akshay-bapat-magna

Distributed Training Slower

11

Hi, I have two RTX A6000 GPUs available for training (device IDs 0 and 1). I run the GDRN training as: "./core/gdrn_modeling/train_gdrn.sh 0,1". The training starts as usual but it...

Freeze Layers for Training

2

Have you implemented a way to freeze training for certain layers of the network? I have the backbone and geometric feature portion of the network trained, I would like to...

Hello, Thank you for the support you have been providing in solving issues regarding this repository! The detection algorithm works well for objects that are not cluttered, similar to the...