DeepMD-kit(V2.2.2) cannot reshape an array of size 0 into a shape during training

[liqiang4567]

Hello, when I use DeepMD-kit(V2.2.2), I use the command dp train input.json, and the following error occurs. How can I solve it? Data set I am not using force, is force necessary during training?

error message:
DEEPMD INFO training data with min nbor dist: 0.9860776715464545
DEEPMD INFO training data with max nbor size: [2 1]
DEEPMD INFO _____ _____ __ __ _____ _ _ _
DEEPMD INFO | __ \ | __ \ | / || __ \ | | ()| |
DEEPMD INFO | | | | ___ ___ | |__) || \ / || | | | ______ | | __ _ | |
DEEPMD INFO | | | | / _ \ / _ | / | |/| || | | |||| |/ /| || |
DEEPMD INFO | || || /| /| | | | | || || | | < | || |
DEEPMD INFO |/ _| _||| || |_||____/ ||_|| __|
DEEPMD INFO Please read and cite:
DEEPMD INFO Wang, Zhang, Han and E, Comput.Phys.Comm. 228, 178-184 (2018)
DEEPMD INFO Zeng et al, arXiv:2304.09409
DEEPMD INFO See https://deepmd.rtfd.io/credits/ for details.
DEEPMD INFO installed to: /home/conda/feedstock_root/build_artifacts/deepmd-kit_1684940057856/work/_skbuild/linux-x86_64-3.10/cmake-install
DEEPMD INFO source : v2.2.2
DEEPMD INFO source brach: HEAD
DEEPMD INFO source commit: 92ca097
DEEPMD INFO source commit at: 2023-05-24 13:45:03 +0800
DEEPMD INFO build float prec: double
DEEPMD INFO build variant: cuda
DEEPMD INFO build with tf inc: /home/XXX/software/deepmd-kit/lib/python3.10/site-packages/tensorflow/include;/home/XXX/software/deepmd-kit/lib/python3.10/site-packages/tensorflow/../../../../include
DEEPMD INFO build with tf lib:
DEEPMD INFO ---Summary of the training---------------------------------------
DEEPMD INFO running on: gpu04
DEEPMD INFO computing device: gpu:0
DEEPMD INFO CUDA_VISIBLE_DEVICES: unset
DEEPMD INFO Count of visible GPU: 8
DEEPMD INFO num_intra_threads: 0
DEEPMD INFO num_inter_threads: 0
DEEPMD INFO -----------------------------------------------------------------
DEEPMD INFO ---Summary of DataSystem: training -----------------------------------------------
DEEPMD INFO found 1 system(s):
DEEPMD INFO system natoms bch_sz n_bch prob pbc
DEEPMD INFO ../00.data/training_data 3 11 453 1.000 T
DEEPMD INFO --------------------------------------------------------------------------------------
DEEPMD INFO ---Summary of DataSystem: validation -----------------------------------------------
DEEPMD INFO found 1 system(s):
DEEPMD INFO system natoms bch_sz n_bch prob pbc
DEEPMD INFO ../00.data/validation_data 3 11 90 1.000 T
DEEPMD INFO --------------------------------------------------------------------------------------
DEEPMD INFO training without frame parameter
DEEPMD INFO data stating... (this step may take long time)
DEEPMD ERROR cannot reshape array of size 0 into shape (4986,9)
DEEPMD ERROR This error may occur when your label mismatch it's name, i.e. you might store global tensor in atomic_tensor.npy or atomic tensor in tensor.npy.
Traceback (most recent call last):
File "/home/qli/software/deepmd-kit/lib/python3.10/site-packages/deepmd/utils/data.py", line 559, in _load_data
data = np.reshape(data, [nframes, ndof])
File "<array_function internals>", line 180, in reshape
File "/home/qli/software/deepmd-kit/lib/python3.10/site-packages/numpy/core/fromnumeric.py", line 298, in reshape
return _wrapfunc(a, 'reshape', newshape, order=order)
File "/home/qli/software/deepmd-kit/lib/python3.10/site-packages/numpy/core/fromnumeric.py", line 57, in _wrapfunc
return bound(*args, **kwds)
ValueError: cannot reshape array of size 0 into shape (4986,9)

input file:
{
"_comment": " model parameters",
"model": {
"type_map": ["cl", "h"],
"descriptor" :{
"type": "se_e2_a",
"sel": "auto",
"rcut_smth": 0.50,
"rcut": 6.00,
"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":	500,
"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":	0,
"limit_pref_f":	0,
"start_pref_v":	0,
"limit_pref_v":	0,
"_comment":	" that's all"
},

"training" : {
"training_data": {
    "systems":     ["../00.data/training_data"],
    "batch_size":  "auto",
    "_comment":	   "that's all"
},
"validation_data":{
    "systems":	   ["../00.data/validation_data"],
    "batch_size":  "auto",
    "numb_btch":   1,
    "_comment":	   "that's all"
},
"numb_steps":	100000,
"seed":		10,
"disp_file":	"lcurve.out",
"disp_freq":	200,
"save_freq":	1000,
"_comment":	"that's all"
},    

"_comment":		"that's all"

}

[njzjz]

Please check your data. From the error message, the box seems to be an empty array.

[liqiang4567]

Hi, I checked the data, printed the first three frames, and I didn't see anything wrong.
cells:
[[[25. 0. 0.]
[ 0. 25. 0.]
[ 0. 0. 25.]]

[[25. 0. 0.]
[ 0. 25. 0.]
[ 0. 0. 25.]]

[[25. 0. 0.]
[ 0. 25. 0.]
[ 0. 0. 25.]]]
coords:
[[[-1.1 0. 0. ]
[ 0.7 1.2124356 0. ]
[ 0. 0. 0. ]]

[[-1.1 0. 0. ]
[ 0.43262377 1.3314792 0. ]
[ 0. 0. 0. ]]

[[-1.2 0. 0. ]
[ 1.1 0. 0. ]
[ 0. 0. 0. ]]]
energies:
[3.7458065 4.682527 4.710594 ]
forces:
[]

[njzjz]

Obviously, the force is empty.

[liqiang4567]

As mentioned earlier we did not use force, is force necessary for dp training?

[njzjz]

You don't have to provide the force. If you provide the force, it should not be empty.