Geonuk Kim

DeFRCN implementation.

2

Thanks for this repo. I wonder if you have plan to implement DeFRCN (ICCV'21) which is a strong baseline.

How did you select the samples of novel classes?

1

I think FT performance could be dependent on samples of novel class at Fine-tuning phase. Did you select the samples totally randomly to produce the paper's result?

I wonder if the results on paper are single value (from single few-sampled set) or averaged value. If it is average, how many times did you iterate it with shuffle?...

Nice released code. Thanks. Could you share a weight file for the proposed model?

Thank you for a nice work! I found that there is pos_encoding argument in class Relationshipness (relationshipness.py) I guess it is to regress each relationshipness with considering geometric location of...

effect with other augmentation method?

1

Thanks for nice paper and releasing your source code. I wonder if your approach makes effect with other augmentation method such as color jittering, HSV, ...

How can id run multi-node training?

1

### Search before asking - [X] I have searched the Ultralytics YOLO [issues](https://github.com/ultralytics/ultralytics/issues) and [discussions](https://github.com/ultralytics/ultralytics/discussions) and found no similar questions. ### Question Hi there, How can i run multi-node training?...