diff --git a/README.md b/README.md index d48732b78575967dd28a891091325d4c5b5b511d..f58e2660eee504da87185578a4efffd7688aa0d0 100644 --- a/README.md +++ b/README.md @@ -19,15 +19,15 @@ python /gdrnpp_bop2022/preprocessing/preprocess_fruitbin.py --src_directory PATH - --src_directory - the input directory with the folders of all the fruits; - --dst_directory - the output directory; -- --scenario - the scenario for splitting data in the dataset from the Splitting folder. Basic dataset splitting scenarios: +- --scenario - the scenario for splitting data in the dataset. Basic dataset splitting scenarios: `_world_occ_07.txt, _world_occ_05.txt, _world_occ_03.txt, _world_occ_01.txt, _camera_occ_07.txt, _camera_occ_05.txt, _camera_occ_03.txt, _camera_occ_01.txt` -Due to the specifics of the fruitbin dataset, it turned out that using yolox did not give good results, so instead of the detections detected by yolox, a gt was used. To do this, a script was written that generates a .json file of gt in the required format. The command to run the script: +Due to the specifics of the fruitbin dataset, it turned out that using yolox did not give good results, so instead of the detections detected by yolox, a gt was used. To do this, a [script](https://gitlab.liris.cnrs.fr/gduret/gdrnpp_bop2022/-/blob/main/preprocessing/generate_gt.py?ref_type=heads) was written that generates a .json file of gt in the required format. The command to run the script: ``` python /gdrnpp_bop2022/preprocessing/generate_gt.py`. ``` -After creating the file, make sure that the path to it is correct in the main config file +After creating the file, make sure that the path to it is correct in the main config file in GDRNPP. The [generate_image_sets_file](https://gitlab.liris.cnrs.fr/gduret/gdrnpp_bop2022/-/blob/main/preprocessing/generate_image_sets_file.py?ref_type=heads) and [generate_test_targets_file](https://gitlab.liris.cnrs.fr/gduret/gdrnpp_bop2022/-/blob/main/preprocessing/generate_test_targets_file.py?ref_type=heads) scripts create two files required for testing: ``` @@ -46,7 +46,7 @@ python /gdrnpp_bop2022/core/gdrn_modeling/tools/fruitbin/eval_pose.py --path_dat ``` - --path_data - path to the dataset -- --pred_path - the path to the .csv file created after testing the model with the detected positions +- --pred_path - path to .csv file with detected positions created after testing the model - --class_name - the fruit for which the pose accuracy is estimated - --symmetry - a boolean value of whether the fruit is symmetrical. In the Fruitbin dataset, only banana and pear are asymmetrical.