Merge pull request #162 from fatihbaltaci/master
Local tcp:ip and changed setting of rank and world-size
This commit is contained in:
commit
49ae0a55b1
6
train.py
6
train.py
|
@ -212,9 +212,9 @@ if __name__ == '__main__':
|
||||||
parser.add_argument('--img-size', type=int, default=32 * 13, help='pixels')
|
parser.add_argument('--img-size', type=int, default=32 * 13, help='pixels')
|
||||||
parser.add_argument('--resume', action='store_true', help='resume training flag')
|
parser.add_argument('--resume', action='store_true', help='resume training flag')
|
||||||
parser.add_argument('--num-workers', type=int, default=4, help='number of Pytorch DataLoader workers')
|
parser.add_argument('--num-workers', type=int, default=4, help='number of Pytorch DataLoader workers')
|
||||||
parser.add_argument('--dist-url', default='tcp://224.66.41.62:23456', type=str,help='url used to set up distributed training')
|
parser.add_argument('--dist-url', default='tcp://127.0.0.1:9999', type=str,help='url used to set up distributed training')
|
||||||
parser.add_argument('--rank', default=-1, type=int,help='node rank for distributed training')
|
parser.add_argument('--rank', default=0, type=int,help='node rank for distributed training')
|
||||||
parser.add_argument('--world-size', default=-1, type=int,help='number of nodes for distributed training')
|
parser.add_argument('--world-size', default=1, type=int,help='number of nodes for distributed training')
|
||||||
parser.add_argument('--dist-backend', default='nccl', type=str,help='distributed backend')
|
parser.add_argument('--dist-backend', default='nccl', type=str,help='distributed backend')
|
||||||
opt = parser.parse_args()
|
opt = parser.parse_args()
|
||||||
print(opt, end='\n\n')
|
print(opt, end='\n\n')
|
||||||
|
|
Loading…
Reference in New Issue