dp train AssertionError

[StevenAlice93]

Hello, friends, I have met a problem when I train a model using the command: dp train my.json, which output these error:

WARNING:tensorflow:From /usr/local/anaconda3/lib/python3.8/site-packages/tensorflow/python/compat/v2_compat.py:96: 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
WARNING:root:Environment variable KMP_BLOCKTIME is empty. Use the default value 0
WARNING:root:Environment variable KMP_AFFINITY is empty. Use the default value granularity=fine,verbose,compact,1,0

DEEPMD: _____ _____ __ __ _____ _ _ _

DEEPMD: | __ \ | __ \ | / || __ \ | | (_)| |

DEEPMD: | | | | ___ ___ | |__) || \ / || | | | ______ | | __ _ | |_

DEEPMD: | | | | / _ \ / _ | / | |/| || | | ||___|| |/ /| || __|

DEEPMD: | |__| || _/| /| | | | | || || | | < | || |

DEEPMD: |/ _| _||| || |_||____/ ||_|| __|

DEEPMD:

DEEPMD: Please read and cite:

DEEPMD: Wang, Zhang, Han and E, Comput.Phys.Comm. 228, 178-184 (2018)

DEEPMD:

DEEPMD: ---Summary of the training---------------------------------------

DEEPMD: installed to: /tmp/pip-req-build-yjnc2t_a/_skbuild/linux-x86_64-3.8/cmake-install

DEEPMD: source : v1.2.1-3-g30922e7

DEEPMD: source brach: HEAD

DEEPMD: source commit: 30922e7

DEEPMD: source commit at: 2020-09-14 22:49:07 +0800

DEEPMD: build float prec: double

DEEPMD: build with tf inc: /usr/local/anaconda3/lib/python3.8/site-packages/tensorflow/include;/usr/local/anaconda3/lib/python3.8/site-packages/tensorflow/include

DEEPMD: build with tf lib:

DEEPMD: running on: VM-16-80-centos

DEEPMD: CUDA_VISIBLE_DEVICES: unset

DEEPMD: num_intra_threads: 0

DEEPMD: num_inter_threads: 0

DEEPMD: -----------------------------------------------------------------

DEEPMD:

2020-11-02 12:20:16.194233: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 AVX512F FMA
2020-11-02 12:20:16.221681: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3200000000 Hz
2020-11-02 12:20:16.223804: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x2b5f1781a780 initialized for platform Host (this does not guarantee that XLA will be used). Devices:
2020-11-02 12:20:16.223838: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version
2020-11-02 12:20:16.226920: I tensorflow/core/common_runtime/process_util.cc:147] Creating new thread pool with default inter op setting: 2. Tune using inter_op_parallelism_threads for best performance.
Traceback (most recent call last):
File "/usr/local/anaconda3/bin/dp", line 10, in
sys.exit(main())
File "/usr/local/anaconda3/lib/python3.8/site-packages/deepmd/main.py", line 66, in main
train(args)
File "/usr/local/anaconda3/lib/python3.8/site-packages/deepmd/train.py", line 81, in train
_do_work(jdata, run_opt)
File "/usr/local/anaconda3/lib/python3.8/site-packages/deepmd/train.py", line 122, in _do_work
data = DeepmdDataSystem(systems,
File "/usr/local/anaconda3/lib/python3.8/site-packages/deepmd/DataSystem.py", line 27, in init
self.data_systems.append(DeepmdData(ii,
File "/usr/local/anaconda3/lib/python3.8/site-packages/deepmd/Data.py", line 25, in init
assert(len(self.type_map) >= max(self.atom_type)+1)
AssertionError

However, if I use the command dp train water_se_a.json to train a dataset from the example, which is correct.

Please help me!

[njzjz]

I think the atom type in your training data is not consistent with type_map in your json file. Please check it.