RuntimeError: Address already in use

zhiyuanyou / SAFECount

[WACV 2023] Few-shot Object Counting with Similarity-Aware Feature Enhancement

Other

124 stars 22 forks source link

RuntimeError: Address already in use #1

Closed shanguangcv closed 1 year ago

shanguangcv commented 1 year ago

Hi, thanks for your good work, I am trying to reproduce your method. When I train by running (./train_torch.sh #Num_GPUS), if I use one GPU (i.e., ./train_torch.sh 1), the network can be trained. However, if I use more gpus (e.g., ./train_torch.sh 2), it will shows that "RuntimeError: Address already in use".
Moreover, I have tried to change the master_port, but it is still wrong.

zhiyuanyou commented 1 year ago

Hi～ I will fix it soon.

zhiyuanyou commented 1 year ago

Hi~ We have fixed this bug. Please try again. If you use 2 GPU, you could run sh train_torch.sh 2 GPU_IDS, where GPU_IDS is the ID of the GPU you will use, like 0,1.