问题:如何经过convTransposed1d输出指定大小的特征?
代码语言:javascript复制import torch
from torch import nn
import torch.nn.functional as F
conv1 = nn.Conv1d(1, 2, 3, padding=1)
conv2 = nn.Conv1d(in_channels=2, out_channels=4, kernel_size=3, padding=1)
#转置卷积
dconv1 = nn.ConvTranspose1d(4, 1, kernel_size=3, stride=2, padding=1, output_padding=1)
x = torch.randn(16, 1, 8)
print(x.size())
x1 = conv1(x)
x2 = conv2(x1)
print(x2.size())
x3 = dconv1(x2)
print(x3.size())
'''
torch.Size([16, 1, 8])
torch.Size([16, 4, 8]) #conv2输出特征图大小
torch.Size([16, 1, 16]) #转置卷积输出特征图大小
'''
代码语言:javascript复制#转置卷积
dconv1 = nn.ConvTranspose1d(1, 1, kernel_size=3, stride=3, padding=1, output_padding=1)
x = torch.randn(16, 1, 8)
print(x.size()) #torch.Size([16, 1, 23])
x3 = dconv1(x)
print(x3.size()) #torch.Size([16, 1, 23])
下面两图为演示conv1d,在padding和不padding下的输出特征图大小
不带padding
带padding
补充知识:判断pytorch是否支持GPU加速
如下所示:
print torch.cuda.is_available()
以上这篇pytorch 计算ConvTranspose1d输出特征大小方式就是小编分享给大家的全部内容了,希望能给大家一个参考。