PyTorch学习记录（八）卷积神经网络（基础篇）

第一次接触pytorch，本贴仅记录学习过程，侵删

在B站看完了视频的P10 10.卷积神经网络（基础篇）。
附上视频地址：《PyTorch深度学习实践》完结合集_10. 卷积神经网络（基础篇）

1、每一个卷积核的通道数量n，要求和输入通道是一样的；
2、这种卷积核的个数m与输出通道的数量是一致的；
3、卷积核大小kernel_size(width)×kernel_size(height)可自行决定（与图像大小无关）。

用pytorch来实现，举例：

import torch

in_channels, out_channels = 5, 10
width, height = 100, 100
kernel_size = 3
batch_size = 1

input = torch.randn(batch_size,
                    in_channels,
                    width,
                    height)

conv_layer = torch.nn.Conv2d(in_channels,
                             out_channels,
                             kernel_size=kernel_size)

output = conv_layer(input)

print(input.shape)
print(output.shape)
print(conv_layer.weight.shape)

在这里，输入维度为1×5×100×100，卷积核是10×5×3×3，输出维度为1×10×98×98

介绍几个卷积层中常见的参数、操作：

1、padding

当我们需要输入大小和输出大小一样时，我们可以使用padding来进行填充。

例：padding=1

对于这个input来说，如果要和3×3的卷积核做卷积，只需要padding=1就足够了（即3/2=1）；若是要和5×5的卷积核做卷积，则需要padding=2（即5/2=2）。

例：padding=2

将padding=1的例子来实践一下：

import torch

input = [3, 4, 6, 5, 7,
         2, 4, 6, 8, 2,
         1, 6, 7, 8, 4,
         9, 7, 4, 6, 2,
         3, 7, 5, 4, 1]
input = torch.Tensor(input).view(1, 1, 5, 5)
# 参数分别为(batch_size, C, W, H)

conv_layer = torch.nn.Conv2d(1, 1, kernel_size=3, padding=1, bias=False)
# 1, 1分别为输入通道数和输出通道数

kernel = torch.Tensor([1, 2, 3, 4, 5, 6, 7, 8, 9]).view(1, 1, 3, 3)
# view的参数分别为(输入通道数, 输出通道数, W, H)
conv_layer.weight.data = kernel.data

output = conv_layer(input)
print(output)

2、stride(步长)

stride=2举例：

import torch

input = [3, 4, 6, 5, 7,
         2, 4, 6, 8, 2,
         1, 6, 7, 8, 4,
         9, 7, 4, 6, 2,
         3, 7, 5, 4, 1]
input = torch.Tensor(input).view(1, 1, 5, 5)

conv_layer = torch.nn.Conv2d(1, 1, kernel_size=3, stride=2, bias=False)

kernel = torch.Tensor([1, 2, 3, 4, 5, 6, 7, 8, 9]).view(1, 1, 3, 3)
conv_layer.weight.data = kernel.data

output = conv_layer(input)
print(output)

3、Downsampling（下采样）

用的较多的一种下采样为Max Pooling Layer（最大池化层）

Max Pooling Layer是没有权重的

例如：2×2的MaxPooling，默认的步长stride=2

将其分为2×2一组，在每一组里找最大值，再将最大值拼成2×2的新输出

实现：

import torch

input = [3, 4, 6, 5,
         2, 4, 6, 8,
         1, 6, 7, 8,
         9, 7, 4, 6]
input = torch.Tensor(input).view(1, 1, 4, 4)

maxpooling_layer = torch.nn.MaxPool2d(kernel_size=2)

output = maxpooling_layer(input)
print(output)

用一个简单的卷积神经网络来实现MNIST：

在构造神经网络时，我们必须要保证每一层的数据维度能够对上。但在卷积层和池化层不在乎输入的大小，而最后的分类器比较在意输入大小。所以我们需要算出在使用了这些卷积结构之后，到分类器时，对于每一个样本来说，它的元素一共有多少个。

