| #!/bin/bash | |
| #SBATCH -J diffusion # Job name | |
| #SBATCH -p rtx #-dev | |
| #SBATCH -N8 # Number of nodes and cores per node required | |
| #SBATCH --ntasks-per-node=1 | |
| #SBATCH -t 47:59:59 # Duration of the job (Ex: 15 mins) | |
| #SBATCH -oReport-%j # Combined output and error messages file | |
| #SBATCH --mail-type=BEGIN,END,FAIL # Mail preferences | |
| #SBATCH --mail-user=xiabin@gatech.edu | |
| pwd | |
| date | |
| #module load anaconda3/2022.05 # Load module dependencies | |
| #module load pytorch | |
| #conda activate diffusers | |
| conda env list | |
| module list | |
| python -c "import torch; print(torch.cuda.is_available(), torch.__version__, torch.__path__, torch.version.cuda)" | |
| cat $0 | |
| MASTER_ADDR=$(scontrol show hostnames $SLURM_JOB_NODELIST | head -n 1) | |
| MASTER_PORT=$((10000 + RANDOM % 10000)) #12355 | |
| export MASTER_ADDR=$MASTER_ADDR | |
| export MASTER_PORT=$MASTER_PORT | |
| srun python diffusion.py \ | |
| --num_new_img_per_gpu 50 \ | |
| --max_num_img_per_gpu 2 \ | |
| --gradient_accumulation_steps 5 \ | |
| --train "$SCRATCH/LEN128-DIM64-CUB16-Tvir[4, 6]-zeta[10, 250]-0809-123640.h5" \ | |
| #--resume outputs/model-N3000-device_count4-node2-epoch49-23040531 \ | |
| ###################################################################################### | |