Tensorflow中Conv2D和Conv2DTranspose前后尺寸的变化

Conv2D:

参数为 p a d d i n g = v a l i d padding='valid' 时,
o u t p u t = i n p u t k e r n e l _ s i z e / 2 + 1 output=\lfloor input-kernel\_size \rfloor/2+1
参数为 p a d d i n g = s a m e padding='same' 时,
o u t p u t _ s i z e = i n p u t _ s i z e output\_size=input\_size

Conv2DTranspose:

参数为 p a d d i n g = v a l i d padding='valid' 时,
o u t p u t = i n p u t × s t r i d e s output=input\times strides
参数为 p a d d i n g = s a m e padding='same' 时,
o u t p u t = ( i n p u t 1 ) × s t r i d e s + k e r n e l _ s i z e output=(input-1)\times strides+kernel\_size

发布了116 篇原创文章 · 获赞 13 · 访问量 3万+

猜你喜欢

转载自blog.csdn.net/qq_36758914/article/details/104648322