因为我们需要做交叉熵损失，所以最后一层不用激活。

代码实现：

class Net(torch.nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = torch.nn.Conv2d(1, 10, kernel_size=5)
        self.conv2 = torch.nn.Conv2d(10, 20, kernel_size=5)
        self.pooling = torch.nn.MaxPool2d(2)
        self.fc = torch.nn.Linear(320, 10)

    def forward(self, x):
        batch_size = x.size(0)
        x = F.relu(self.pooling(self.conv1(x)))
        x = F.relu(self.pooling(self.conv2(x)))
        x = x.view(batch_size, -1)
        x = self.fc(x)
        return x


model = Net()

如何使用显卡GPU来计算？

1、Move Model to GPU

（1）Define device as the first visible cuda device if we have CUDA available

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

（2）Convert parameters and buffers of all modules to CUDA Tensor.

model.to(device)

即：

class Net(torch.nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = torch.nn.Conv2d(1, 10, kernel_size=5)
        self.conv2 = torch.nn.Conv2d(10, 20, kernel_size=5)
        self.pooling = torch.nn.MaxPool2d(2)
        self.fc = torch.nn.Linear(320, 10)

    def forward(self, x):
        batch_size = x.size(0)
        x = F.relu(self.pooling(self.conv1(x)))
        x = F.relu(self.pooling(self.conv2(x)))
        x = x.view(batch_size, -1)
        x = self.fc(x)
        return x


model = Net()
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
model.to(device)

2、Move Tensors to GPU

Send the inputs and targets at every step to the GPU.

(1)在train()中：

inputs, target = inputs.to(device), target.to(device)

(2)在test()中：

inputs, target = inputs.to(device), target.to(device)

最后，贴出使用这节课所学的知识实现的MNIST：

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

batch_size = 64
transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.1307,), (0.3081,))
])

train_dataset = datasets.MNIST(root='../dataset/mnist/',
                               train=True,
                               download=True,
                               transform=transform)
train_loader = DataLoader(train_dataset,
                          shuffle=True,
                          batch_size=batch_size)
test_dataset = datasets.MNIST(root='../dataset/mnist/',
                              train=False,
                              download=True,
                              transform=transform)
test_loader = DataLoader(train_dataset,
                         shuffle=False,
                         batch_size=batch_size)


class Net(torch.nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = torch.nn.Conv2d(1, 10, kernel_size=5)
        self.conv2 = torch.nn.Conv2d(10, 20, kernel_size=5)
        self.pooling = torch.nn.MaxPool2d(2)
        self.fc = torch.nn.Linear(320, 10)

    def forward(self, x):
        batch_size = x.size(0)
        x = F.relu(self.pooling(self.conv1(x)))
        x = F.relu(self.pooling(self.conv2(x)))
        x = x.view(batch_size, -1)
        x = self.fc(x)
        return x


model = Net()
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
model.to(device)

criterion = torch.nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)


def train(epoch):
    running_loss = 0.0
    for batch_idx, data in enumerate(train_loader, 0):
        inputs, target = data
        inputs, target = inputs.to(device), target.to(device)
        optimizer.zero_grad()

        outputs = model(inputs)
        loss = criterion(outputs, target)
        loss.backward()
        optimizer.step()

        running_loss += loss.item()
        if batch_idx % 300 == 299:
            print('[%d, %5d] loss:%.3f' % (epoch + 1, batch_idx + 1, running_loss / 300))
            running_loss = 0.0


def test():
    correct = 0
    total = 0
    with torch.no_grad():
        for data in test_loader:
            images, labels = data
            images, labels = images.to(device), labels.to(device)
            outputs = model(images)
            _, predicted = torch.max(outputs.data, dim=1)
            total += labels.size(0)
            correct += (predicted == labels).sum().item()
    print('Accuracy on test set:%d %%' % (100 * correct / total))


if __name__ == '__main__':
    for epoch in range(10):
        train(epoch)
        test()

作业：