Open renshouyu opened 1 month ago
Hi, we used 4 A100 GPUs for training. You can try to change the number of learnable layers (https://github.com/GuangxingHan/FCT/blob/main/configs/fsod/two_branch_training_coco_pvt_v2_b2_li.yaml#L10) or use smaller backbone to save memory.
您好,我想请问一下作者的显卡是多大的啊,我batch_size设为1,运行sh scripts/two_branch_training_pascalvoc_split1_pvt_v2_b2_li.sh的时候还是会爆显存。