-
Notifications
You must be signed in to change notification settings - Fork 2
FAQ
The main loop is shared between different trainers:
The details are specified in the subclasses:
- https://github.com/NeedsMorePie/interpolator/blob/master/train/pwcnet/trainer.py
- https://github.com/NeedsMorePie/interpolator/blob/master/train/context_interp/trainer.py
The top level definition is in this file:
The various components (i.e. context and estimator networks) are in subdirectories.
The total loss (with regularization) is constructed in the main model file:
The implementation details are in a separate file:
https://github.com/NeedsMorePie/interpolator/tree/master/data
Take the warp op for example: https://github.com/NeedsMorePie/interpolator/tree/master/pwcnet/warp/native
There are 3 files in that folder, 2 source files and 1 cmake. If you read through these files it should be fairly straight forward. The root cmake file will automatically glob/find these subdirectory cmake files and add them to the build rules.
To use these ops in Python, create a wrapper like so: https://github.com/NeedsMorePie/interpolator/blob/master/pwcnet/warp/warp.py