Convolution operation and Grouped Convolution

filter is not the kernel,but the kernels.that's mean a filter include one or two or more kernels.that's depend the input feature map and the output feature maps. for example, if we have an image, the shape of image is (32,32), has 3 channels,that's RGB.so the input feature maps is (1,3,32,32).the format of input feature maps is (batch_size,in_channels,H_in,W_in),the output feature maps is(batch_size,out_channels,H_out,W_out),there is a formulation for out_H,out_W.

p is padding,default is 0. s is stride,default is 1.

so, we get the the Height and Width of output feature map,but how about the output channels?how do we get the output channels from the input channels.Or,In other words,what's the convolution operation?

first,i'll give the conclusion and explain it later.

so the weight size is (filters, kernels of filter,H_k,W_k),the format of weight vector is (C_out,C_in,H_k,W_k)

that's mean we have C_out filters, and each filter has C_in kernels.if you don't understand, look through this link,it will tell you the specific operations.

as we go deeper into the convolution this dimension of channels increases very rapidly thus increases complexity. The spatial dimensions(means height and weight) have some degree of effect on the complexity but in deeper layers, they are not really the cause of concern. Thus in bigger neural networks, the filter groups will dominate.so,the grouped convolution was proposed,you can access to this link for more details.

you can try this code for validation.

python 复制代码
import torch.nn as nn
import torch

# 假设输入特征图的大小为 (batch_size, in_channels, H, W)
batch_size = 1
in_channels = 4
out_channels = 2
H = 6
W = 6

# 定义1x1卷积层,输入通道数为in_channels,输出通道数为out_channels
conv = nn.Conv2d(in_channels, out_channels, kernel_size=1, stride=1, padding=0)

# 对输入特征图进行1x1卷积操作
x = torch.randn(batch_size, in_channels, H, W)
y = conv(x)

# 输入特征图的大小为 (batch_size, in_channels, H, W)
print(x.shape)  # torch.Size([1, 4, 6, 6])
# 输出特征图的大小为 (batch_size, out_channels, H, W)
print(y.size())   # torch.Size([1, 2, 6, 6])
# 获取卷积核的尺寸 (out_channels, in_channels // groups, *kernel_size)
weight_size = conv.weight.size()
print('卷积核的尺寸为:', weight_size)  # torch.Size([2, 4, 1, 1])
相关推荐
电科_银尘1 天前
【深度学习项目实战·22】灰度图像着色:用小型U-Net学习从灰度到RGB
人工智能·深度学习·学习
猿人谷1 天前
遗传编程的未来:从进化搜索到自主发现求解方法
人工智能·深度学习·神经网络·ai-native
泓博1 天前
Android仿写苹果缩放窗口
人工智能·gpt·深度学习
在所不辞兄1 天前
【人工智能驱动的电催化研究-07】CSV文件、路径与可追溯记录
人工智能·深度学习·神经网络·机器学习·有限元·电化学·电催化
jay神1 天前
基于 YOLOv8 的传送带异物检测系统(Web 版)
前端·人工智能·深度学习·yolo·计算机视觉·计算机毕业设计
电科_银尘2 天前
【深度学习项目实战·33】自定义数据集:把自己的图片接入PyTorch
人工智能·pytorch·深度学习
武子康2 天前
单卡 A6000 跑 Qwen-Drive:怎样留下可比较的第一条基线?
linux·人工智能·深度学习
严肃小白兔2 天前
第 06/24 期:神经网络的反向传播算法:从链式法则到梯度计算
人工智能·神经网络·算法
在所不辞兄2 天前
为什么在新能源汽车电驱与热管理开发中,AI驱动的数字孪生和数据驱动仿真正在部分替代对物理台架与实车标定的依赖?
人工智能·深度学习·神经网络·算法·机器学习
伞伞悦读3 天前
【第83期】特征选择中的验证泄漏排查的实验与排查
人工智能·深度学习·机器学习