What ground truth information is available in round two?
- Full ground truth segmentation?
- Additional cameras?
- All multimodal information?
Do you mean as a way to validate results offline?
Sorry, during the training step (1hr practice).
You can choose to use any set of parameters while training or during the practice session, as these will ultimately change the quality of the trained model. However during evaluation only a fixed set of parameters are available (speed, RGB from front+right+left).