24 lines
578 B
Bash
24 lines
578 B
Bash
|
|
#!/usr/bin/env bash
|
||
|
|
|
||
|
|
set -euo pipefail
|
||
|
|
|
||
|
|
NNODES=${PET_NNODES:-1}
|
||
|
|
NODE_RANK=${PET_NODE_RANK:-0}
|
||
|
|
MASTER_ADDR=${PET_MASTER_ADDR:-"127.0.0.1"}
|
||
|
|
MASTER_PORT=${PET_MASTER_PORT:-29500}
|
||
|
|
NPROC_PER_NODE=${PET_NPROC_PER_NODE:-8}
|
||
|
|
|
||
|
|
/home/fcheng/miniconda/bin/python -m torch.distributed.run \
|
||
|
|
--nnodes="${NNODES}" \
|
||
|
|
--node_rank="${NODE_RANK}" \
|
||
|
|
--master_addr "${MASTER_ADDR}" \
|
||
|
|
--master_port "${MASTER_PORT}" \
|
||
|
|
--nproc_per_node "${NPROC_PER_NODE}" \
|
||
|
|
train_mono2d.py \
|
||
|
|
--model yolo26s.pt \
|
||
|
|
--epochs 100 \
|
||
|
|
--batch 128 \
|
||
|
|
--imgsz 768 \
|
||
|
|
--pretrained \
|
||
|
|
--exp_dir=./runs/detect/train_mono2d_20260429
|