An error when running conda-installed lmp

[leiwang1989]

2020-10-26 23:57:10.091502: I tensorflow/core/platform/cpu_feature_guard.cc:142] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN)to use the following CPU instructions in performance-critical operations: SSE4.1 SSE4.2 AVX AVX2 FMA
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
2020-10-26 23:57:10.116914: I tensorflow/core/platform/profile_utils/cpu_utils.cc:104] CPU Frequency: 2800075000 Hz
2020-10-26 23:57:10.120487: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x55ca67ebf0c0 initialized for platform Host (this does not guarantee that XLA will be used). Devices:
2020-10-26 23:57:10.120554: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version
Not found: Op type not registered 'DescrptNorot' in binary running on ws8364. Make sure the Op and Kernel are registered in the binary running in this process. Note that if you are loading a saved graph which used ops from tf.contrib, accessing (e.g.) tf.contrib.resampler should be done before importing the graph, as contrib ops are lazily registered when the module is first accessed.

[njzjz]

Which version did you install? conda list | grep lmp
And which model did you use?

[leiwang1989]

I am using the latest version by doing:
conda install deepmd-kit=*=cpu lammps-dp==*cpu -c deepmodeling

The model I use is the Al-Mg downloaded from deepmd-kit website.

[njzjz]

Oh I see. You cannot use a model trained by 1.x version deepmd-kit in 1.y deepmd-kit if x≠y.

[njzjz]

@amcadmus @jameswind Who maintains the website? We need to indicate the deepmd-kit version of the model.

[njzjz]

I am using the latest version by doing:
conda install deepmd-kit=*=cpu lammps-dp==*cpu -c deepmodeling

The model I use is the Al-Mg downloaded from deepmd-kit website.

To install 1.1 version, using

conda install deepmd-kit=1.1.*=*cpu lammps-dp=1.1.*=*cpu -c deepmodeling

[leiwang1989]

Thanks for your response. It however give me another error called "out of range" using 1.1.* version.

build with tf lib: /home/zit.bam.de/lwang1/miniconda3/envs/deepmd/lib/libtensorflow_cc.so;/home/zit.bam.de/lwang1/miniconda3/envs/deepmd/lib/libtensorflow_framework.so
2020-10-28 16:56:15.512907: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA
2020-10-28 16:56:15.530230: I tensorflow/core/platform/profile_utils/cpu_utils.cc:94] CPU Frequency: 2800075000 Hz
2020-10-28 16:56:15.531938: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x55fc01bfb0f0 initialized for platform Host (this does not guarantee that XLA will be used). Devices:
2020-10-28 16:56:15.531977: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version
Out of range: Read less bytes than requested

[njzjz]

tensorflow/tensorflow#21544 (comment)

[leiwang1989]

The version of 0.12. * seems not working?

conda install deepmd-kit==0.12.8=*cpu lammps-dp==0.12.8=*cpu -c deepmodeling
Collecting package metadata (current_repodata.json): done
Solving environment: failed with initial frozen solve. Retrying with flexible solve.
Solving environment: failed with repodata from current_repodata.json, will retry with next repodata source.
Collecting package metadata (repodata.json): done
Solving environment: failed with initial frozen solve. Retrying with flexible solve.
Solving environment: /
Found conflicts! Looking for incompatible packages.
This can take several minutes. Press CTRL-C to abort. failed

UnsatisfiableError: The following specifications were found to be incompatible with each other:

Output in format: Requested package -> Available versions

Package deepmd-kit conflicts for:
lammps-dp==0.12.8[build=*cpu] -> deepmd-kit==0.12.8[build=*cpu]
deepmd-kit==0.12.8[build=*cpu]

[njzjz]

We deleted 0.12 because there was not enough space. We just re-upload it.