dist_train.sh 421 B

1234567891011121314151617
  1. CONFIG=$1
  2. GPUS=$2
  3. NNODES=${NNODES:-1}
  4. NODE_RANK=${NODE_RANK:-0}
  5. PORT=${PORT:-29500}
  6. MASTER_ADDR=${MASTER_ADDR:-"127.0.0.1"}
  7. PYTHONPATH="$(dirname $0)/..":$PYTHONPATH \
  8. python -m torch.distributed.launch \
  9. --nnodes=$NNODES \
  10. --node_rank=$NODE_RANK \
  11. --master_addr=$MASTER_ADDR \
  12. --nproc_per_node=$GPUS \
  13. --master_port=$PORT \
  14. $(dirname "$0")/train.py \
  15. $CONFIG \
  16. --launcher pytorch ${@:3}