Chap 8 notebook: ONNX TypeError: export() got an unexpected keyword argument 'use_external_data_format'
jeromemassot opened this issue · comments
Jerome MASSOT commented
Information
The problem arises in chapter:
- Introduction
- Text Classification
- Transformer Anatomy
- Multilingual Named Entity Recognition
- Text Generation
- Summarization
- Question Answering
- [x ] Making Transformers Efficient in Production
- Dealing with Few to No Labels
- Training Transformers from Scratch
- Future Directions
Describe the bug
TypeError: export() got an unexpected keyword argument 'use_external_data_format'
In the notebook from this repository, the same problem has generated a warning not a TypeError.
To Reproduce
Steps to reproduce the behavior:
- model_ckpt = "transformersbook/distilbert-base-uncased-distilled-clinc"
- onnx_model_path = Path("onnx/model.onnx")
- convert( ...
Expected behavior
Mayank Bhaskar commented
Facing the same issue, while executing convert()
from transformers.convert_graph_to_onnx import convert
model_ckpt = "transformersbook/distilbert-base-uncased-distilled-clinc"
onnx_model_path = Path("onnx/model.onnx")
convert(framework="pt", model=model_ckpt, tokenizer=tokenizer, output=onnx_model_path,
opset=12, pipeline_name="text-classification")
Added stacktrace
ONNX opset version set to: 12
Loading pipeline (model: transformersbook/distilbert-base-uncased-distilled-clinc, tokenizer: PreTrainedTokenizerFast(name_or_path='transformersbook/distilbert-base-uncased-distilled-clinc', vocab_size=30522, model_max_len=512, is_fast=True, padding_side='right', special_tokens={'unk_token': '[UNK]', 'sep_token': '[SEP]', 'pad_token': '[PAD]', 'cls_token': '[CLS]', 'mask_token': '[MASK]'}))
Using framework PyTorch: 1.12.1+cu113
Found input input_ids with shape: {0: 'batch', 1: 'sequence'}
Found input attention_mask with shape: {0: 'batch', 1: 'sequence'}
Found output output_0 with shape: {0: 'batch'}
Ensuring inputs are in correct order
head_mask is not present in the generated input list.
Generated inputs order: ['input_ids', 'attention_mask']
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
[<ipython-input-68-46e250e62185>](https://localhost:8080/#) in <module>
5 onnx_model_path = Path("onnx/model.onnx")
6 convert(framework="pt", model=model_ckpt, tokenizer=tokenizer, output=onnx_model_path,
----> 7 opset=12, pipeline_name="text-classification")
1 frames
[/usr/local/lib/python3.7/dist-packages/transformers/convert_graph_to_onnx.py](https://localhost:8080/#) in convert_pytorch(nlp, opset, output, use_external_format)
289 use_external_data_format=use_external_format,
290 enable_onnx_checker=True,
--> 291 opset_version=opset,
292 )
293
TypeError: export() got an unexpected keyword argument 'use_external_data_format'
Any workarounds?
Srinivas commented
I am encountering the same exact problem when running the chapter 8 notebook and with the same error message as in cataluna84 msg above while running convert().
Is there a fix or a workaround?