Copyright (C) 2018 NVIDIA Corporation. All rights reserved. Licensed under the CC BY-NC-SA 4.0 license (https://creativecommons.org/licenses/by-nc-sa/4.0/legalcode).
Most parameters in the config files are self-explanatory. Here are some notes:
-
betais the initial value of Gamma (Eq. 3 of the paper) for absolute pose -
gammais the initial value of Gamma (Eq. 3 of the paper) for relative pose -
stepsis the size of tuples of images to use for training (parametersdescribed in Section 3.5 of the paper) -
skipis the spacing between these images (parameterkdescribed in Section 3.5 of the paper) -
realis a flag indicating whether the poses should be GPS/SLAM/integration of visual odometry (true) or from ground truth (false) -
color_jitteris the intensity of color jittering (brightness, hue, contrast and saturation) data augmentation. NOTE: Setcolor_jitter = 0inmapnet.iniwhile training it on the 7 Scenes dataset. -
s_abs_trans,s_abs_rot,s_rel_trans,s_rel_rotare the covariance values for absolute and relative translations and rotations passed to the PGO algorithm (see Appendix in our arXiv paper). To reproduce results from our paper, use the following values:
7 Scenes:
| Scene | s_abs_trans |
s_abs_rot |
s_rel_trans |
s_rel_rot |
|---|---|---|---|---|
| chess | 1 | 1 | 35 | 35 |
| fire | 1 | 1 | 10 | 10 |
| heads | 1 | 1 | 1 | 1 |
| office | 0.1 | 0.1 | 20 | 10 |
| pumpkin | 1 | 1 | 500 | 500 |
| redkitchen | 1 | 1 | 35 | 35 |
| stairs | 1 | 1 | 2 | 4 |
RobotCar
| Scene | s_abs_trans |
s_abs_rot |
s_rel_trans |
s_rel_rot |
|---|---|---|---|---|
| loop | 1 | 1 | 20 | 20 |
| full | 1 | 1 | 1 | 10 |
Use the files according to their name e.g. use mapnet++_7Scenes.ini if you
want to train a MapNet++ model on the 7 Scenes dataset.
If you want to perform pose-graph optimization (PGO) during inference on any
of the trained models, use the pgo_inference_*.ini files. The inference of a
MapNet++ model (without PGO) should be done with mapnet.ini.