dilation

最近在学习Paddle，使用过程中有了些许的理解，所以把这部分内容记录下来，分享给大家，如果有问题也可以留言一起探讨~进入正文部分，Paddle下Conv2d这个API的使用说明，首先来看一下Conv2d的声明部分：paddle.fluid.dygraph.Conv2D(num_channels, num_filters, filter_size, \stride=1, padding=0, dilation=1, groups=None, param_attr=None, \bias_att

带dilation的卷积输出尺寸计算公式K′=dilation+(kernel−1)⋅(dilation−1)K'=dilation+(kernel-1)\cdot(dilation-1)K′=dilation+(kernel−1)⋅(dilation−1)Wout=win−K′+2paddingstride+1W_{out}=\frac{w_{in}-K'+2padding}{stride}+1Wout​=stridewin​−K′+2padding​+1举例# -*- coding: utf-8

torch.nn.Conv2d def __init__(self, in_channels, out_channels, kernel_size, stride=1, padding=0, dilation=1, groups=1, bias=True, padding_mode='zeros'):Parametersin_channels (int) – Number of channels in the input i