cd course-software-skills-hpc/demo
-cat batch_example.sh
-
#!/bin/bash
-
-#SBATCH -p gpu # partition (queue)
-#SBATCH -N 1 # number of nodes
-#SBATCH --mem 2G # memory pool for all cores
-#SBATCH -n 2 # number of cores
-#SBATCH -t 0-0:10 # time (D-HH:MM)
-#SBATCH -o slurm_output.out
-#SBATCH -e slurm_error.err
-#SBATCH --mail-type=ALL
-#SBATCH --mail-user=adam.tyson@ucl.ac.uk
-
-module load miniconda
-conda activate slurm_demo
-
-for i in{1..5}
-do
-echo"Multiplying $i by 10"
-python multiply.py $i 10 --jazzy
-done
+
cd course-software-skills-hpc/demo
+cat batch_example.sh
+
#!/bin/bash
+
+#SBATCH -p gpu # partition (queue)
+#SBATCH -N 1 # number of nodes
+#SBATCH --mem 2G # memory pool for all cores
+#SBATCH -n 2 # number of cores
+#SBATCH -t 0-0:10 # time (D-HH:MM)
+#SBATCH -o slurm_output.out
+#SBATCH -e slurm_error.err
+#SBATCH --mail-type=ALL
+#SBATCH --mail-user=adam.tyson@ucl.ac.uk
+
+module load miniconda
+conda activate slurm_demo
+
+for i in{1..5}
+do
+echo"Multiplying $i by 10"
+python multiply.py $i 10 --jazzy
+done
Run batch job:
-
sbatch batch_example.sh
+
sbatch batch_example.sh
Array jobs
Check out array script:
-
cat array_example.sh
-
#!/bin/bash
-
-#SBATCH -p gpu # partition (queue)
-#SBATCH -N 1 # number of nodes
-#SBATCH --mem 2G # memory pool for all cores
-#SBATCH -n 2 # number of cores
-#SBATCH -t 0-0:10 # time (D-HH:MM)
-#SBATCH -o slurm_array_%A-%a.out
-#SBATCH -e slurm_array_%A-%a.err
-#SBATCH --mail-type=ALL
-#SBATCH --mail-user=adam.tyson@ucl.ac.uk
-#SBATCH --array=0-9%4
-
-# Array job runs 10 separate jobs, but not more than four at a time.
-# This is flexible and the array ID ($SLURM_ARRAY_TASK_ID) can be used in any way.
-
-module load miniconda
-conda activate slurm_demo
-
-echo"Multiplying $SLURM_ARRAY_TASK_ID by 10"
-python multiply.py $SLURM_ARRAY_TASK_ID 10 --jazzy
+
cat array_example.sh
+
#!/bin/bash
+
+#SBATCH -p gpu # partition (queue)
+#SBATCH -N 1 # number of nodes
+#SBATCH --mem 2G # memory pool for all cores
+#SBATCH -n 2 # number of cores
+#SBATCH -t 0-0:10 # time (D-HH:MM)
+#SBATCH -o slurm_array_%A-%a.out
+#SBATCH -e slurm_array_%A-%a.err
+#SBATCH --mail-type=ALL
+#SBATCH --mail-user=adam.tyson@ucl.ac.uk
+#SBATCH --array=0-9%4
+
+# Array job runs 10 separate jobs, but not more than four at a time.
+# This is flexible and the array ID ($SLURM_ARRAY_TASK_ID) can be used in any way.
+
+module load miniconda
+conda activate slurm_demo
+
+echo"Multiplying $SLURM_ARRAY_TASK_ID by 10"
+python multiply.py $SLURM_ARRAY_TASK_ID 10 --jazzy
Run array job:
-
sbatch array_example.sh
+
sbatch array_example.sh
Using GPUs
Start an interactive job with one GPU:
-
srun-p gpu --gres=gpu:1 --pty bash -i
+
srun-p gpu --gres=gpu:1 --pty bash -i
Load TensorFlow & CUDA
-
module load tensorflow
-module load cuda/11.8
+
module load tensorflow
+module load cuda/11.8
Check GPU
-
python
-
import tensorflow as tf
-tf.config.list_physical_devices('GPU')
+
python
+
import tensorflow as tf
+tf.config.list_physical_devices('GPU')
cd ~/course-software-skills-hpc/pose-estimation/slurm-scripts
-ls
+
cd ~/course-software-skills-hpc/pose-estimation/slurm-scripts
+ls
@@ -991,14 +1121,14 @@
See example batch scripts
Make sure all scripts are executable
-
chmod +x *.sh
+
chmod +x *.sh
Edit a specific script:
-
nano sleap_train_slurm.sh
+
nano sleap_train_slurm.sh
Save with Ctrl+O (followed by Enter), exit with Ctrl+X
@@ -1008,66 +1138,66 @@
Batch script for training
sleap_train_slurm.sh
-
#!/bin/bash
-
-#SBATCH -J slp_train # job name
-#SBATCH -p gpu # partition (queue)
-#SBATCH -N 1 # number of nodes
-#SBATCH --mem 16G # memory pool for all cores
-#SBATCH -n 4 # number of cores
-#SBATCH -t 0-06:00 # time (D-HH:MM)
-#SBATCH --gres gpu:1 # request 1 GPU (of any kind)
-#SBATCH -o slurm.%x.%N.%j.out # STDOUT
-#SBATCH -e slurm.%x.%N.%j.err # STDERR
-#SBATCH --mail-type=ALL
-#SBATCH --mail-user=user@domain.com
-
-# Load the SLEAP module
-module load SLEAP
-
-# Define the directory of the exported training job package
-SLP_JOB_NAME=labels.v001.slp.training_job
-SLP_JOB_DIR=/ceph/scratch/$USER/$SLP_JOB_NAME
-
-# Go to the job directory
-cd$SLP_JOB_DIR
-
-# Run the training script generated by SLEAP
-./train-script.sh
+
#!/bin/bash
+
+#SBATCH -J slp_train # job name
+#SBATCH -p gpu # partition (queue)
+#SBATCH -N 1 # number of nodes
+#SBATCH --mem 16G # memory pool for all cores
+#SBATCH -n 4 # number of cores
+#SBATCH -t 0-06:00 # time (D-HH:MM)
+#SBATCH --gres gpu:1 # request 1 GPU (of any kind)
+#SBATCH -o slurm.%x.%N.%j.out # STDOUT
+#SBATCH -e slurm.%x.%N.%j.err # STDERR
+#SBATCH --mail-type=ALL
+#SBATCH --mail-user=user@domain.com
+
+# Load the SLEAP module
+module load SLEAP
+
+# Define the directory of the exported training job package
+SLP_JOB_NAME=labels.v001.slp.training_job
+SLP_JOB_DIR=/ceph/scratch/$USER/$SLP_JOB_NAME
+
+# Go to the job directory
+cd$SLP_JOB_DIR
+
+# Run the training script generated by SLEAP
+./train-script.sh
