pytorch学习笔记-最大池化的使用
作者:互联网
作用:保留输入特征,同时减小数据量。
输入图像:
1 | 2 | 0 | 3 | 1 |
0 | 1 | 2 | 3 | 1 |
1 | 2 | 1 | 0 | 0 |
5 | 2 | 3 | 1 | 1 |
2 | 1 | 0 | 1 | 1 |
池化核:3*3,kernel_size=3
输出图像:ceil_mode=True
2 | 3 |
5 | 1 |
ceil_mode=False
2 |
输入:
from turtle import shape
import torch
from torch import nn
from torch.nn import MaxPool2d
input=torch.tensor([[1,2,0,3,1],
[0,1,2,3,1],
[1,2,1,0,0],
[5,2,3,1,1],
[2,1,0,1,1]],dtype=torch.float32)
input=torch.reshape(input,(-1,1,5,5))
print(input,shape)
class KELE(nn.Module):
def __init__(self):
super(KELE,self).__init__()
self.maxpool1=MaxPool2d(kernel_size=3,ceil_mode=True)
def forward (self,input):
output=self.maxpool1(input)
return output
kele=KELE()
output=kele(input)
print(output)
输出:
tensor([[[[1., 2., 0., 3., 1.],
[0., 1., 2., 3., 1.],
[1., 2., 1., 0., 0.],
[5., 2., 3., 1., 1.],
[2., 1., 0., 1., 1.]]]]) <function shape at 0x00000158F63DD0D0>
tensor([[[[2., 3.],
[5., 1.]]]])
标签:__,output,self,torch,笔记,pytorch,池化,import,input 来源: https://blog.csdn.net/weixin_43435855/article/details/122641679