error: Not found: No attr named 'T' in NodeDef when running lammps

[minghuisvn]

I tried the water data in the deepmd-kit' repository example folder, and obtained the frozened model, graph.pb. But when running lammps by "lmp -i in.lammps", the errors occured. The error message was:

lmp: Relink `/home/linazhao/anaconda3/envs/dpmd/bin/../lib/./libgfortran.so.4' with `/lib/x86_64-linux-gnu/librt.so.1' for IFUNC symbol `clock_gettime'
2021-03-15 13:27:39.025473: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcudart.so.10.1
LAMMPS (29 Oct 2020)
OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (src/comm.cpp:94)
Warning: please export TSAN_OPTIONS='ignore_noninstrumented_modules=1' to avoid false positive reports from the OpenMP runtime!
  using 1 OpenMP thread(s) per MPI task
Reading data file ...
  triclinic box = (0.0000000 0.0000000 0.0000000) to (12.444700 12.444700 12.444700) with tilt (0.0000000 0.0000000 0.0000000)
  1 by 1 by 1 MPI processor grid
  reading atoms ...
  192 atoms
  read_data CPU = 0.001 seconds
Summary of lammps deepmd module ...
  >>> Info of deepmd-kit:
  installed to:       /home/linazhao/anaconda3/envs/dpmd
  source:             v1.3.2
  source brach:       HEAD
  source commit:      2644cca
  source commit at:   2021-03-02 06:30:13 +0800
  build float prec:   double
  build with tf inc:  /home/linazhao/anaconda3/envs/dpmd/include;/home/linazhao/anaconda3/envs/dpmd/include
  build with tf lib:  /home/linazhao/anaconda3/envs/dpmd/lib/libtensorflow_cc.so;/home/linazhao/anaconda3/envs/dpmd/lib/libtensorflow_framework.so
  set tf intra_op_parallelism_threads: 0
  set tf inter_op_parallelism_threads: 0
  >>> Info of lammps module:
  use deepmd-kit at:  /home/linazhao/anaconda3/envs/dpmd
  source:             v1.3.2
  source branch:      HEAD
  source commit:      2644cca
  source commit at:   2021-03-02 06:30:13 +0800
  build float prec:   double
  build with tf inc:  /home/linazhao/anaconda3/envs/dpmd/include;/home/linazhao/anaconda3/envs/dpmd/include
  build with tf lib:  /home/linazhao/anaconda3/envs/dpmd/lib/libtensorflow_cc.so;/home/linazhao/anaconda3/envs/dpmd/lib/libtensorflow_framework.so
2021-03-15 13:27:39.160914: 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 AVX512F FMA
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
2021-03-15 13:27:39.161764: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcuda.so.1
2021-03-15 13:27:39.476767: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1716] Found device 0 with properties:
pciBusID: 0000:17:00.0 name: GeForce RTX 2070 SUPER computeCapability: 7.5
coreClock: 1.8GHz coreCount: 40 deviceMemorySize: 7.79GiB deviceMemoryBandwidth: 417.29GiB/s
2021-03-15 13:27:39.477166: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1716] Found device 1 with properties:
pciBusID: 0000:65:00.0 name: GeForce RTX 2070 SUPER computeCapability: 7.5
coreClock: 1.8GHz coreCount: 40 deviceMemorySize: 7.79GiB deviceMemoryBandwidth: 417.29GiB/s
2021-03-15 13:27:39.477186: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcudart.so.10.1
2021-03-15 13:27:39.478532: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcublas.so.10
2021-03-15 13:27:39.479767: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcufft.so.10
2021-03-15 13:27:39.480076: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcurand.so.10
2021-03-15 13:27:39.481273: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcusolver.so.10
2021-03-15 13:27:39.481847: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcusparse.so.10
2021-03-15 13:27:39.484181: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcudnn.so.7
2021-03-15 13:27:39.485599: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1858] Adding visible gpu devices: 0, 1
2021-03-15 13:27:39.485626: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcudart.so.10.1
2021-03-15 13:27:40.234693: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1257] Device interconnect StreamExecutor with strength 1 edge matrix:
2021-03-15 13:27:40.234741: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1263]      0 1
2021-03-15 13:27:40.234747: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1276] 0:   N N
2021-03-15 13:27:40.234751: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1276] 1:   N N
2021-03-15 13:27:40.236264: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1402] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 7184 MB memory) -> physical GPU (device: 0, name: GeForce RTX 2070 SUPER, pci bus id: 0000:17:00.0, compute capability: 7.5)
2021-03-15 13:27:40.237286: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1402] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:1 with 7181 MB memory) -> physical GPU (device: 1, name: GeForce RTX 2070 SUPER, pci bus id: 0000:65:00.0, compute capability: 7.5)
Not found: No attr named 'T' in NodeDef:
         [[{{node DescrptSeA}}]]
         [[DescrptSeA]]

