pytorch conv2d卷积核尺寸

Lecture_10 卷积神经网络 Convolutional Neural Network

一、重点回顾——卷积神经网络的结构

（一） 卷积层：特征提取

1. 卷积核尺寸的确定

（1） 单输入通道

滤波器filter/卷积核kernel在输入图像上滑动，遍历，并做数乘运算（对应元素相乘）再相加【即互相关运算】得到输出。

（2）3输入通道

（3）N输入通道

输出通道的高和宽 = 输入通道的高和宽 - 卷积核的高和宽 + 1

卷积核通道数 = 输入通道数

输出通道数 = 卷积核的数量

（4） N输入通道M输出通道

个人理解：输入图像的每一个通道与一个卷积核的每一个通道做卷积运算，n个卷积运算结果相加，得到一个特征提取图，即输出图像的一个通道。每个卷积核进行n次卷积运算。

m个n通道的卷积核，卷积核大小为输出图像的宽高-输入图像宽高+1

2. 零填充和步长 Padding and Stride

Padding 在输入图像四周补零

输出通道的宽高=输入通道宽高-卷积核宽高+1Stride 卷积核每次移动的间隔

（二）池化层：减少数据量，降低运算需求

1. 最大池化

找最大的元素，默认步长为2

（三）全连接层：分类，输出结果

二、代码复现

一个简单的卷积神经网络：

# 卷积层的输入输出
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)

# 卷积运算结果输出
input2 = [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]
input2 = torch.Tensor(input2).view(1, 1, 5, 5)
conv_layer2 = 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_layer2.weight.data = kernel.data
output2 = conv_layer2(input2)
print(output2)

# 最大池化
input3 = [3,4,6,5, 2,4,6,8, 1,6,7,8, 9,7,4,6, ]
input3 = torch.Tensor(input3).view(1, 1, 4, 4)
maxpooling_layer = torch.nn.MaxPool2d(kernel_size=2)
output3 = maxpooling_layer(input3)
print(output3)

# Move Module to GPU
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
# Move Tensors to GPU
	# Send the inputs and targets at every step to the GPU.（写在train和test的循环体里）
	inputs, target = data
	inputs, target = inputs.to(device),target.to(device)

全部代码：

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

# Prepare Dataset
batch_size = 64
transform = transforms.Compose([
	transforms.ToTensor(), # Convert the PIL Image to Tensor
	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):
	"""docstring for Net"""
	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):
		# Flatten data from (n,1,28,28) to (n,784)
		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) # Flatten
		x = self.fc(x)
		return x

model = Net()

# Move Module to GPU
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
print(device)
model = model.to(device)


# Construct Loss and Optimizer
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):
		# Move Tensors to GPU
		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/2000))
			running_loss = 0.0

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

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