RuntimeError: Did not find valid system

[ayda1]

I need help please

---

#!/bin/bash
#SBATCH -A HfA22_EAIFR
#SBATCH -p m100_usr_prod
#SBATCH --time 24:00:00 # format: HH:MM:SS
#SBATCH -N 1 # 1 node
#SBATCH --ntasks-per-node=16 # 8 tasks out of 128
#SBATCH --gres=gpu:4 # 1 gpus per node out of 4
#SBATCH --mem=7100 # memory per node out of 246000MB
#SBATCH --job-name=watdim-e0
#SBATCH --mail-type=ALL
#SBATCH --mail-user=[email protected]

module load profile/deeplrn
module load autoload deepmd
module load autoload cuda

export OMP_NUM_THREADS=3
export TF_INTRA_OP_PARALLELISM_THREADS=3
export TF_INTER_OP_PARALLELISM_THREADS=2

CUDA_VISIBLE_DEVICES=0,1 horovodrun -np 1
dp train --mpi-log=workers input.json

#dp train input.json
dp freeze -o graph.pb
dp test

ERROR **********************************
input_checkpoint = checkpoint.model_checkpoint_path
AttributeError: 'NoneType' object has no attribute 'model_checkpoint_path'
2022-08-18 11:57:24.642552: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcudart.so.11.0
WARNING:tensorflow:From /cineca/prod/opt/libraries/open-ce/1.1.3/none/opence-conda-env-py3.8-cuda-openmpi-11.0/opence/lib/python3.8/site-packages/tensorflow/python/compat/v2_compat.py:96: 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
Traceback (most recent call last):
File "/cineca/prod/opt/applications/deepmd/2.0/cuda--11.0/deepmd/bin/dp", line 8, in
sys.exit(main())
File "/m100/prod/opt/applications/deepmd/2.0/cuda--11.0/deepmd/lib/python3.8/site-packages/deepmd/entrypoints/main.py", line 443, in main
test(**dict_args)
File "/m100/prod/opt/applications/deepmd/2.0/cuda--11.0/deepmd/lib/python3.8/site-packages/deepmd/entrypoints/test.py", line 62, in test
raise RuntimeError("Did not find valid system")
RuntimeError: Did not find valid system

[PabloPiaggi]

Is this question connected to the tutorial? Which input files are you using and which hands-on sessions are you referring to?

The second error means that you are running dp test in a folder where there are no valid systems.

I am not sure about the first error. Do you have valid checkpoint files in the folder?