带权重的pytorch conv2d

Question

我有这两个变量：

result- tensor 1 X 251 X 20
kernel - tensor 1 X 10 X 10

当我运行命令时：

from torch.nn import functional as F
result = F.conv2d(result, kernel)

我收到错误：

RuntimeError: expected stride to be a single integer value or a list of 1 values to match the convolution dimensions, but got stride=[1, 1]

我没有任何进步，我做错了什么？

Answer 1

import torch
import torch.nn.functional as F
image = torch.rand(16, 3, 32, 32)
filter = torch.rand(1, 3, 5, 5)
out_feat_F = F.conv2d(image, filter,stride=1, padding=0)
print(out_feat_F.shape)

输出：

torch.Size([16, 1, 28, 28])

相当于：

import torch
import torch.nn
image = torch.rand(16, 3, 32, 32)
conv_filter = torch.nn.Conv2d(in_channels=3, out_channels=1, kernel_size=5, stride=1, padding=0)
output_feature = conv_filter(image)
print(output_feature.shape)

输出：

torch.Size([16, 1, 28, 28])

Padding默认为0，stride默认为1。第一个示例中的过滤器最后两个维度对应于第二个例子中的内核大小。

kernel_size=5 等同于 kernel_size=(5,5).

带权重的pytorch conv2d

pytorch conv2d with weights

convolution

conv-neural-network

pytorch