Nikos Giakoumoglou
Nikos Giakoumoglou
> > > Hello. First of all, thank you for your amazing code. While trying to train the YOLOv3 model from scratch on yymnist dataset, I noticed that the loss...
Can you paste the command that freezes the weights?
Dont think I did at that time.
For the specific feature, the mask is indeed ignored. It is a section.
Hi and thank you for your comment. Indeed, the implementation does not include a memory bank, rather it calculates the loss using the mini batch.
Most self-supervised learning methods typically operate on feature vectors, making it possible to work with 3D data. However, when working with 3D data, two specific modifications are required: 1) applying...
TBH, I haven't thought about it yet. However, I might consider including it in the near future!