villanuevab

num_classes=8 creates off-by-one error with number of predictions

1

Thanks for this implementation. In `ssd_common.py` using default params we have `num_classes=8`; this is consistent with what is in `datasets/kitti*`. I understand why `no_annotations_label=9`, and think I see that these...

Minimum graph for inference

5

Hello. Thank you for your great work. In `nets/SqueezeDet.py` we have: ``` self._add_forward_graph() self._add_interpretation_graph() self._add_loss_graph() self._add_train_graph() self._add_viz_graph() ``` What is the purpose of each of these graphs, and which is...

Fix typo in random_split_train_val.py

util is not used in this script.

Calibration .txt files

4

Which of the calibration parameters in `calib/xxxxx.txt` are required for inference? `P0-P3` ??? `R0_rect` Required `Tr_velo_to_cam` Required `Tr_imu_to_velo` ???