how to give two datasets containing different elements in dpgen

[kyuan2019]

Dear all,
I have two training data but they contain different elements. Here is my input file for the beginning part of the param.jason:
{
"type_map": ["Mg","O","H","Na","C"],
"init_data_prefix": "../",
"init_data_sys":[
["init/mgo_NaHCO3_330K/training_data"], #notes: this file contains all the type
["init/mgo444_330K/training_data"] #notes: this one only contains Mg and O, and I also checked the type.raw file to make sure Mg is 0 and O is 1.
],
"sys_configs_prefix": "../",
"sys_configs": [
["init/mgo_NaHCO3_330K/POSCAR_FILES/00001/POSCAR"]
],
"_comment": " that's all ",
"numb_models": 1,
"train_param": "input.json",
"default_training_param": {
"model": {
"type_map": ["Mg","O","H","Na","C"], # notes: I put every element here
"descriptor": {
"type": "se_e2_a",
"sel": [16,95,95,95,95],
"rcut_smth": 0.5,
"rcut": 6.0,
"neuron": [25,50,100],
"resnet_dt": true,
"axis_neuron": 12,
"seed": 5678
},
"fitting_net": {
"neuron": [120,120,120],
"resnet_dt": true,
"seed": 5678
}
},

After I run the code, it shows an error:

nohup: ignoring input
Traceback (most recent call last):
File "/home/cloud/anaconda3/envs/deepmd/bin/dpgen", line 8, in
sys.exit(main())
File "/home/cloud/anaconda3/envs/deepmd/lib/python3.10/site-packages/dpgen/main.py", line 233, in main
args.func(args)
File "/home/cloud/anaconda3/envs/deepmd/lib/python3.10/site-packages/dpgen/generator/run.py", line 5109, in gen_run
run_iter(args.PARAM, args.MACHINE)
File "/home/cloud/anaconda3/envs/deepmd/lib/python3.10/site-packages/dpgen/generator/run.py", line 4437, in run_iter
make_train(ii, jdata, mdata)
File "/home/cloud/anaconda3/envs/deepmd/lib/python3.10/site-packages/dpgen/generator/run.py", line 353, in make_train
sys_paths = expand_sys_str(os.path.join(init_data_prefix, ii))
File "/home/cloud/anaconda3/envs/deepmd/lib/python3.10/posixpath.py", line 90, in join
genericpath._check_arg_types('join', a, *p)
File "/home/cloud/anaconda3/envs/deepmd/lib/python3.10/genericpath.py", line 152, in _check_arg_types
raise TypeError(f'{funcname}() argument must be str, bytes, or '
TypeError: join() argument must be str, bytes, or os.PathLike object, not 'list'

Any idea on how to solve this issue? Thanks!

[njzjz]

init_data_sys should be an 1D list.

[kyuan2019]

Thanks for your reply. What do you mean by a "1D" list? Here is my init_data_sys

"init_data_sys":[
["init/mgo_NaHCO3_330K/training_data"], #Contains Mg, O, H, Na, C
["init/mgo444_330K/training_data"] # contains only Mg and O

So you mean both data should have the same types of elements? In fact, the first one is a MgO surface in NaHCO3 solution and the second one is just a mgo bulk crystal. Is there a way to include both in the dpgen init_data_sys?

Thanks!

[Tong-Zhou223]

Thanks for your reply. What do you mean by a "1D" list? Here is my init_data_sys

"init_data_sys":[ ["init/mgo_NaHCO3_330K/training_data"], #Contains Mg, O, H, Na, C ["init/mgo444_330K/training_data"] # contains only Mg and O

So you mean both data should have the same types of elements? In fact, the first one is a MgO surface in NaHCO3 solution and the second one is just a mgo bulk crystal. Is there a way to include both in the dpgen init_data_sys?

Thanks!

Excuse me, do you know how to write this order of the elements in param.json file now?