TypeError: Cannot convert numpy.ndarray to numpy.ndarray

[TerenceChen95]

Hi, thanks for this amazing work! Here's a small question when I was tring to do predicting just like #2 (comment).
The environment I was using is python3.10.0, torch2.3.1. Maybe causes by some miscellaneous package version problem, I guess?

Traceback (most recent call last):
  File "load_model.py", line 16, in <module>
    output = model.forward_and_sample(
  File "esm\models\esm3.py", line 543, in forward_and_sample
    default_protein_tensor = ESMProteinTensor.empty(
  File "esm\sdk\api.py", line 199, in empty
    residue_annotations=encoding.get_default_residue_annotation_tokens(
  File "esm\utils\encoding.py", line 236, in get_default_residue_annotation_tokens
    * residue_annotation_tokenizer.pad_token_id
  File "esm\tokenization\residue_tokenizer.py", line 224, in pad_token_id
    return self.vocab_to_index[self.pad_token]
  File "D:\python3_10\lib\functools.py", line 970, in __get__
    val = self.func(instance)
  File "esm\tokenization\residue_tokenizer.py", line 66, in vocab_to_index
    return {token: token_id for token_id, token in enumerate(self.vocab)}
  File "D:\python3_10\lib\functools.py", line 970, in __get__
    val = self.func(instance)
  File "esm\tokenization\residue_tokenizer.py", line 61, in vocab
    annotation_tokens = [f"<ra:{id}>" for _, id in self._label2id.items()]
  File "D:\python3_10\lib\functools.py", line 970, in __get__
    val = self.func(instance)
  File "esm\tokenization\residue_tokenizer.py", line 52, in _label2id
    return {label: offset + i for i, label in enumerate(self._labels)}
  File "D:\python3_10\lib\functools.py", line 970, in __get__
    val = self.func(instance)
  File "esm\tokenization\residue_tokenizer.py", line 35, in _labels
    df = pd.read_csv(f)
  File "venv\lib\site-packages\pandas\io\parsers\readers.py", line 1026, in read_csv
    return _read(filepath_or_buffer, kwds)
  File "venv\lib\site-packages\pandas\io\parsers\readers.py", line 626, in _read
    return parser.read(nrows)
  File "venv\lib\site-packages\pandas\io\parsers\readers.py", line 1968, in read
    df = DataFrame(
  File "venv\lib\site-packages\pandas\core\frame.py", line 778, in __init__
    mgr = dict_to_mgr(data, index, columns, dtype=dtype, copy=copy, typ=manager)
  File "venv\lib\site-packages\pandas\core\internals\construction.py", line 443, in dict_to_mgr
    arrays = Series(data, index=columns, dtype=object)
  File "venv\lib\site-packages\pandas\core\series.py", line 490, in __init__
    index = ensure_index(index)
  File "venv\lib\site-packages\pandas\core\indexes\base.py", line 7647, in ensure_index
    return Index(index_like, copy=copy, tupleize_cols=False)
  File "venv\lib\site-packages\pandas\core\indexes\base.py", line 565, in __new__
    arr = sanitize_array(data, None, dtype=dtype, copy=copy)
  File "venv\lib\site-packages\pandas\core\construction.py", line 654, in sanitize_array
    subarr = maybe_convert_platform(data)
  File "venv\lib\site-packages\pandas\core\dtypes\cast.py", line 139, in maybe_convert_platform
    arr = lib.maybe_convert_objects(arr)
  File "lib.pyx", line 2538, in pandas._libs.lib.maybe_convert_objects
TypeError: Cannot convert numpy.ndarray to numpy.ndarray

[TerenceChen95]

I figure out the problem is using different version of pandas. Pandas2.2 causes for this problem and maybe version above 2.0, I guess. Rolling back to 1.5.0 works perfect for me.