search

koehlp / wda_tracker

Weighted distance aggregation multi person multi camera tracker
MIT License
49 stars 12 forks source link

Inference on my dataset using WDA model. #4

Open toshalpatel opened 3 years ago

toshalpatel commented 3 years ago

Hi @koehlp Thanks a lot for the open repository. This is a great help! I am using your trained models on a different sample dataset for inference. I got the SCT and now I want to do the clustering of the tracks across cameras. When I configure the configs/clustering_configs/mta_es_abd_non_clean.py, do I need the "train_data" paths? Can I just perform a simple inference (as I don't have the gt values for my dataset)? If so, can you please help me as to what needs to be done?

koehlp commented 3 years ago

You can switch the features of that need them. Like the feature homography matching feature.

sry948749099 commented 3 years ago

Hi @koehlp Thanks a lot for the open repository. This is a great help! I am using your trained models on a different sample dataset for inference. I got the SCT and now I want to do the clustering of the tracks across cameras. When I configure the configs/clustering_configs/mta_es_abd_non_clean.py, do I need the "train_data" paths? Can I just perform a simple inference (as I don't have the gt values for my dataset)? If so, can you please help me as to what needs to be done?

Hi，

I also want to use WDA model on my own dataset, may i ask if you have completed it? Could you please give some key suggestions for modification?

Thanks