Generates the input. Json file for nitrogen molecules

[2329611140]

This is the first time FOR me to come into contact with DEEPMD-Kit. At present, I am using deepMD-Kit on the MobaXterm server. I am looking for articles on building molecular models and training tests on the Internet. JSON file to use it?

[njzjz]

The manual is available at https://docs.deepmodeling.org/projects/deepmd/.

…

On Oct 16, 2021, at 09:04, 2329611140 ***@***.***> wrote:  我是第一次接触deepmd-kit，目前是在MobaXterm服务器上使用deepmd-kit，在网上找不到关于构建分子模型并用来训练测试的文章，我想使用deepmd-kit 来对氮气分子进行模拟并且收集其训练数据，我该如何生成相关的.JSON文件去使用它？ — You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub, or unsubscribe.

[AnguseZhang]

Please use English instead of Chinese to communicate, since we have many users who can't read Chinese. So this issue is declined.

[2329611140]

I tried to modify the parameters in the input.json file of se_e2_A in the water folder on GitHub, and then used deepMD to collect training data of nitrogen molecules, but I received an error when running the code. The error code is as follows:
WARNING:tensorflow:From /home/feng/.local/conda/envs/deepmd/lib/python3.9/site-p_resource_variables (from tensorflow.python.ops.variable_scope) is deprecated an
Instructions for updating:
non-resource variables are not supported in the long term
WARNING:root:Environment variable KMP_BLOCKTIME is empty. Use the default value
WARNING:root:Environment variable KMP_AFFINITY is empty. Use the default value g
WARNING:deepmd.train.run_options:Switch to serial execution due to lack of horov
Traceback (most recent call last):
File "/home/feng/.local/conda/envs/deepmd/bin/dp", line 10, in
sys.exit(main())
File "/home/feng/.local/conda/envs/deepmd/lib/python3.9/site-packages/deepmd/e
train_dp(**dict_args)
File "/home/feng/.local/conda/envs/deepmd/lib/python3.9/site-packages/deepmd/e
jdata = j_loader(INPUT)
File "/home/feng/.local/conda/envs/deepmd/lib/python3.9/site-packages/deepmd/c
return json.load(fp)
File "/home/feng/.local/conda/envs/deepmd/lib/python3.9/json/init.py", lin
return loads(fp.read(),
File "/home/feng/.local/conda/envs/deepmd/lib/python3.9/json/init.py", lin
return _default_decoder.decode(s)
File "/home/feng/.local/conda/envs/deepmd/lib/python3.9/json/decoder.py", line
obj, end = self.raw_decode(s, idx=_w(s, 0).end())
File "/home/feng/.local/conda/envs/deepmd/lib/python3.9/json/decoder.py", line
raise JSONDecodeError("Expecting value", s, err.value) from None
json.decoder.JSONDecodeError: Expecting value: line 49 column 3 (char 1325)

The code of my JSON file is as follows. I hope you can help me to see what needs to be improved. Thank you very much！
{
"_comment": " model parameters",
"model": {
"type_map": ["N"],
"_comment": " type_map 应该和训练集中的顺序保持一致",
"descriptor" :{
"type": "se_e2_a",
"sel": "auto",
"rcut_smth": 0.50,
"rcut": 5.00,
"neuron": [25, 50, 100],
"resnet_dt": false,
"axis_neuron": 16,
"seed": 1,
"_comment": " that's all"
},
"fitting_net" : {
"neuron": [240, 240, 240],
"resnet_dt": true,
"seed": 1,
"_comment": " that's all"
},
"_comment": " that's all"
},

"learning_rate" :{
    "type":         "exp",
    "decay_steps":  5000,
    "start_lr":     0.001,
    "stop_lr":      3.51e-8,
    "_comment":     "that's all"
},

"loss" :{
    "type":         "ener",
    "start_pref_e": 0.02,
    "limit_pref_e": 1,
    "start_pref_f": 1000,
    "limit_pref_f": 1,
    "start_pref_v": 0.02,
    "limit_pref_v": 1,
    "_comment":     " that's all"
},

"training" : {
    "training_data": {
        "systems":   [

"../data/N2",
],
"batch_size": "auto",
"_comment": "that's all"
},
"numb_steps": 1000000,
"seed": 10,
"disp_file": "lcurve.out",
"disp_freq": 100,
"save_freq": 1000,
"_comment": "that's all"
},

"_comment":         "that's all"

}

[wanghan-iapcm]

The error message is quite clear:

json.decoder.JSONDecodeError: Expecting value: line 49 column 3 (char 1325)