out of memory if don`t fix VGG16 param

[aRookieMan]

If dont fix pretrained VGG16s parameters , the model will increasing untill memory booms.
But if fix these parameters , it works.
Why?

code in train.py

for param in net.rpn.features.parameters():
    param.requires_grad = False

[SmallSmallQiu]

谢谢