tfx-bsl

import tensorflow as tf import pyarrow as pa from tfx_bsl.coders.example_coder import ExampleToRecordBatchDecoder, RecordBatchToExamplesEncoder # 1. Create a list of serialized tf.train.Example examples_list = [ tf.train.Example(features=tf.train.Features(feature={ 'feature1': tf.train.Feature(int64_list=tf.train.Int64List(value=[1, 2])), 'feature2': tf.train.Feature(float_list=tf.train.FloatList(value=[1.0, 2.0])) })).SerializeToString(), tf.train.Example(features=tf.train.Features(feature={ 'feature1': tf.train.Feature(int64_list=tf.train.Int64List(value=[3])), 'feature2': tf.train.Feature(float_list=tf.train.FloatList(value=[3.0])) })).SerializeToString() ] # 2. Decode TF.Examples to an Apache Arrow RecordBatch decoder = ExampleToRecordBatchDecoder() record_batch = decoder.decode(examples_list) print(f"\nDecoded RecordBatch schema:\n{record_batch.schema}") print(f"Decoded RecordBatch content:\n{record_batch}") # 3. Encode the Apache Arrow RecordBatch back to TF.Examples encoder = RecordBatchToExamplesEncoder(record_batch.schema) encoded_examples_iterator = encoder.encode(record_batch) encoded_examples_list = list(encoded_examples_iterator) print(f"\nRe-encoded examples (first one):\n{tf.train.Example().FromString(encoded_examples_list[0])}") # Verify round-trip (simplified check) assert len(examples_list) == len(encoded_examples_list) print("\nSuccessfully decoded to Arrow and re-encoded to TF.Example.")