security_vision/Trajectron-plus-plus
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Merge pull request #9 from mo-zahran/patch-1

Browse source 
Updating pedestrians testing command. Thank you @mo-zahran for catching this!
This commit is contained in:
Boris Ivanovic 2020-04-14 03:27:54 -04:00 committed by GitHub
commit 139080c2ae
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
README.md
View file

@ -125,7 +125,7 @@ If you instead wanted to evaluate a trained model's performance on forecasting p
| Model | Command |
|-----------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| Base | `python evaluate.py --model models/ee_vel --checkpoint=12 --data ../processed/nuScenes_test_full.pkl --output_path results --output_tag vel_ee_ped --node_type PEDESTRIAN --prediction_horizon 6` |
| Base | `python evaluate.py --model models/vel_ee --checkpoint=12 --data ../processed/nuScenes_test_full.pkl --output_path results --output_tag vel_ee_ped --node_type PEDESTRIAN --prediction_horizon 6` |
| +Dynamics Integration, Maps | `python evaluate.py --model models/int_ee_me --checkpoint=12 --data ../processed/nuScenes_test_full.pkl --output_path results --output_tag int_ee_me_ped --node_type PEDESTRIAN --prediction_horizon 6` |
These scripts will produce csv files in the `results` directory which can then be analyzed in the `NuScenes Quantitative.ipynb` notebook.