I want to use a Sequential to build a model but i just use each of them to froward? what the difference of them?
m = Sequential(nn.Conv2d(),nn.ReLU(),nn.Conv2d(),nn.ReLU())
what the difference of the following of
o = m(x)
o = m(m(x))
o = m(m(o))
do the backward have some influences or other difference?
Thanks for your reply, and i mean that i define the network by sequential and in forward process, i want to get intermediate outputs, so i use o1=m(m(x)) o2=m(m(o1)) and output o1, and o2. I want make sure that the process whether the same as o=m(x)（including forward , backward, weight update ect.）
ok,thanks a lot. By the way, do the eval mode fix the running_mean and var and weight and bias of BatchNorm2d, or only fix the mean and var? When fixing the bn, is fix all the 4 or only mean and var, thanks.