[英]how can I connect models in pytorch?
I made 2 classes:我做了2节课:
class Preprocess():
def __init
.....
def forward
....
class Model ():
def __init
.....
def forward
I would like to do Preprocess before putting them into Model.我想在将它们放入 Model 之前进行预处理。 Could you kindly tell me how can I achieve that?
你能告诉我我怎样才能做到这一点吗?
Just compose them:只需编写它们:
pre = Preprocess()
model = Model()
output = model(pre(input))
One could also use torch.nn.Sequential
which has the following upsides:也可以使用
torch.nn.Sequential
,它具有以下优点:
inputs
instead of remembering to call Preprocess
before itinputs
,而不是记住在它之前调用Preprocess
Code being:代码是:
model = torch.nn.Sequential(Preprocess(), Model())
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.