- 'SAME':
out_height = ⌈ float (in_height) / float (strides[1]) ⌉ (向上取整)
out_width = ⌈ float (in_width) / float (strides[2]) ⌉ - 'VALID':
out_height = ⌈ float (in_height - filter_height + 1) / float (strides[1]) ⌉
out_width = ⌈ float (in_width - filter_width + 1) / float (strides[2]) ⌉
卷积神经网络中经卷积、池化后张量形状的变化
猜你喜欢
转载自blog.csdn.net/Juicewyh/article/details/98739675
今日推荐
周排行