SuperPC/half_skipConnect_v100.script at main · sair-lab/SuperPC · GitHub

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
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
#!/bin/sh
################################### Start of SLRUM Script ###################################

################################### Select your cluster ###################################
###SBATCH --cluster=ub-hpc
#SBATCH --cluster=faculty

## Select your partition
#SBATCH --partition=scavenger --qos=scavenger

################################### Set your running time ###################################
#SBATCH --time=48:00:00
#SBATCH --nodes=1
#SBATCH --ntasks-per-node=8

################################### Select your GPU ###################################
## Use snodes command to check their status first
#SBATCH --gres=gpu:tesla_v100-pcie-32gb:1
##SBATCH --gres=gpu:tesla_v100-pcie-16gb:1
###SBATCH --gres=gpu:a100-pcie-40gb:1


################################### Set your memory ###################################
#SBATCH --mem=32768
# Memory per node specification is in MB. It is optional.
# The default limit is 3000MB per core.

################################### Set your job name ###################################
#SBATCH --job-name="super_map_half_skipConnect_input_downsample_2_latent2048"

## Set output name (not work very well right now)
### SBATCH --output= "result_$(date +"%Y_%m_%d_%k_%M_%S").out"

############################ Set the email to receive email #############################
#SBATCH --mail-user=yidu@buffalo.edu
#SBATCH --mail-type=ALL
##SBATCH --requeue
#Specifies that the job will be requeued after a node failure.
#The default is that the job will not be requeued.


################### Beginning of your scipt, it is written with shell ####################

echo "SLURM_JOBID="$SLURM_JOBID
echo "SLURM_TIME="$(date +"%Y_%m_%d_%k_%M_%S")

echo "SLURM_JOB_NODELIST"=$SLURM_JOB_NODELIST
echo "SLURM_NNODES"=$SLURM_NNODES
echo "SLURMTMPDIR="$SLURMTMPDIR

echo "working directory = "$SLURM_SUBMIT_DIR


# module use /projects/academic/cwx/modulefiles
# module load python/my-python-3
source ~/.bashrc
conda activate supermap

## List the module your are using
module list
ulimit -s unlimited

which python
which pytest

nvidia-smi


cat half_skipConnect_v100.script


python train_ae.py --dataset_path '/user/yidu/projects/yidu/super_map/super_map_point_based_one_branch/data/shapenet_oneTraj_20000pts.hdf5' --latent_dim 2048 --input_downsample 2 --run_name 'Attention-TwoBranch-half-skipConect' --project_name 'Super-Map-Project-SmallDataset'


################################### End of SLRUM Script ###################################