Loading weights from pretrained model with different module names

3

@smth shouldn’t this work?

pre_trained_model=torch.load("Path to the .pth file")
 new=list(pre_trained.items())

my_model_kvpair=mymodel.state_dict()
count=0
for key,value in my_model_kvpair.item():
  layer_name,weights=new[count]      
mymodel_kvpair[key]=weights
count+=1
6 Likes