czczup / ViT-Adapter

[ICLR 2023 Spotlight] Vision Transformer Adapter for Dense Predictions
https://arxiv.org/abs/2205.08534
Apache License 2.0
1.26k stars 139 forks source link

number of iteration in the case of a batchsize equals to 1 #149

Open iacopo97 opened 1 year ago

iacopo97 commented 1 year ago

Hi, thank you for your amazing work! I have a question regarding the number of iteration in the following scenario. I have a gpu with 12 gigs, I have managed to start a training with a crop size of (448, 448) in the config of mask2former_beit_adapter_large_896_80k_cityscapes_ss.py and a batchsize equals to 1. Which is the number of iterations thta you suggest to use in the following scenario? Or should I add another modification to the network?