INVALID_ARGUMENT: Tensor descrpt_attr/rcut:0, specified in either feed_devices or fetch_devices was not found in the Graph ERROR: DeePMD-kit Error: TensorFlow Error: INVALID_ARGUMENT: Tensor descrpt_attr/rcut:0, specified in either feed_devices or fetch_devices was not found in the Graph

[FandosWang]

Error appeared when I run lammps whith deepmd potential, and how can I solve this problem?

Error information:
LAMMPS (23 Jun 2022 - Update 1)
OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (src/comm.cpp:98)
using 1 OpenMP thread(s) per MPI task
Loaded 1 plugins from /share/home/02011315/miniconda3/envs/dpgen/lib/deepmd_lmp
Loaded 0 plugins from
OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (src/comm.cpp:98)
using 1 OpenMP thread(s) per MPI task
Loaded 1 plugins from /share/home/02011315/miniconda3/envs/dpgen/lib/deepmd_lmp
Loaded 0 plugins from
Reading data file ...
triclinic box = (0 0 0) to (4.05 4.05 4.05) with tilt (0 0 0)
1 by 1 by 1 MPI processor grid
reading atoms ...
4 atoms
read_data CPU = 0.002 seconds
Summary of lammps deepmd module ...

Info of deepmd-kit:
installed to: /share/home/02011315/miniconda3/envs/dpgen
source: v2.1.5
source branch: HEAD
source commit: 6e3d4a6
source commit at: 2022-09-23 16:10:28 +0800
surpport model ver.:1.1
build float prec: double
build variant: cuda
build with tf inc: /share/home/02011315/miniconda3/envs/dpgen/include;/share/home/02011315/miniconda3/envs/dpgen/include
build with tf lib: /share/home/02011315/miniconda3/envs/dpgen/lib/libtensorflow_cc.so;/share/home/02011315/miniconda3/envs/dpgen/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: /share/home/02011315/miniconda3/envs/dpgenDeePMD-kit WARNING: Environmental variable TF_INTRA_OP_PARALLELISM_THREADS is not set. Tune TF_INTRA_OP_PARALLELISM_THREADS for the best performance.
DeePMD-kit WARNING: Environmental variable TF_INTER_OP_PARALLELISM_THREADS is not set. Tune TF_INTER_OP_PARALLELISM_THREADS for the best performance.
DeePMD-kit WARNING: Environmental variable OMP_NUM_THREADS is not set. Tune OMP_NUM_THREADS for the best performance.
2023-02-03 14:03:05.694171: I tensorflow/core/platform/cpu_feature_guard.cc:193] 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 AVX512_VNNI FMA
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
2023-02-03 14:03:08.816744: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1532] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 29259 MB memory: -> device: 0, name: Tesla V100S-PCIE-32GB, pci bus id: 0000:1a:00.0, compute capability: 7.0
2023-02-03 14:03:08.820625: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1532] Created device /job:localhost/replica:0/task:0/device:GPU:1 with 29259 MB memory: -> device: 1, name: Tesla V100S-PCIE-32GB, pci bus id: 0000:1f:00.0, compute capability: 7.0
2023-02-03 14:03:08.822305: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1532] Created device /job:localhost/replica:0/task:0/device:GPU:2 with 29259 MB memory: -> device: 2, name: Tesla V100S-PCIE-32GB, pci bus id: 0000:b3:00.0, compute capability: 7.0
2023-02-03 14:03:08.824248: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1532] Created device /job:localhost/replica:0/task:0/device:GPU:3 with 29259 MB memory: -> device: 3, name: Tesla V100S-PCIE-32GB, pci bus id: 0000:b6:00.0, compute capability: 7.0
2023-02-03 14:03:08.824537: I tensorflow/core/common_runtime/process_util.cc:146] Creating new thread pool with default inter op setting: 2. Tune using inter_op_parallelism_threads for best performance.
2023-02-03 14:03:08.869981: I tensorflow/compiler/mlir/mlir_graph_optimization_pass.cc:354] MLIR V1 optimization pass is not enabled
INVALID_ARGUMENT: Tensor descrpt_attr/rcut:0, specified in either feed_devices or fetch_devices was not found in the Graph
ERROR: DeePMD-kit Error: TensorFlow Error: INVALID_ARGUMENT: Tensor descrpt_attr/rcut:0, specified in either feed_devices or fetch_devices was not found in the Graph (/home/conda/feedstock_root/build_artifacts/libdeepmd_1663923207577/work/source/lmp/pair_deepmd.cpp:840)
Last command: pair_style deepmd Cu-dpgen-model.pb
std-bcc.zip

[njzjz]

Hi, if you have the same situation as #1934, you could run dp convert-from 0.12 in v2.1.5.