np.object was a deprecated alias for the builtin object. To avoid this error in existing code, use object by itself. Doing this will not modify any behavior and is safe.AttributeError Traceback (most recent call last)
Cell In[98], line 2
1 print(âPreparing Training and Testing sets to TRAIN the MODELâ)
----> 2 tf_train_set = model.prepare_tf_dataset(
3 tokenized_inputs[âtrainâ],
4 shuffle=True,
5 batch_size=16,
6 collate_fn=data_collator,
7 )
9 tf_test_set = model.prepare_tf_dataset(
10 tokenized_inputs[âtestâ],
11 shuffle=False,
12 batch_size=16,
13 collate_fn=data_collator,
14 )
File /opt/conda/lib/python3.10/site-packages/transformers/modeling_tf_utils.py:1488, in TFPreTrainedModel.prepare_tf_dataset(self, dataset, batch_size, shuffle, tokenizer, collate_fn, collate_fn_args, drop_remainder, prefetch)
1486 if drop_remainder is None:
1487 drop_remainder = shuffle
â 1488 tf_dataset = dataset.to_tf_dataset(
1489 columns=feature_cols,
1490 label_cols=label_cols,
1491 batch_size=batch_size,
1492 shuffle=shuffle,
1493 drop_remainder=drop_remainder,
1494 collate_fn=collate_fn,
1495 collate_fn_args=collate_fn_args,
1496 prefetch=prefetch,
1497 )
1498 return tf_dataset
File /opt/conda/lib/python3.10/site-packages/datasets/arrow_dataset.py:381, in TensorflowDatasetMixin.to_tf_dataset(self, columns, batch_size, shuffle, collate_fn, drop_remainder, collate_fn_args, label_cols, dummy_labels, prefetch)
378 retained_columns = [key for key in self.features.keys() if key in cols_to_retain]
379 dataset = self.with_format(ânumpyâ, columns=retained_columns)
â 381 columns_to_dtypes, output_signature = self._get_output_signature(
382 dataset, collate_fn, collate_fn_args, batch_size=batch_size if drop_remainder else None
383 )
384 all_columns = list(columns_to_dtypes.keys())
385 all_dtypes = list(columns_to_dtypes.values())
File /opt/conda/lib/python3.10/site-packages/datasets/arrow_dataset.py:244, in TensorflowDatasetMixin._get_output_signature(dataset, collate_fn, collate_fn_args, batch_size)
242 raise ValueError(âUnable to get the output signature because the dataset is empty.â)
243 test_batch_size = min(len(dataset), 4)
â 244 test_batch = dataset[:test_batch_size]
245 test_batch = [{key: value[i] for key, value in test_batch.items()} for i in range(test_batch_size)]
246 test_batch = collate_fn(test_batch, **collate_fn_args)
File /opt/conda/lib/python3.10/site-packages/datasets/arrow_dataset.py:1764, in Dataset.getitem(self, key)
1762 def getitem(self, key): # noqa: F811
1763 âââCan be used to index columns (by string names) or rows (by integer index or iterable of indices or bools).âââ
â 1764 return self._getitem(
1765 key,
1766 )
File /opt/conda/lib/python3.10/site-packages/datasets/arrow_dataset.py:1749, in Dataset._getitem(self, key, decoded, **kwargs)
1747 formatter = get_formatter(format_type, features=self.features, decoded=decoded, **format_kwargs)
1748 pa_subtable = query_table(self._data, key, indices=self._indices if self._indices is not None else None)
â 1749 formatted_output = format_table(
1750 pa_subtable, key, formatter=formatter, format_columns=format_columns, output_all_columns=output_all_columns
1751 )
1752 return formatted_output
File /opt/conda/lib/python3.10/site-packages/datasets/formatting/formatting.py:540, in format_table(table, key, formatter, format_columns, output_all_columns)
538 else:
539 pa_table_to_format = pa_table.drop(col for col in pa_table.column_names if col not in format_columns)
â 540 formatted_output = formatter(pa_table_to_format, query_type=query_type)
541 if output_all_columns:
542 if isinstance(formatted_output, MutableMapping):
File /opt/conda/lib/python3.10/site-packages/datasets/formatting/formatting.py:285, in Formatter.call(self, pa_table, query_type)
283 return self.format_column(pa_table)
284 elif query_type == âbatchâ:
â 285 return self.format_batch(pa_table)
File /opt/conda/lib/python3.10/site-packages/datasets/formatting/formatting.py:346, in NumpyFormatter.format_batch(self, pa_table)
