kaist-amsg / imatgen Goto Github PK
View Code? Open in Web Editor NEWimage-based generative model for inverse design of solid state materials
image-based generative model for inverse design of solid state materials
I am getting the below error when I try to run the following lines of code
import argparse
from ase.io import read, write
from ase.io import iread
import numpy as np
from ase import Atom, Atoms
parser = argparse.ArgumentParser(description='mapping POSCAR or cif structure into a box image')
parser.add_argument('--input_file', type=str,nargs='+',
help='a file path with the poscar or cif structure')
parser.add_argument('--filetype', type=str,default='cif',
help='filetype : cif,vasp')
parser.add_argument('--nbins', type=int,default=32,
help='number of bins in one dimension')
parser.add_argument('--nproc', type=int,default=1,
help='number of process')
args = parser.parse_args()
inputfile = args.input_file
filetype = args.filetype
print(inputfile)
print(filetype)
atoms = read(inputfile,format = args.filetype, parallel = False)
My command line input is the following
python prog.py --input_file D:\deepak\coding practice\iMatGen-VO_dataset_generated_strctures\VO_dataset\geometries\mp-170_copy1_opt.vasp --file_type vasp --nbins 20 --nproc 1
Please add some instructions in the README
@jhwann
Hi, I'm a master student in Japan.
Thank you for sharing codes and data about the iMatGen.
I'm interested in your research and trying to reproduce the result using Pytorch.
When I'm reading the Supplemental Information, I wonder how to get the MP subset data. Especially, I couldn't understand the two constraints in the following sentence.
we trained iMatGen using the MP subset consisting of
28,242 crystal structures taken from the MP database (up to 5 atom types in the unit cell)
satisfying two constraints as mentioned in the main text to obtain pre-trained model parameters
for IC and MG (without formation energy classification task)
What is the two constraints...?
I think the main paper didn't mention about them. I want to know the details about MP subset.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.