torch.nn.functional.conv2d中bias

InternetFake

于 2024-07-19 14:41:44 发布

阅读量245

点赞数 5

文章标签：深度学习人工智能机器学习 pytorch

本文链接：https://blog.csdn.net/qq_54871862/article/details/140548774

版权

bias为维度为卷积核个数的tensor

若设置了bias值，则每计算完一次卷积操作后，加上bias值

示例代码：

不使用bias：

import torch
import torch.nn.functional as F

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]])

kernel = torch.tensor([[1, 2, 1],
                       [0, 1, 0],
                       [2, 1, 0]])

input = torch.reshape(input, (1, 1, 5, 5))
kernel = torch.reshape(kernel, (1, 1, 3, 3))

output = F.conv2d(input, kernel, stride=1)
print(output)

#输出结果：
tensor([[[[10, 12, 12],
          [18, 16, 16],
          [13,  9,  3]]]])

使用bias：

# 开发时间：2024/7/19 14:27
import torch
import torch.nn.functional as F

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]])

kernel = torch.tensor([[1, 2, 1],
                       [0, 1, 0],
                       [2, 1, 0]])

input = torch.reshape(input, (1, 1, 5, 5))
kernel = torch.reshape(kernel, (1, 1, 3, 3))

bias = torch.tensor([1])
output = F.conv2d(input, kernel, bias=bias, stride=1)
print(output)

#输出结果
tensor([[[[11, 13, 13],
          [19, 17, 17],
          [14, 10,  4]]]])