A problem occurred in DP predicting after the version upgrade

[zhao-w-en]

I'm sorry to bother you so often. Recently I've update DeePMD-kit to V2.0.3 and meet some questions in DP predicting which have never met in V2.0.0.
I would like to know if there are any changes or optimizations to the forecast commands after the version upgrade?
My code are list below:

ss = dpdata.LabeledSystem('./OUTCAR')
dp = deepmd.infer.DeepPot('frozen_model_new.pb')
ss.to_vasp_poscar('POSCAR',frame_idx = i)
sys = dpdata.System('POSCAR')
labeled_sys = sys.predict(dp)

An error occurred when the last command was executed.

Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "/home/zhaow/.local/lib/python3.9/site-packages/dpdata/system.py", line 988, in predict
    e, f, v = dp.eval(coord, cell, atype)
  File "/home/zhaow/anaconda3/envs/deepmd/lib/python3.9/site-packages/deepmd/infer/deep_pot.py", line 246, in eval
    e, f, v = self.auto_batch_size.execute_all(self._eval_inner, numb_test, natoms,
  File "/home/zhaow/anaconda3/envs/deepmd/lib/python3.9/site-packages/deepmd/utils/batch_size.py", line 116, in execute_all
    n_batch, result = self.execute(execute_with_batch_size, index, natoms)
  File "/home/zhaow/anaconda3/envs/deepmd/lib/python3.9/site-packages/deepmd/utils/batch_size.py", line 66, in execute
    n_batch, result = callable(max(self.current_batch_size // natoms, 1), start_index)
  File "/home/zhaow/anaconda3/envs/deepmd/lib/python3.9/site-packages/deepmd/utils/batch_size.py", line 108, in execute_with_batch_size
    return (end_index - start_index), callable(
  File "/home/zhaow/anaconda3/envs/deepmd/lib/python3.9/site-packages/deepmd/infer/deep_pot.py", line 278, in _eval_inner
    cells = np.array(cells).reshape([nframes, 9])
ValueError: cannot reshape array of size 1 into shape (1,9)

[njzjz]

We fixed it in #207. Please upgrade dpdata.

[zhao-w-en]

thanks for your help!