ERROR on proc 0: DeePMD-kit C API Error: DeePMD-kit Error: TensorFlow Error: NOT_FOUND: graph-compress.pb; No such file or directory

[chb-deep]

conda create deepmd-kit=*=cpu libdeepmd==*cpu lammps -c https://conda.deepmodeling.com -n deepmd -y
I installed deepmd-kit and lammps with the above commands,but I get an error when using lmp
Before running the task, the deepmd environment has been loaded. "conda activate deepmd"
How can I solve this problem? Can anyone help me?

[shuoxing@node01 02.lmp]$ conda activate deepmd
(deepmd) [shuoxing@node01 02.lmp]$ lmp -in in.lammps
LAMMPS (23 Jun 2022 - Update 4)
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 /home/shuoxing/.conda/envs/deepmd/lib/deepmd_lmp
Reading data file ...
triclinic box = (0 0 0) to (10.114259 10.263124 10.216793) with tilt (0.036749877 0.13833062 -0.056322169)
1 by 1 by 1 MPI processor grid
reading atoms ...
5 atoms
read_data CPU = 0.000 seconds
DeePMD-kit WARNING: Environmental variable TF_INTRA_OP_PARALLELISM_THREADS is not set. Tune TF_INTRA_OP_PARALLELISM_THREADS for the best performance. See https://deepmd.rtfd.io/parallelism/ for more information.
DeePMD-kit WARNING: Environmental variable TF_INTER_OP_PARALLELISM_THREADS is not set. Tune TF_INTER_OP_PARALLELISM_THREADS for the best performance. See https://deepmd.rtfd.io/parallelism/ for more information.
DeePMD-kit WARNING: Environmental variable OMP_NUM_THREADS is not set. Tune OMP_NUM_THREADS for the best performance. See https://deepmd.rtfd.io/parallelism/ for more information.
Summary of lammps deepmd module ...

Info of deepmd-kit:
installed to: /home/shuoxing/.conda/envs/deepmd
source: v2.2.2
source branch: HEAD
source commit: 92ca097
source commit at: 2023-05-24 13:45:03 +0800
surpport model ver.:1.1
build variant: cpu
build with tf inc: /home/shuoxing/.conda/envs/deepmd/include;/home/shuoxing/.conda/envs/deepmd/include
build with tf lib: /home/shuoxing/.conda/envs/deepmd/lib/libtensorflow_cc.so
set tf intra_op_parallelism_threads: 0
set tf inter_op_parallelism_threads: 0
Info of lammps module:
use deepmd-kit at: /home/shuoxing/.conda/envs/deepmdNOT_FOUND: graph-compress.pb; No such file or directory
ERROR on proc 0: DeePMD-kit C API Error: DeePMD-kit Error: TensorFlow Error: NOT_FOUND: graph-compress.pb; No such file or directory (/home/conda/feedstock_root/build_artifacts/libdeepmd_1689710008919/work/source/lmp/pair_deepmd.cpp:838)
Last command: pair_style deepmd graph-compress.pb
application called MPI_Abort(MPI_COMM_WORLD, 1) - process 0
[unset]: write_line error; fd=-1 buf=:cmd=abort exitcode=1
:
system msg for write_line failure : Bad file descriptor

in.lammps:

gas phase methane

units metal
boundary p p p
atom_style atomic

neighbor 1.0 bin
neigh_modify every 10 delay 0 check no

read_data conf.lmp
mass 1 1
mass 2 12

pair_style deepmd graph-compress.pb
pair_coeff * *

velocity all create 50.0 23456789
fix 1 all nvt temp 50.0 50.0 0.5
timestep 0.001

thermo_style custom step pe ke etotal temp press vol
thermo 100
dump 1 all custom 100 ch4.dump id type x y z

run 5000

log.lammps:
LAMMPS (23 Jun 2022 - Update 4)
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 /home/shuoxing/.conda/envs/deepmd/lib/deepmd_lmp

gas phase methane

units metal
boundary p p p
atom_style atomic

neighbor 1.0 bin
neigh_modify every 10 delay 0 check no

read_data conf.lmp
Reading data file ...
triclinic box = (0 0 0) to (10.114259 10.263124 10.216793) with tilt (0.036749877 0.13833062 -0.056322169)
1 by 1 by 1 MPI processor grid
reading atoms ...
5 atoms
read_data CPU = 0.000 seconds
mass 1 1
mass 2 12

pair_style deepmd graph-compress.pb
Summary of lammps deepmd module ...

Info of deepmd-kit:
installed to: /home/shuoxing/.conda/envs/deepmd
source: v2.2.2
source branch: HEAD
source commit: 92ca097
source commit at: 2023-05-24 13:45:03 +0800
surpport model ver.:1.1
build variant: cpu
build with tf inc: /home/shuoxing/.conda/envs/deepmd/include;/home/shuoxing/.conda/envs/deepmd/include
build with tf lib: /home/shuoxing/.conda/envs/deepmd/lib/libtensorflow_cc.so
set tf intra_op_parallelism_threads: 0
set tf inter_op_parallelism_threads: 0
Info of lammps module:
use deepmd-kit at: /home/shuoxing/.conda/envs/deepmdERROR on proc 0: DeePMD-kit C API Error: DeePMD-kit Error: TensorFlow Error: NOT_FOUND: graph-compress.pb; No such file or directory (/home/conda/feedstock_root/build_artifacts/libdeepmd_1689710008919/work/source/lmp/pair_deepmd.cpp:838)
Last command: pair_style deepmd graph-compress.pb

[njzjz]

I think the error message is clear enough.

[chb-deep]

I have fixed this issue, thank you for the answer

[hezs-LZJTU]

Hi, I also encountered this problem. How did you solve it?