Pytorch建立神经网络

卷积前后的大小变化可由以下公式得到：

$I n p u t : (N, C_{i n}, H_{i n}, W_{i n}) o r (C_{i n}, H_{i n}, W_{i n})$ $O u t p u t : (N, C_{out}, H_{out}, W_{out}) o r (C_{out}, H_{out}, W_{out})$ $H_{out} = [\frac{H_{in} + 2 \times padding [0] - dliation [0] \times (kernel\_size [0] - 1) - 1}{stride[0]} + 1]$ $W_{out} = [\frac{W_{in} + 2 \times padding [1] - dliation [0] \times (kernel\_size [1] - 1) - 1}{stride[1]} + 1]$

CATALOG

FEATURED TAGS

FRIENDS