From 7650867801941430e5d56634073957b566f84c90 Mon Sep 17 00:00:00 2001
From: ssibirtsev <sibi_ballad@gmx.de>
Date: Wed, 15 Nov 2023 14:51:08 +0100
Subject: [PATCH] Upload New File

---
 ...er_job_GPU_and_sweep_training_template.job | 62 +++++++++++++++++++
 1 file changed, 62 insertions(+)
 create mode 100644 manual/cluster_job_GPU_and_sweep_training_template.job

diff --git a/manual/cluster_job_GPU_and_sweep_training_template.job b/manual/cluster_job_GPU_and_sweep_training_template.job
new file mode 100644
index 0000000..e25032f
--- /dev/null
+++ b/manual/cluster_job_GPU_and_sweep_training_template.job
@@ -0,0 +1,62 @@
+#!/usr/bin/zsh
+
+##############################################
+##### Batch script for the MRCNN training ####
+##############################################
+
+#### CREATE SBATCH ENTRIES ####
+#### Paths and parameters must be adapted accordingly. 
+
+#### job name 
+#SBATCH --job-name=<JobName>
+
+#### Path and name of the output file of the job execution 
+#SBATCH --output=/home/<UserID>/.../<JobOutputFolderName>/%x_%J_output.txt
+
+#### Job runtime determined by testing jobs on the GPU node (see manual). 
+#### Multiply the computing time per epoch resulting from the test by the number of epochs to be trained. 
+#### Add a safety factor, e.g. multiply with 1.2 
+#SBATCH --time=0-00:00:00
+
+#### Memory requirement per GPU determined by testing jobs on the GPU node (see manual). 
+#### Add a safety factor, e.g. multiply with 1.2. 
+#### For example: resulting value is 5GB --> --mem-per-gpu=5G 
+#SBATCH --mem-per-gpu=5G
+
+#### E-mail address 
+#SBATCH --mail-user=<EmailAdress>
+
+#### E-mails to be received 
+#SBATCH --mail-type=ALL
+
+#### Number of tasks to be performed 
+#SBATCH --ntasks=1
+
+#### Number of GPUs required per node 
+#SBATCH --gres=gpu:1
+
+#### Definition of the job array starting at 0. ###
+#### This parameter is only required if you want to perform several jobs in parallel 
+#### from one job script, e.g. grid search via Weights and Biases sweep. 
+#### In this example we perform a grid search with 6 jobs --> array=0-5 
+#SBATCH --array=0-5
+
+#### CREATE TERMINAL ENTRIES ####
+#### Paths and parameters must be adapted accordingly 
+
+#### Loading the Cuda module 
+module load cuda/10.0
+
+#### Export path in which Anaconda is located 
+export PATH=$PATH:/home/<UserID>/anaconda3/bin
+
+#### Activate environment 
+source activate env_mrcnn_gpu
+
+#### Navigate to the path where the droplet.py script is located
+cd /home/<UserID>/.../samples/droplet/
+
+#### Run MRCNN via Weights and Biases.
+#### The <SweepCode> is generated after a sweep is created at the Weights and Biases homepage.
+#### All training parameters are specified in the sweep configuration.
+wandb agent --count 1 avt-droplet-detection/paper/<SweepCode>
\ No newline at end of file
-- 
GitLab