single point of truth for data and model

Goal: make easier to re-configure for different architectures and datatypes.

• Single file for datatypes
• Config which includes the datatype
• Update train and val entrypoints to use new config
• load_dataset update to use data_config
• directly do a loss function in trainer instead of purpose?

---

Changelog

• main.py sketch no longer needed, ros_adetector covers.

assigned to @hanikevi

created branch 65-single-point-of-truth-for-data-and-model to address this issue

Test suite fresh from main; latent_dim not handled everywhere

changed the description

changed the description

marked the checklist item Single file for datatypes as completed

marked the checklist item Config which includes the datatype as completed

marked the checklist item Update train and val entrypoints to use new config as completed

marked the checklist item load_dataset update to use data_config as completed

marked the checklist item Update train and val entrypoints to use new config as incomplete

mentioned in merge request !45 (merged)

mentioned in commit d931cd10

closed with merge request !45 (merged)