Any suggestions for improving the effectiveness of the model, such as increasing the number of model parameters?

[2anchao]

hello author: I find that fsdv2 model training occupy less memory, config is configs/fsdv2/fsdv2_nusc_2x.py, and I want use fsdv2 for autolabel, so do you have any suggestions on the model structure to improve the model, such as backbone choice or other module?