Files
DCN_custom_op/classification/train_in1k_deepspeed.sh
Pikaliov 1b3206b6a7 Initial commit: DCNv4 custom op mirror setup
- Add enhanced README with project structure and quick start guide
- Initialize repository with DCNv4 CUDA extension (PyTorch module)
- Include classification, detection, and segmentation subdirectories
- Reference upstream OpenGVLab DCNv4 implementation

Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
2026-06-11 10:30:44 +03:00

28 lines
643 B
Bash

#!/usr/bin/env bash
set -x
PARTITION=$1
JOB_NAME=$2
CONFIG=$3
GPUS=${GPUS:-8}
GPUS_PER_NODE=${GPUS_PER_NODE:-8}
CPUS_PER_TASK=${CPUS_PER_TASK:-12}
SRUN_ARGS=${SRUN_ARGS:-""}
PYTHONPATH="$(dirname $0)/..":$PYTHONPATH \
srun -p ${PARTITION} \
--job-name=${JOB_NAME} \
--gres=gpu:${GPUS_PER_NODE} \
--ntasks=${GPUS} \
--ntasks-per-node=${GPUS_PER_NODE} \
--cpus-per-task=${CPUS_PER_TASK} \
--kill-on-bad-exit=1 \
--quotatype=spot \
${SRUN_ARGS} \
python -u main_deepspeed.py \
--cfg ${CONFIG} \
--local-rank 0 \
--data-path /mnt/lustre/share/images \
--output work_dirs_deepspeed ${@:4}