I’m trying to export my fine-tuned-bert-classifier torch model into ONNX format using optimum and then eventually want ro run it through a pipeline for sequence classification task.
Here is the code:
from optimum.onnxruntime import ORTModelForSequenceClassification, ORTOptimizer
from optimum.onnxruntime.configuration import OptimizationConfig
from optimum.pipelines import pipeline
# path_to_fine_tuned_model contains the path to the folder containing the pytorch_model.bin file
optimizer = ORTOptimizer.from_pretrained(path_to_fine_tuned_model, feature="sequence-classification")
optimization_config = OptimizationConfig(optimization_level=2)
optimizer.export(
onnx_model_path='../models/bert_model_opt.onnx',
onnx_optimized_model_output_path='../models/bert_model_optimized.onnx',
optimization_config=optimization_config,
)
However, this operation throws ValueError: Unable to generate dummy inputs for the model. Please provide a tokenizer or a preprocessor.
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
Input In [35], in <cell line: 1>()
----> 1 optimizer.export(
2 onnx_model_path='../models/bert_model_opt.onnx',
3 onnx_optimized_model_output_path='../models/bert_model_optimized.onnx',
4 optimization_config=optimization_config,
5 )
File /opt/conda/envs/conda_ml/lib/python3.9/site-packages/optimum/onnxruntime/optimization.py:123, in ORTOptimizer.export(self, onnx_model_path, onnx_optimized_model_output_path, optimization_config, use_external_data_format)
121 # Export the model if it has not already been exported to ONNX IR
122 if not onnx_model_path.exists():
--> 123 export(self.preprocessor, self.model, self._onnx_config, self.opset, onnx_model_path)
125 ORTConfigManager.check_supported_model_or_raise(self._model_type)
126 num_heads = getattr(self.model.config, ORTConfigManager.get_num_heads_name(self._model_type))
File /opt/conda/envs/conda_ml/lib/python3.9/site-packages/transformers/onnx/convert.py:336, in export(preprocessor, model, config, opset, output, tokenizer, device)
330 logger.warning(
331 f"Unsupported PyTorch version for this model. Minimum required is {config.torch_onnx_minimum_version},"
332 f" got: {torch_version}"
333 )
335 if is_torch_available() and issubclass(type(model), PreTrainedModel):
--> 336 return export_pytorch(preprocessor, model, config, opset, output, tokenizer=tokenizer, device=device)
337 elif is_tf_available() and issubclass(type(model), TFPreTrainedModel):
338 return export_tensorflow(preprocessor, model, config, opset, output, tokenizer=tokenizer)
File /opt/conda/envs/conda_ml/lib/python3.9/site-packages/transformers/onnx/convert.py:143, in export_pytorch(preprocessor, model, config, opset, output, tokenizer, device)
139 setattr(model.config, override_config_key, override_config_value)
141 # Ensure inputs match
142 # TODO: Check when exporting QA we provide "is_pair=True"
--> 143 model_inputs = config.generate_dummy_inputs(preprocessor, framework=TensorType.PYTORCH)
144 device = torch.device(device)
145 if device.type == "cuda" and torch.cuda.is_available():
File /opt/conda/envs/conda_ml/lib/python3.9/site-packages/transformers/onnx/config.py:347, in OnnxConfig.generate_dummy_inputs(self, preprocessor, batch_size, seq_length, num_choices, is_pair, framework, num_channels, image_width, image_height, tokenizer)
345 return dict(preprocessor(images=dummy_input, return_tensors=framework))
346 else:
--> 347 raise ValueError(
348 "Unable to generate dummy inputs for the model. Please provide a tokenizer or a preprocessor."
349 )
ValueError: Unable to generate dummy inputs for the model. Please provide a tokenizer or a preprocessor.
Any idea how to fix this? Thanks!
