = nn.CrossEntropyLoss().to(device)
    optimizer = optim.Adam(model.parameters(), lr=1e-3)
    print(model)

    for epoch in range(1000):

        model.train()
        for batchidx, (x, label) in enumerate(cifar_train):
            # [b, 3, 32, 32]
            # [b]
            x, label = x.to(device), label.to(device)

            logits = model(x)
            # logits: [b, 10]
            # label:  [b]
            # loss: tensor scalar
            loss = criteon(logits, label)

            # backprop
            optimizer.zero_grad()
            loss.backward()
            optimizer.step()

        print(epoch, 'loss:', loss.item())

        model.eval()
        with torch.no_grad():
            # test
            total_correct = 0
            total_num = 0
            for x, label in cifar_test:
                # [b, 3, 32, 32]
                # [b]
                x, label = x.to(device), label.to(device)

                # [b, 10]
                logits = model(x)
                # [b]
                pred = logits.argmax(dim=1)
                # [b] vs [b] => scalar tensor
                correct = torch.eq(pred, label).float().sum().item()
                total_correct += correct
                total_num += x.size(0)
                # print(correct)

            acc = total_correct / total_num
            print(epoch, 'acc:', acc)


def load_data(batchsz):
    cifar_train = datasets.CIFAR10('../data/cifar', True, transform=transforms.Compose([
        transforms.Resize((32, 32)),
        transforms.ToTensor()
    ]), download=True)
    cifar_train = DataLoader(cifar_train, batch_size=batchsz, shuffle=True)
    cifar_test = datasets.CIFAR10('../data/cifar', False, transform=transforms.Compose([
        transforms.Resize((32, 32)),
        transforms.ToTensor()
    ]), download=True)
    cifar_test = DataLoader(cifar_test, batch_size=batchsz, shuffle=True)
    return cifar_test, cifar_train


if __name__ == '__main__':
    main()