using multiple dataset with vasp OUTCAR #185

deleep225 · 2022-03-27T04:54:51Z

deleep225
Mar 27, 2022

Is your feature request related to a problem? Please describe.
Im trying to train the vasp output of two different systems (same solvent different solutes).

I have combined the two OUTCAR files with cat command and tried to train the data and got the following error.

Traceback (most recent call last):
File "/data/home/reddy/anaconda3/lib/python3.8/site-packages/nequip/utils/auto_init.py", line 232, in instantiate
instance = builder(**positional_args, **final_optional_args)
File "/data/home/reddy/anaconda3/lib/python3.8/site-packages/nequip/data/dataset.py", line 796, in init
super().init(
File "/data/home/reddy/anaconda3/lib/python3.8/site-packages/nequip/data/dataset.py", line 123, in init
super().init(root=root, transform=type_mapper)
File "/data/home/reddy/anaconda3/lib/python3.8/site-packages/nequip/utils/torch_geometric/dataset.py", line 90, in init
self._process()
File "/data/home/reddy/anaconda3/lib/python3.8/site-packages/nequip/utils/torch_geometric/dataset.py", line 175, in _process
self.process()
File "/data/home/reddy/anaconda3/lib/python3.8/site-packages/nequip/data/dataset.py", line 206, in process
data = self.get_data()
File "/data/home/reddy/anaconda3/lib/python3.8/site-packages/nequip/data/dataset.py", line 857, in get_data
atoms_list = self.get_atoms()
File "/data/home/reddy/anaconda3/lib/python3.8/site-packages/nequip/data/dataset.py", line 852, in get_atoms
return aseread(self.raw_dir + "/" + self.raw_file_names[0], **self.ase_args)
File "/data/home/reddy/anaconda3/lib/python3.8/site-packages/ase/io/formats.py", line 733, in read
return list(_iread(filename, index, format, io, parallel=parallel,
File "/data/home/reddy/anaconda3/lib/python3.8/site-packages/ase/parallel.py", line 275, in new_generator
for result in generator(*args, **kwargs):
File "/data/home/reddy/anaconda3/lib/python3.8/site-packages/ase/io/formats.py", line 803, in _iread
for dct in io.read(fd, *args, **kwargs):
File "/data/home/reddy/anaconda3/lib/python3.8/site-packages/ase/io/formats.py", line 559, in wrap_read_function
for atoms in read(filename, index, **kwargs):
File "/data/home/reddy/anaconda3/lib/python3.8/site-packages/ase/utils/init.py", line 486, in iofunc
obj = func(fd, *args, **kwargs)
File "/data/home/reddy/anaconda3/lib/python3.8/site-packages/ase/io/vasp.py", line 270, in read_vasp_out
return list(g)
File "/data/home/reddy/anaconda3/lib/python3.8/site-packages/ase/io/utils.py", line 246, in call
yield chunk.build(**kwargs)
File "/data/home/reddy/anaconda3/lib/python3.8/site-packages/ase/io/vasp_parsers/vasp_outcar_parsers.py", line 710, in build
return self.parser.build(self.lines)
File "/data/home/reddy/anaconda3/lib/python3.8/site-packages/ase/io/vasp_parsers/vasp_outcar_parsers.py", line 593, in build
results = self.parse(lines)
File "/data/home/reddy/anaconda3/lib/python3.8/site-packages/ase/io/vasp_parsers/vasp_outcar_parsers.py", line 527, in parse
prop = parser.parse(cursor, lines)
File "/data/home/reddy/anaconda3/lib/python3.8/site-packages/ase/io/vasp_parsers/vasp_outcar_parsers.py", line 436, in parse
assert 'spin component' in lines[cursor]
AssertionError
The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "/data/home/reddy/anaconda3/bin/nequip-train", line 8, in
sys.exit(main())
File "/data/home/reddy/anaconda3/lib/python3.8/site-packages/nequip/scripts/train.py", line 65, in main
trainer = fresh_start(config)
File "/data/home/reddy/anaconda3/lib/python3.8/site-packages/nequip/scripts/train.py", line 163, in fresh_start
dataset = dataset_from_config(config, prefix="dataset")
File "/data/home/reddy/anaconda3/lib/python3.8/site-packages/nequip/data/_build.py", line 78, in dataset_from_config
instance, _ = instantiate(
File "/data/home/reddy/anaconda3/lib/python3.8/site-packages/nequip/utils/auto_init.py", line 234, in instantiate
raise RuntimeError(
RuntimeError: Failed to build object with prefix dataset using builder ASEDataset

Describe the solution you'd like
Can we combine the OUTCAR files of different systems and train with nequip?

I have seen in the following thread it is possible with extxyz format.
#89

Should I convert the OUTCAR file to etxyz format if so how to do it?

Thank you.