torch.nn.Conv3d(in_channels, out_channels, kernel_size, stride=1, padding=0, dilation=1, groups=1, bias=True)
Parameters:
- in_channels(int) – 输入信号的通道
- out_channels(int) – 卷积产生的通道
- kernel_size(int or tuple) - 卷积核的尺寸
- stride(int or tuple, optional) - 卷积步长
- padding(int or tuple, optional) - 输入的每一条边补充0的层数
- dilation(int or tuple, optional) – 卷积核元素之间的间距
- groups(int, optional) – 从输入通道到输出通道的阻塞连接数
- bias(bool, optional) - 如果bias=True,添加偏置
三维卷积层, 输入的尺度是(N, C_in,D,H,W),输出尺度(N,C_out,D_out,H_out,W_out)
下面是自己瞎举了个例子,参考:
def __init__(self):
self.conv3d_1 = nn.Conv3d(2048,1024,3,padding=1)
def forward(self,x):
n, c, t, h, w = x.size() # t是帧数,n是batchsize, c是channel, h是高度, w是宽度
x = self.conv3d_1(x)
原链接 http://t.zoukankan.com/luckyplj-p-13467823.html (纯属学习用)