Commit b1dd01ec authored by Jong, Stefan1 de's avatar Jong, Stefan1 de
Browse files


parent 86251dd9
......@@ -141,7 +141,7 @@ The output can be found in the `forwarded` folder. The visuals can be found in t
## Tuning
Tuning will be used to find the most suitable parameters to detect and track your objects. A random search approach is been applied on the training dataset (`train.seqmap`) and will be validated on your validation set (`val.seqmap`).
Both the training and validation sequences should be stored in the `train` folder ("KITTI_segtrack_data_dir"). In order to specify the sequences for training and testing please follow this procedure:
- Go to home folder/mots_tools/mots_eval/
- Go to TrackR-CNN/mots_tools/mots_eval/
- Open train.seqmap and val.seqmap
- Add the sequences for training (train.seqmap) and validation (val.seqmap) according to the following format:
- `<seq_id> empty <start_frame> <end_frame>`
Supports Markdown
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment