documentation

This commit is contained in:
Lorenzo 2021-01-07 16:31:03 +01:00
parent a843ca8c85
commit d940c60fec
3 changed files with 4 additions and 4 deletions

View File

@ -57,5 +57,5 @@ or check the file `monstereo/run.py`
Further instructions for prediction, preprocessing, training and evaluation can be found here:
* [MonoLoco++README](https://github.com/vita-epfl/monstereo/blob/master/docs/MonoLoco%2B%2B.md)
* [MonoLoco++ README](https://github.com/vita-epfl/monstereo/blob/master/docs/MonoLoco%2B%2B.md)
* [MonStereo README](https://github.com/vita-epfl/monstereo/blob/master/docs/MonStereo.md)

View File

@ -138,7 +138,7 @@ We provide evaluation on KITTI in the eval section. Txt files for MonStereo are
`python -m monstereo.run eval --dir_ann <directory of pifpaf annotations> --model data/models/ms-200710-1511.pkl --generate`
<img src="quantitative_mono.png" width="500"/>
<img src="quantitative_mono.png" width="600"/>
### Relative Average Precision Localization (RALP-5%)
We modified the original C++ evaluation of KITTI to make it relative to distance. We use **cmake**.

View File

@ -200,10 +200,10 @@ python -m monstereo.run eval
To include also geometric baselines and MonoLoco, add the flag ``--baselines``
<img src="quantitative_mono.png" width="500"/>
<img src="quantitative_mono.png" width="550"/>
Adding the argument `save`, a few plots will be added including 3D localization error as a function of distance:
<img src="results.png" width="500"/>
<img src="results.png" width="600"/>
### Activity Estimation (Talking)
Please follow preprocessing steps for Collective activity dataset and run pifpaf over the dataset images.