tensorflow中neural network中的卷积
首先下面是3个常用的卷积函数
conv2d
: Arbitrary filters that can mix channels together.
depthwise_conv2d
: Filters that operate on each channel independently.
separable_conv2d
: A depthwise spatial filter followed by a pointwise filter.
1.卷积操作的结果output的大小[out_height, out_width]与input大小[in_height, in_width]和移动步长stride之间的关系。
out_height = ceil(float(in_height) / float(strides[1]))
out_width = ceil(float(in_width) / float(strides[2]))