TypeError**: Couldn't cast array of type int64 to Sequence #4905

Laxmi530 · 2022-08-27T14:09:31Z

Laxmi530
Aug 27, 2022

Hai,
I am trying to finetune LayoutLMV2 model for document image classification but while mapping the dataset I am getting error. The dataset contain two column one image_file which is str data type another is Label which is numpy int64 data type. below is the code which I tried. Can someone please help me in fixing the error.

dataset = Dataset.from_pandas(df_copy)
dataset

Dataset({
    features: ['Image_File_Path', 'Label'],
    num_rows: 12
})

path = './Image FIle/'

features = Features({
    'image': Array3D(dtype="int64", shape=(3, 224, 224)),
    'input_ids': Sequence(feature=Value(dtype='int64')),
    'attention_mask': Sequence(Value(dtype='int64')),
    'token_type_ids': Sequence(Value(dtype='int64')),
    'bbox': Array2D(dtype="int64", shape=(512, 4)),
    'labels': Sequence(Value(dtype='int64')),
})

def preprocess_data(examples):
  # take a batch of images
  images = [Image.open(os.path.join(path, file)).convert("RGB") for file in examples['Image_File_Path']]
  encoded_inputs = processor(images, padding="max_length", truncation=True)
  # add labels
  encoded_inputs["labels"] = [label2id[label] for label in examples["Label"]]
  return encoded_inputs

encoded_dataset = dataset.map(preprocess_data, remove_columns=dataset.column_names, features=features, batched=True, batch_size=2)

this is the error

**TypeError** Traceback (most recent call last) **d:\Working\Trans_LayoutLMV2_Doc_Classification.ipynb Cell 24** in <cell line: 21>**()** 
[18]encoded_inputs["labels"] = [label2id[label] for label in examples["Label"]] 
[19]return encoded_inputs **---> 
[21]encoded_dataset = dataset.map(preprocess_data, remove_columns=dataset.column_names, features=features, batched=True, batch_size=2) File **~\AppData\Roaming\Python\Python310\site-packages\datasets\arrow_dataset.py:2387**, in Dataset.map**(self, function, with_indices, with_rank, input_columns, batched, batch_size, drop_last_batch, remove_columns, keep_in_memory, load_from_cache_file, cache_file_name, writer_batch_size, features, disable_nullable, fn_kwargs, num_proc, suffix_template, new_fingerprint, desc)** 
2384 disable_tqdm = not logging.is_progress_bar_enabled() 
2386 if num_proc is None or num_proc == 1: **-> 
2387** return self._map_single( 
2388 function=function, 
2389 with_indices=with_indices, 
2390 with_rank=with_rank, 
2391 input_columns=input_columns, 
2392 batched=batched, 
2393 batch_size=batch_size, 
2394 drop_last_batch=drop_last_batch, 
2395 remove_columns=remove_columns, 
2396 keep_in_memory=keep_in_memory, 
2397 load_from_cache_file=load_from_cache_file, 
2398 cache_file_name=cache_file_name, 
2399 writer_batch_size=writer_batch_size, 
2400 features=features, 
2401 disable_nullable=disable_nullable, 
2402 fn_kwargs=fn_kwargs, 
2403 new_fingerprint=new_fingerprint, 
2404 disable_tqdm=disable_tqdm, 
2405 desc=desc, 
2406 ) 
2407 else: 
2409 def format_cache_file_name(cache_file_name, rank): File **~\AppData\Roaming\Python\Python310\site-packages\datasets\arrow_dataset.py:557**, in transmit_tasks.<locals>.wrapper**(*args, **kwargs)** 555 self: "Dataset" = kwargs.pop("self")

...

**TypeError**: Couldn't cast array of type int64 to Sequence(feature=Value(dtype='int64', id=None), length=-1, id=None)