Closed nikk-nikaznan closed 3 years ago
Hi, thank you for your interest.
I recommend you not using the embedding_model
. It is very time-consuming to code and train and you can get great results without it. Just set in the cfg file appearance_matching
to False
, and then you just have to calculate the rest of the box features related to their size, location, etc. Bbox descriptors are not needed.
@AlbertoSabater I am using scaled yolo v4 in my current project. I have already implemented the version with appearance_matching set as False for Scaled Yolo V4 and am getting a good improvement in results. But there are cases of false positives, mixing of different objects in tubelets at times, etc. Hence, want to dedicate time to building the embedding model for the same.
It would be really great if you could provide an idea/strcuture of the embedding model and the manner in which feature maps are pulled from a base model.
Thank you.
Hi,
Thank you for the great work. I want to try to implement your work for detection from detectron2. Your get_repp_predictions.py really helpful for me to re-format my prediction from detectron2. However, I am stuck in getting the embedding_model. Is there any example on how the embedding model need to look like?
Thank you