Issues when using python script to test the trained model

[sd123s0-3123]

I was following the instractionn of the website: https://nb.bohrium.dp.tech/detail/1003 on my own ubuntu system(22.03), some issue occur when I reach part 5 of testing trained model. when I try to run the python script to generate a plot to compare trained data and validation data, the following error occurred:
WARNING:tensorflow:From /home/murphy/deepmd-kit/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
WARNING:root:To get the best performance, it is recommended to adjust the number of threads by setting the environment variables OMP_NUM_THREADS, TF_INTRA_OP_PARALLELISM_THREADS, and TF_INTER_OP_PARALLELISM_THREADS. See https://deepmd.rtfd.io/parallelism/ for more information.
Traceback (most recent call last):
File "/home/murphy/CH4/01.train/correlation.py", line 6, in
predict = training_systems.predict("graph.pb")
File "/home/murphy/deepmd-kit/lib/python3.10/site-packages/dpdata/system.py", line 947, in predict
driver = Driver.get_driver(driver)(*args, **kwargs)
File "/home/murphy/deepmd-kit/lib/python3.10/site-packages/dpdata/plugins/deepmd.py", line 369, in init
import deepmd.DeepPot as DeepPot
File "/home/murphy/deepmd-kit/lib/python3.10/site-packages/deepmd/init.py", line 32, in
set_mkl()
File "/home/murphy/deepmd-kit/lib/python3.10/site-packages/deepmd/env.py", line 244, in set_mkl
if "mkl_rt" in np.config.get_info("blas_mkl_info").get("libraries", []):
AttributeError: module 'numpy.config' has no attribute 'get_info'

Will it be the module predict goes wrong?

[njzjz]

#2853 is going to fix it.

[njzjz]

By the way, TensorFlow has limited the maximum NumPy version to 1.24.3.
https://github.com/tensorflow/tensorflow/blob/v2.13.0/tensorflow/tools/pip_package/setup.py#L93
If you installed TensorFlow normally, NumPy 1.26 should not be installed.

[sd123s0-3123]

Thanks for your reply，I successfully ran the script after reinstalling the 1.24.3 version of numpy and got the diagram.