the deepmd version is v.1.3.2.

[amcadmus]

The model was trained with a DeePMD-kit version < 1.3.

[SteveRickUNO]

I am having a very similar problem, when I try to go through the water example. It got through the training and freezing, but encounters this error with lammps. I installed using conda install deepmd-kit=*=cpu lammps-dp==*cpu -c deepmodeling
The training used v1.2.3-4-gc3dff7c and lmp is version v1.3.3
Was the previous issue resolved?

[njzjz]

@SteveRickUNO I think the version you are actually using for training is 1.2.4

[SteveRickUNO]

so should I update lmp? Can I do the with conda?

[njzjz]

Use conda create -n deepmd deepmd-kit=*=*cpu lammps-dp=*=*cpu -c deepmodeling and you should get a correct version.

[njzjz]

If the old version is v1.2, we've provided dp convert-to command in v1.2.4 and you can convert it to v1.3.

[SteveRickUNO]

thanks for your response. That was the same install command I used intially, but I ran it again But now I cant run dp to train (previously I could). I get errors about importing numpy c-extenions failed Any help or suggestions you could give would be great. Thanks!

…

________________________________ From: Jinzhe Zeng ***@***.***> Sent: Friday, June 25, 2021 8:35 PM To: deepmodeling/deepmd-kit ***@***.***> Cc: Steven W Rick ***@***.***>; Mention ***@***.***> Subject: Re: [deepmodeling/deepmd-kit] error: Not found: No attr named 'T' in NodeDef when running lammps (#417) WARNING: This email originated outside of the University of New Orleans system. The sender of this email could not be validated and may not actually be the person in the “From” field. Do NOT click links or open attachments if the message seems suspicious in any way. Never provide your user ID or password. Use conda create -n deepmd deepmd-kit=*=*cpu lammps-dp=*=*cpu -c deepmodeling and you should get a correct version. — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub<https://nam12.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2Fdeepmodeling%2Fdeepmd-kit%2Fdiscussions%2F417%23discussioncomment-923294&data=04%7C01%7Csrick%40uno.edu%7C2a20ab0db3444a28048008d93842acfa%7C31d4dbf540044469bfeedf294a9de150%7C0%7C0%7C637602681288314454%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&sdata=HiGDR8dVKLkKx%2B1taRupJEdQys1yoSLgOma69%2B%2BydW8%3D&reserved=0>, or unsubscribe<https://nam12.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2Fnotifications%2Funsubscribe-auth%2FAUJCTBQNFJQPZPFJBW7FFQDTUUVF5ANCNFSM47H4XKGA&data=04%7C01%7Csrick%40uno.edu%7C2a20ab0db3444a28048008d93842acfa%7C31d4dbf540044469bfeedf294a9de150%7C0%7C0%7C637602681288324449%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&sdata=So%2FFLQApCPY5%2FRA1HZflANzo5lVFEl5KymZcKWYp7C4%3D&reserved=0>. NOTICE: This message, including all attachments transmitted with it, is intended solely for the use of the Addressee(s) and may contain information that is PRIVILEGED, CONFIDENTIAL, and/or EXEMPT FROM DISCLOSURE under applicable law. If you are not the intended recipient, you are hereby notified that any disclosure, copying, distribution, or use of the information contained herein is STRICTLY PROHIBITED. If you received this communication in error, please destroy all copies of the message, whether in electronic or hard copy format, as well as attachments and immediately contact the sender by replying to this email or contact the sender at the telephone numbers listed above. Thank you!