345 def format_batch(self, pa_table: pa.Table) â dict:
â 346 batch = self.numpy_arrow_extractor(**self.np_array_kwargs).extract_batch(pa_table)
347 if self.decoded:
348 batch = self.python_features_decoder.decode_batch(batch)
File /opt/conda/lib/python3.10/site-packages/datasets/formatting/formatting.py:160, in NumpyArrowExtractor.extract_batch(self, pa_table)
159 def extract_batch(self, pa_table: pa.Table) â dict:
â 160 return {col: self._arrow_array_to_numpy(pa_table[col]) for col in pa_table.column_names}
File /opt/conda/lib/python3.10/site-packages/datasets/formatting/formatting.py:160, in (.0)
159 def extract_batch(self, pa_table: pa.Table) â dict:
â 160 return {col: self._arrow_array_to_numpy(pa_table[col]) for col in pa_table.column_names}
File /opt/conda/lib/python3.10/site-packages/datasets/formatting/formatting.py:196, in NumpyArrowExtractor._arrow_array_to_numpy(self, pa_array)
194 array: List = pa_array.to_numpy(zero_copy_only=zero_copy_only).tolist()
195 if len(array) > 0:
â 196 if any(
197 (isinstance(x, np.ndarray) and (x.dtype == np.object or x.shape != array[0].shape))
198 or (isinstance(x, float) and np.isnan(x))
199 for x in array
200 ):
201 return np.array(array, copy=False, **{**self.np_array_kwargs, âdtypeâ: np.object})
202 return np.array(array, copy=False, **self.np_array_kwargs)
File /opt/conda/lib/python3.10/site-packages/datasets/formatting/formatting.py:197, in (.0)
194 array: List = pa_array.to_numpy(zero_copy_only=zero_copy_only).tolist()
195 if len(array) > 0:
196 if any(
â 197 (isinstance(x, np.ndarray) and (x.dtype == np.object or x.shape != array[0].shape))
198 or (isinstance(x, float) and np.isnan(x))
199 for x in array
200 ):
201 return np.array(array, copy=False, **{**self.np_array_kwargs, âdtypeâ: np.object})
202 return np.array(array, copy=False, **self.np_array_kwargs)
File /opt/conda/lib/python3.10/site-packages/numpy/init.py:305, in getattr(attr)
300 warnings.warn(
301 f"In the future np.{attr} will be defined as the "
302 âcorresponding NumPy scalar.â, FutureWarning, stacklevel=2)
304 if attr in former_attrs:
â 305 raise AttributeError(former_attrs[attr])
307 # Importing Tester requires importing all of UnitTest which is not a
308 # cheap import Since it is mainly used in test suits, we lazy import it
309 # here to save on the order of 10 ms of import time for most users
310 #
311 # The previous way Tester was imported also had a side effect of adding
312 # the full numpy.testing namespace
313 if attr == âtestingâ:
AttributeError: module ânumpyâ has no attribute âobjectâ.
np.object was a deprecated alias for the builtin object. To avoid this error in existing code, use object by itself. Doing this will not modify any behavior and is safe.
The aliases was originally deprecated in NumPy 1.20; for more details and guidance see the original release note at:
NumPy 1.20.0 Release Notes â NumPy v2.0.dev0 Manual
Thank you very much for your response. Could you provide the example of code snippet about how should I change
np.object
on
object
I ma also getting same error, so i am asking experts for an answer.
But from what i understand, the error is from numpy as it has deprecated np.object but the transformer library is not updated. You can try downgrading numpy to version 1.20.0 or below. That should fix your problem temporarily.
I tried downgrading but it did not provide any solution for me. In my opinion, the problem also could be with Kaggle environment because this problem I encountered working with Kaggle environment
i was working on kaggle as well.
You could try running your notebook on colab.
@OleksiiVNTU In kaggle what worked for me is using the Kaggle Notebook that I have created several months back, as it had the old environment code ran perfectly.
This is my Notebook. You can copy edit and remove my code and add yours to Run.
In this notebook I am having problem with GPT2. If you know the fix thatâd be help too.