Open skycat88 opened 1 year ago
I have the same issue.
Same question
I have the same issue.
解决了吗
same question!
same question!
you can try: CUDA_VISIBLE_DEVICES=8,9,10,11 python -m torch.distributed.launch train.py
@skycat88 You should change the config .yaml file in ./configs/, specifically the pretrained weight should be h rather than l.
I think the train command should be: CUDA_VISIBLE_DEVICES=0,1,2,3 python -m torch.distributed.launch --nnodes 1 --nproc_per_node 4 train.py --config [CONFIG_PATH]
how do you solve it? Is there four gpus?so if i only have one ,how should I change the command?thank you all
same question!
Please check whether you have change the config .yaml file in ./configs/ with the right SAM checkpoints file.
solve same exception by install package strictly as the requirements and modify the config
@skycat88您应该更改 ./configs/ 中的配置 .yaml 文件,特别是预训练权重应该是 h 而不是 l。
是这样的,我改了一下就可以运行了
I have the same issue.
解决了吗
同问 解决了吗
how do you solve it? Is there four gpus?so if i only have one ,how should I change the command?thank you all
May I ask if you have resolved the problem
我有同样的问题。
解决了吗
同问 解决了吗
maybe? i can use ddp now,i i resolved this problem by reseted my ubuntu ,but i have not to do this program
1、环境版本按照要求配置 readme 中的 loadddptrain.py 没有,使用的是train, 2、下载的数据是cmos,, 请问数据处理有其他要求吗 训练实验用的数据,只有下面的伪装物检测数据,制作的1500 CAMO-COCO-V.1.0-CVIU2019\Camouflage\Images GT