File size: 2,355 Bytes
8d82201 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 |
#!/bin/bash
#SBATCH --job-name=lavt_ccg # Submit a job named "example"
#SBATCH [email protected]
#SBATCH --mail-type=BEGIN,END,FAIL
#SBATCH --partition=a100 # a6000 or a100
#SBATCH --gres=gpu:2
#SBATCH --time=7-00:00:00 # d-hh:mm:ss, max time limit
#SBATCH --mem=84000 # cpu memory size
#SBATCH --cpus-per-task=8 # cpu num
#SBATCH --output=log_refcocog_google_lavt_one.txt # std output filename
ml cuda/11.0 # ํ์ํ ์ฟ ๋ค ๋ฒ์ ๋ก๋
eval "$(conda shell.bash hook)" # Initialize Conda Environment
conda activate lavt # Activate your conda environment
# train
# mkdir ./models
# mkdir ./models/gref_umd/
# CUDA_VISIBLE_DEVICES=0,1 python -m torch.distributed.launch --nproc_per_node 2 --master_port 12345 train.py --model lavt --dataset refcocog --splitBy umd --model_id gref_umd --batch-size 14 --lr 0.00005 --wd 1e-2 --swin_type base --pretrained_swin_weights ./pretrained_weights/swin_base_patch4_window12_384_22k.pth --epochs 40 --img_size 480 2>&1 | tee ./models/gref_umd/output
# mkdir ./models/gref_umd_lavt_one/
# srun python -m torch.distributed.launch --nproc_per_node 2 --master_port 12345 train.py --model lavt_one --dataset refcocog --splitBy umd --model_id gref_umd_lavt_one --batch-size 14 --lr 0.00005 --wd 1e-2 --swin_type base --pretrained_swin_weights ./pretrained_weights/swin_base_patch4_window12_384_22k.pth --epochs 40 --img_size 480 2>&1 | tee ./models/gref_umd_lavt_one/output
# mkdir ./models/gref_google
# CUDA_VISIBLE_DEVICES=0,1,2,3 python -m torch.distributed.launch --nproc_per_node 4 --master_port 12345 train.py --model lavt --dataset refcocog --splitBy google --model_id gref_google --batch-size 8 --lr 0.00005 --wd 1e-2 --swin_type base --pretrained_swin_weights ./pretrained_weights/swin_base_patch4_window12_384_22k.pth --epochs 40 --img_size 480 2>&1 | tee ./models/gref_google/output
mkdir ./models/gref_google_lavt_one
srun python -m torch.distributed.launch --nproc_per_node 2 --master_port 12347 train.py --model lavt_one --dataset refcocog --splitBy google --model_id gref_google_lavt_one --batch-size 14 --lr 0.00005 --wd 1e-2 --swin_type base --pretrained_swin_weights ./pretrained_weights/swin_base_patch4_window12_384_22k.pth --epochs 50 --img_size 480 2>&1 | tee ./models/gref_google_lavt_one/output |