The inner workings of this model are documented in detail in doc/report.pdf
This resvar implementation has been overhauled using the Dense Transformer Networks and Feature Pyramid Networks proposed by Roddick and Cipolla, 2020. This implementation also comes with a custom pretraining task of predicting the permutation of the six input images.
This model is not documented in the report
Contains the resvar model in resnet
along with other helper models like
segmentation
and a plain vae
that was also implemented. A util
class
implements intermediate models.
Contains data transformation functions for the resvar model
This is the main training script which performs the following:
- Sets up the training environment and training parameters
- Sets up
DataParallel
if possible - Performs unsupervised image reconstruction for the backbone and saves the model
- Performs superivsed map reconstruction and bounding box prediction, and saves the model.