You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
There are cases where multiple nn.Module components are involved in a training process, some of which are never trained but used in an eval mode, in a preprocessing, for instance (detection, neural augmenters, batch preprocessor). In these cases, we would have to override constructors for those components, but why not abstract all the checkpoint loading logic inside class Mixins, and the instantiate components that need checkpoint loading logic from the corresponding Mixin. In this case, all the checkpoint loading parameters for the mixin are placed as module parameters in config.
The text was updated successfully, but these errors were encountered:
There are cases where multiple nn.Module components are involved in a training process, some of which are never trained but used in an eval mode, in a preprocessing, for instance (detection, neural augmenters, batch preprocessor). In these cases, we would have to override constructors for those components, but why not abstract all the checkpoint loading logic inside class Mixins, and the instantiate components that need checkpoint loading logic from the corresponding Mixin. In this case, all the checkpoint loading parameters for the mixin are placed as module parameters in config.
The text was updated successfully, but these errors were encountered: