deepmodeling
Error while dp train input.json
Summary
I constructes folders as type.raw, type_map.raw, set.000 - [box.npy, force.npy, energy.npy, coord.npy] { "model": { "type_map": [ "W", "Fe", "Ni", "Co" ], "descriptor": { "type": "se_e2_a", "rcut": 6.0, "rcut_smth": 0.5, "sel": [ 40, 40, 40, 40 ], "neuron": [ 10, 20, 40 ], "resnet_dt": false, "axis_neuron": 4, "seed": 1, "_comment": "that's all" }, "fitting_net": { "neuron": [ 100, 100, 100 ], "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-08, "_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, "limit_pref_v": 0, "_comment": "that's all" }, "training": { "training_data": { "systems": [ "train_data/set_1/", "train_data/set_2/", "train_data/set_3/" ], "batch_size": "auto", "_comment": "that's all" }, "validation_data": { "systems": [ "test_data/set_1/", "test_data/set_2/", "test_data/set_3/" ], "batch_size": "auto", "numb_btch": 1, "_comment": "that's all" }, "numb_steps": 100000, "seed": 10, "disp_file": "lcurve.out", "disp_freq": 1000, "save_freq": 10000 } } This is the input.json I am using.
DeePMD-kit Version
DeePMD-kit v2.2.9
Backend and its version
Tensorflow 2.9.0
Python Version, CUDA Version, GCC Version, LAMMPS Version, etc
No response
Details
ARNING:tensorflow:From /home/user/anaconda3/envs/deepmd/lib/python3.10/site-packages/tensorflow/python/compat/v2_compat.py:107: disable_resource_variables (from tensorflow.python.ops.variable_scope) is deprecated and will be removed in a future version.
Instructions for updating:
non-resource variables are not supported in the long term
DEEPMD INFO Calculate neighbor statistics... (add --skip-neighbor-stat to skip this step)
Traceback (most recent call last):
File "/home/user/anaconda3/envs/deepmd/bin/dp", line 10, in
Does the format of the coord.npy file as 73.57 and 7.357+e1 is creating this error? I am using dump files from lammps to create coord.npy, force.npy, box.npy and energy.npy for correspondin frame.
Using dp data the coord generated file contains the format 7.357+e1 but manually creating the same files the format was the former one. Can this be the source of error?
And if my dump file is in the format id Type x y z fx fy fz. Then using the command
dsys = dpdata.System("/content/dump.w_ni_fe_1900.lammpstrj", fmt="lammps/dump") dsys.to("deepmd/npy", "deepmd_data", set_size=dsys.get_nframes())
is only creating the coord.npy, type.raw type_map.raw and box.npy.
In spite of having fx fy fz in the dump file, the above command is not able to account for the forces to create force.npy file.
To solve this issue, I have to extract the corresponding data manually, which results in the error. The shape of data is the same after using update and manually extracting data from frames.
I think the error is because https://github.com/deepmodeling/dpdata/tree/master/dpdata/lammps/dump.py does not have any code snippet for force when using lammps/dump format.
This is the data format I am using for training
energy = [-245065.86684099, -245043.93657998, -245078.53004939, -245036.34437463, -245108.69610125, -245173.16775741, -245215.20799936, -245135.88491991, -245208.40294702,........,]
force = array([[ 0.722155 , 1.66346 , 0.182122 , ..., -0.116272 , 0.485847 , -1.33518 ], [-0.83064 , -1.31154 , 0.387978 , ..., 6.23634 , 6.10007 , -1.11442 ], [-0.142134 , 1.41269 , -2.4242 , ..., -4.30655 , 0.709387 , -1.23845 ], ..., [ 0.0186577, 0.150581 , -0.727243 , ..., -0.502336 , -0.660103 , -1.29336 ], [ 1.28235 , -0.375996 , 0.200156 , ..., 1.17807 , 1.61571 , 0.646577 ], [ 1.18955 , 1.91557 , 0.920073 , ..., -1.23146 , 1.72745 , 3.02438 ]])
coord = ([[69.1717 , 59.716 , 4.91938, ..., 57.8245 , 48.3722 , 14.392 ], [69.5761 , 60.1495 , 74.4595 , ..., 57.8314 , 48.1864 , 14.312 ], [69.5075 , 60.0246 , 5.08948, ..., 57.8827 , 48.7315 , 14.1056 ], ..., [68.4911 , 59.1742 , 73.6108 , ..., 56.6714 , 46.084 , 12.5388 ], [68.1387 , 59.1014 , 73.3706 , ..., 56.4182 , 46.2359 , 12.5394 ], [68.2556 , 58.8982 , 73.3789 , ..., 56.6145 , 45.388 , 12.4219 ]])
box = array([[69.60792272, 0. , 0. , 0. , 69.60792272, 0. , 0. , 0. , 69.60792272],...............................]])
However I ran another program with different data and this ran.
This is the data which is running properly
energy = [-245065.86684099, -245043.93657998, -245078.53004939, -245036.34437463, -245108.69610125, -245173.16775741, -245215.20799936, -245135.88491991, -245208.40294702,........,]
force = array([[ 3.6391 , 2.20297 , 3.04376 , ..., 0.165536 , 0.121503 , -0.939756 ], [-0.955997 , -1.82867 , -0.320071 , ..., 5.49932 , -0.213522 , 2.20919 ], [ 1.86836 , 2.75882 , -0.457042 , ..., 4.37476 , -1.67104 , -0.68138 ], ..., [-0.111075 , -0.0626644, -0.277481 , ..., -0.744622 , 0.755648 , -0.780645 ], [-0.399858 , -1.18326 , -1.75817 , ..., -1.61044 , -0.189367 , 1.03649 ], [-0.48448 , -3.57668 , -0.724496 , ..., 4.93316 , 1.73451 , -0.469619 ]])
coord = array([[6.70427000e-02, 2.46912000e-01, 2.05648000e-02, ..., 6.99589000e+01, 6.99504000e+01, 6.97164000e+01], [2.63638545e-01, 4.02347945e-01, 7.08109239e+01, ..., 7.02872239e+01, 7.04596239e+01, 6.95565239e+01], [2.59688357e-01, 6.82876357e-01, 7.07703334e+01, ..., 7.02759334e+01, 6.91589334e+01, 7.01310334e+01], ..., [6.93155176e+01, 6.87564176e+01, 6.91942176e+01, ..., 6.66071176e+01, 6.81565176e+01, 7.05844176e+01], [6.93936865e+01, 6.92003865e+01, 6.94609865e+01, ..., 6.68730865e+01, 6.78987865e+01, 7.03048865e+01], [6.92384739e+01, 6.84930739e+01, 6.88023739e+01, ..., 6.60239739e+01, 6.76421739e+01, 3.05772869e-01]])
box = array([[71.375 , 0. , 0. , 0. , 71.375 , 0. , 0. , 0. , 71.375 ],,...............................]])