|---| | [ View source on GitHub](https://github.com/tensorflow/tflite-support/blob/v0.4.4/tensorflow_lite_support/metadata/python/metadata_writers/metadata_info.py#L703-L817) | A container for the input tensor metadata information of Bert models. #### View aliases **Main aliases** [`tflite_support.metadata_writers.audio_classifier.metadata_info.BertInputTensorsMd`](https://www.tensorflow.org/lite/api_docs/python/tflite_support/metadata_writers/metadata_info/BertInputTensorsMd), [`tflite_support.metadata_writers.audio_classifier.metadata_writer.metadata_info.BertInputTensorsMd`](https://www.tensorflow.org/lite/api_docs/python/tflite_support/metadata_writers/metadata_info/BertInputTensorsMd), [`tflite_support.metadata_writers.bert_nl_classifier.metadata_info.BertInputTensorsMd`](https://www.tensorflow.org/lite/api_docs/python/tflite_support/metadata_writers/metadata_info/BertInputTensorsMd), [`tflite_support.metadata_writers.bert_nl_classifier.metadata_writer.metadata_info.BertInputTensorsMd`](https://www.tensorflow.org/lite/api_docs/python/tflite_support/metadata_writers/metadata_info/BertInputTensorsMd), [`tflite_support.metadata_writers.image_classifier.metadata_info.BertInputTensorsMd`](https://www.tensorflow.org/lite/api_docs/python/tflite_support/metadata_writers/metadata_info/BertInputTensorsMd), [`tflite_support.metadata_writers.image_classifier.metadata_writer.metadata_info.BertInputTensorsMd`](https://www.tensorflow.org/lite/api_docs/python/tflite_support/metadata_writers/metadata_info/BertInputTensorsMd), [`tflite_support.metadata_writers.image_segmenter.metadata_info.BertInputTensorsMd`](https://www.tensorflow.org/lite/api_docs/python/tflite_support/metadata_writers/metadata_info/BertInputTensorsMd), [`tflite_support.metadata_writers.image_segmenter.metadata_writer.metadata_info.BertInputTensorsMd`](https://www.tensorflow.org/lite/api_docs/python/tflite_support/metadata_writers/metadata_info/BertInputTensorsMd), [`tflite_support.metadata_writers.nl_classifier.metadata_info.BertInputTensorsMd`](https://www.tensorflow.org/lite/api_docs/python/tflite_support/metadata_writers/metadata_info/BertInputTensorsMd), [`tflite_support.metadata_writers.nl_classifier.metadata_writer.metadata_info.BertInputTensorsMd`](https://www.tensorflow.org/lite/api_docs/python/tflite_support/metadata_writers/metadata_info/BertInputTensorsMd), [`tflite_support.metadata_writers.object_detector.metadata_info.BertInputTensorsMd`](https://www.tensorflow.org/lite/api_docs/python/tflite_support/metadata_writers/metadata_info/BertInputTensorsMd), [`tflite_support.metadata_writers.object_detector.metadata_writer.metadata_info.BertInputTensorsMd`](https://www.tensorflow.org/lite/api_docs/python/tflite_support/metadata_writers/metadata_info/BertInputTensorsMd)
tflite_support.metadata_writers.metadata_info.BertInputTensorsMd( model_buffer: bytearray, ids_name: str, mask_name: str, segment_name: str, ids_md: Optional[https://developers.google.com/edge/api/tflite/python/tflite_support/metadata_writers/metadata_info/TensorMd] = None, mask_md: Optional[https://developers.google.com/edge/api/tflite/python/tflite_support/metadata_writers/metadata_info/TensorMd] = None, segment_ids_md: Optional[https://developers.google.com/edge/api/tflite/python/tflite_support/metadata_writers/metadata_info/TensorMd] = None, tokenizer_md: Union[None, https://developers.google.com/edge/api/tflite/python/tflite_support/metadata_writers/metadata_info/BertTokenizerMd, https://developers.google.com/edge/api/tflite/python/tflite_support/metadata_writers/metadata_info/SentencePieceTokenizerMd] = None )


| ## Args || |---|---| | `model_buffer` | valid buffer of the model file. | | `ids_name` | name of the ids tensor, which represents the tokenized ids of the input text. | | `mask_name` | name of the mask tensor, which represents the mask with 1 for real tokens and 0 for padding tokens. | | `segment_name` | name of the segment ids tensor, where `0` stands for the first sequence, and `1` stands for the second sequence if exists. | | `ids_md` | input ids tensor informaton. | | `mask_md` | input mask tensor informaton. | | `segment_ids_md` | input segment tensor informaton. | | `tokenizer_md` | information of the tokenizer used to process the input string, if any. Supported tokenziers are: `BertTokenizer` [1](https://github.com/tensorflow/tflite-support/blob/b80289c4cd1224d0e1836c7654e82f070f9eefaa/tensorflow_lite_support/metadata/metadata_schema.fbs#L436) and `SentencePieceTokenizer` [2](https://github.com/tensorflow/tflite-support/blob/b80289c4cd1224d0e1836c7654e82f070f9eefaa/tensorflow_lite_support/metadata/metadata_schema.fbs#L473). If the tokenizer is `RegexTokenizer` [3](https://github.com/tensorflow/tflite-support/blob/b80289c4cd1224d0e1836c7654e82f070f9eefaa/tensorflow_lite_support/metadata/metadata_schema.fbs#L475), refer to [`nl_classifier.MetadataWriter`](https://developers.google.com/edge/api/tflite/python/tflite_support/metadata_writers/nl_classifier/MetadataWriter).

|
## Methods ### `create_input_process_unit_metadata` [View source](https://github.com/tensorflow/tflite-support/blob/v0.4.4/tensorflow_lite_support/metadata/python/metadata_writers/metadata_info.py#L803-L809) create_input_process_unit_metadata() -> List[https://developers.google.com/edge/api/tflite/python/tflite_support/metadata_schema_py_generated/ProcessUnitT] Creates the input process unit metadata. ### `create_input_tesnor_metadata` [View source](https://github.com/tensorflow/tflite-support/blob/v0.4.4/tensorflow_lite_support/metadata/python/metadata_writers/metadata_info.py#L792-L801) create_input_tesnor_metadata() -> List[https://developers.google.com/edge/api/tflite/python/tflite_support/metadata_schema_py_generated/TensorMetadataT] Creates the input metadata for the three input tesnors. ### `get_tokenizer_associated_files` [View source](https://github.com/tensorflow/tflite-support/blob/v0.4.4/tensorflow_lite_support/metadata/python/metadata_writers/metadata_info.py#L811-L817) get_tokenizer_associated_files() -> List[str] Gets the associated files that are packed in the tokenizer.