It is very possible that this question is a duplicate, but I donβt know what this concept is called, so I donβt even know how to look for it.
I am new to Python and trying to understand this function from Caffe Example :
def conv_relu(bottom, ks, nout, stride=1, pad=0, group=1): conv = L.Convolution(bottom, kernel_size=ks, stride=stride, num_output=nout, pad=pad, group=group) return conv, L.ReLU(conv, in_place=True)
I realized that the parameters are stride=1
, pad=1
, etc. in the definition of the function conv_relu
are the initial default values, but then what does kernel_size=ks
, stride=stride
, etc. mean kernel_size=ks
in calling L.Convolution
? Is it like a pair of names / values?
If nothing else, can someone please tell me what this is called?
source share