search

AlbertoSabater / Robust-and-efficient-post-processing-for-video-object-detection

GNU General Public License v3.0
146 stars 20 forks source link

Embedding model #6

Closed nikk-nikaznan closed 3 years ago

nikk-nikaznan commented 3 years ago

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

AlbertoSabater commented 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.

shardulparab97 commented 3 years ago

@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.