Beihang HPC
Jupyter Interface
reference:
what is great about this method is that you can ssh to the compute node directly, instead of staying in the log in node.
#!/bin/bash
#SBATCH -J name_of_the_job
#SBATCH -p cpu-high
#SBATCH -N 1 # one node
#SBATCH -n 1 # one cpu or gpu
#SBATCH -t 5:00 # maximum time
#SBATCH -o job.out # will print on the terminal if omitted
#SBATCH -e job.err
XDG_RUNTIME_DIR=""
port=$(shuf -i8000-9999 -n1)
node=$(hostname -s)
user=$(whoami)
cluster=$(hostname -f | awk -F"." '{print $2}')
clusterurl="10.212.70.128"
export PATH=$PATH:~/.local/bin
# print tunneling instructions jupyter-log
echo -e "
MacOS or linux terminal command to create your ssh tunnel:
ssh -N -L ${port}:${node}:${port} ${user}@${clusterurl}
Here is the MobaXterm info:
Forwarded port:same as remote port
Remote server: ${node}
Remote port: ${port}
SSH server: ${cluster}.${clusterurl}
SSH login: $user
SSH port: 22
Use a Browser on your local machine to go to:
localhost:${port} (prefix w/ https:// if using password)
or copy the URL from below and put there localhost after http:// so it would be something like:
http://localhost:9499/?token=86c93ba16aaead7529a5da0e5e5a46be7ad8cfea35b2d49f
"
# load modules or conda environments here
# e.g. farnam:
# module load Python/2.7.13-foss-2016b
# conda env activate mx
# DON'T USE ADDRESS BELOW.
# DO USE TOKEN BELOWa
# module load anaconda3
# source activate blpenv
#srun -p gpu-high --gres=gpu:2 jupyter lab --no-browser --port=${port} --ip=${node}
jupyter lab --no-browser --port=${port} --ip=${node}
DATASETS
- CARRADA Dataset:
- RADIATE DATASET:
- CRUW Dataset:
- NuScenes Dataset:
- RadarScenes Dataset:
- RADDet Dataset:
- Real-World Marine Radar Datasets for Target Tracking: (export controlled)
- Waymo Open Dataset:
- Coloradar:
SERVER
WORKSTATION
- Lenovo thinkstation p520
- CPU Xeon w2125 4ghz
- GPU rtx2080 8GMEM
- MEM 32G,can be extended to 128G