vishnuexe

Intrinsic-TexPlain

Dataset Used (Download link is also given):

CUBS (image-wise attributes) - https://www.kaggle.com/datasets/wenewone/cub2002011

AwA2 (class-wise attributes) - https://cvml.ista.ac.at/AwA2/

Paniyoor Research Institute Black pepper leaf dataset (class-wise attributes) - https://drive.google.com/drive/folders/1_YEtSIXGsvzYFVlzz8rVYWB1iZrlUoGG?usp=sharing

vishnuexe

mpi

#!/bin/bash #SBATCH --job-name=aigc # create a short name for your job
#SBATCH --nodes=2 # node count
#SBATCH --ntasks=1 # total number of tasks across all nodes
#SBATCH --cpus-per-task=4 # cpu-cores per task (>1 if multi-threaded tasks)
#SBATCH --mem-per-cpu=4G # memory per cpu-core (4G per cpu-core is default)
#SBATCH --time=11:59:00 # total run time limit (HH:MM:SS)
#SBATCH --error=%j.err # filename for logging errors while execution
#SBATCH --mail-type=begin #send mail when job begins

vishnuexe

Step1:
pip install gdown
Step2:
pip install --upgrade --no-cache-dir gdown
Step3:
Copy file/folder id from google drive (copy the sharabel link and paste it somewhere https://drive.google.com/file/d/1ndGh-3D8kaVFktogs_jhPkvXac90vzTh/view?usp=drive_link)
here this is the file id - 1ndGh-3D8kaVFktogs_jhPkvXac90vzTh
Links will be of the format - https://drive.google.com/file/d/<file_id>/view?usp=drive_link
Step4:
Now paste the file id with the commands below and execute!

vishnuexe

Accessing Jupyter-lab running in remote ssh server

Step1: ssh into your remote server

$ ssh username@server_ip_address

Step2: Run this in the remote server

#starting jupyter lab
$ jupyter lab --ip 0.0.0.0 --port 8888 --no-browser --allow-root

vishnuexe

git add .

git commit -m "message"

git push

git init

vishnuexe

create def file

Bootstrap: docker
From: <give docker image path>  example: nvcr.io/nvidia/pytorch:24.11-py3

%post
    <required packages to be installed or commands to be exectued for preparation of the main program>
    apt-get -y update
    apt-get install -y python-pip
    pip install diffusers==0.30.2

vishnuexe

Accessing Jupyter-lab running inside docker in remote ssh server

Step1: ssh into your remote server

$ ssh username@server_ip_address

Step2: Run this in the remote server

#running docker with port assignment
#replace image:version with your docker image id
$ docker run --gpus all -it -p 8888:8888 image:version

vishnuexe

Docker Manual

Step 1 : Install Docker

#Docker Installation 

$ sudo apt-get update

$ curl https://get.docker.com | sh \