[SteveRickUNO]

it looks like I installed version 1.2.4. Should I install a different version? Are different versions available through conda?

…

________________________________ From: Jinzhe Zeng ***@***.***> Sent: Tuesday, August 10, 2021 10:29 PM To: deepmodeling/deepmd-kit ***@***.***> Cc: Steven W Rick ***@***.***>; Mention ***@***.***> Subject: Re: [deepmodeling/deepmd-kit] error: Not found: No attr named 'T' in NodeDef when running lammps (#417) WARNING: This email originated outside of the University of New Orleans system. The sender of this email could not be validated and may not actually be the person in the “From” field. Do NOT click links or open attachments if the message seems suspicious in any way. Never provide your user ID or password. If the old version is v1.2, we've provided dp convert-to command in v1.2.4 and you can convert it to v1.3. — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub<https://nam12.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2Fdeepmodeling%2Fdeepmd-kit%2Fdiscussions%2F417%23discussioncomment-1156788&data=04%7C01%7Csrick%40uno.edu%7C62349ddca9ac4f9c3f4908d95c7830ae%7C31d4dbf540044469bfeedf294a9de150%7C0%7C0%7C637642493566802462%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&sdata=531yu%2BRbdFlFTyS9K2PcdoA%2B3ywqf%2B9WYF8ERUSwot0%3D&reserved=0>, or unsubscribe<https://nam12.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2Fnotifications%2Funsubscribe-auth%2FAUJCTBV3JIV2J5QS56K67XLT4HVATANCNFSM47H4XKGA&data=04%7C01%7Csrick%40uno.edu%7C62349ddca9ac4f9c3f4908d95c7830ae%7C31d4dbf540044469bfeedf294a9de150%7C0%7C0%7C637642493566802462%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&sdata=dFzTAf8S3ZL9GBIvxl3sStErM7CzjWazOF0ZRUeCrO4%3D&reserved=0>. Triage notifications on the go with GitHub Mobile for iOS<https://nam12.safelinks.protection.outlook.com/?url=https%3A%2F%2Fapps.apple.com%2Fapp%2Fapple-store%2Fid1477376905%3Fct%3Dnotification-email%26mt%3D8%26pt%3D524675&data=04%7C01%7Csrick%40uno.edu%7C62349ddca9ac4f9c3f4908d95c7830ae%7C31d4dbf540044469bfeedf294a9de150%7C0%7C0%7C637642493566812458%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&sdata=cva1Md3zG81sYemT82WbmlLqs%2BB8KgmM8U8ftbiL87I%3D&reserved=0> or Android<https://nam12.safelinks.protection.outlook.com/?url=https%3A%2F%2Fplay.google.com%2Fstore%2Fapps%2Fdetails%3Fid%3Dcom.github.android%26utm_campaign%3Dnotification-email&data=04%7C01%7Csrick%40uno.edu%7C62349ddca9ac4f9c3f4908d95c7830ae%7C31d4dbf540044469bfeedf294a9de150%7C0%7C0%7C637642493566812458%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&sdata=FWQooUKH5vruP8znIJBVRkDTG3DTYKCdlgzWklHLqsQ%3D&reserved=0>. NOTICE: This message, including all attachments transmitted with it, is intended solely for the use of the Addressee(s) and may contain information that is PRIVILEGED, CONFIDENTIAL, and/or EXEMPT FROM DISCLOSURE under applicable law. If you are not the intended recipient, you are hereby notified that any disclosure, copying, distribution, or use of the information contained herein is STRICTLY PROHIBITED. If you received this communication in error, please destroy all copies of the message, whether in electronic or hard copy format, as well as attachments and immediately contact the sender by replying to this email or contact the sender at the telephone numbers listed above. Thank you!