![]() ![]() The first path can be replaced with the dist-packages folder in the virtual environment.cand_factor: a factor for the number of detection candidatesĮxport PYTHONPATH=/usr/local/lib/python3.5/dist-packages:$PYTHONPATH(including other ROS related pathes).task_type : 1 - SiSo task (2017 BOP Challenge), 2 - ViVo task (2019 BOP challenge format).score_type: 1-scores from a 2D detetion pipeline is used (used for the paper), 2-scores are caluclated using detection score+overlapped mask (only supported for Mask RCNN, used for the BOP challenge).Use trained weights for the paper: /cfg/cfg_paper.json (e.g., cfg_tless_paper.json).For the bop challenge dataset: /cfg/cfg_bop2019.json.Set directories properly based on your environment.//pix2pose_weights//inference.hdf5 : weight files for each objects.//weight_detection: weight files for the detection.//models or model_eval or model_recont.: model directory that contains.Make sure the directories follows the structure below. ![]() ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |