{"record":{"id":"050ce42bc4203af9","repo":"tensorflow/models","slug":"s-does-not-match-any-files-050ce4","errorCode":null,"errorMessage":"%s does not match any files.","messagePattern":"(.+?) does not match any files\\.","errorType":"validation","errorClass":"ValueError","httpStatus":null,"severity":"error","filePath":"official/legacy/bert/input_pipeline.py","lineNumber":89,"sourceCode":"          tf.io.FixedLenFeature([seq_length], tf.int64),\n      'segment_ids':\n          tf.io.FixedLenFeature([seq_length], tf.int64),\n      'masked_lm_positions':\n          tf.io.FixedLenFeature([max_predictions_per_seq], tf.int64),\n      'masked_lm_ids':\n          tf.io.FixedLenFeature([max_predictions_per_seq], tf.int64),\n      'masked_lm_weights':\n          tf.io.FixedLenFeature([max_predictions_per_seq], tf.float32),\n  }\n  if use_next_sentence_label:\n    name_to_features['next_sentence_labels'] = tf.io.FixedLenFeature([1],\n                                                                     tf.int64)\n  if use_position_id:\n    name_to_features['position_ids'] = tf.io.FixedLenFeature([seq_length],\n                                                             tf.int64)\n  for input_pattern in input_patterns:\n    if not tf.io.gfile.glob(input_pattern):\n      raise ValueError('%s does not match any files.' % input_pattern)\n\n  dataset = tf.data.Dataset.list_files(input_patterns, shuffle=is_training)\n\n  if input_pipeline_context and input_pipeline_context.num_input_pipelines > 1:\n    dataset = dataset.shard(input_pipeline_context.num_input_pipelines,\n                            input_pipeline_context.input_pipeline_id)\n  if is_training:\n    dataset = dataset.repeat()\n\n    # We set shuffle buffer to exactly match total number of\n    # training files to ensure that training data is well shuffled.\n    input_files = []\n    for input_pattern in input_patterns:\n      input_files.extend(tf.io.gfile.glob(input_pattern))\n    dataset = dataset.shuffle(len(input_files))\n\n  # In parallel, create tf record dataset for each train files.\n  # cycle_length = 8 means that up to 8 files will be read and deserialized in","sourceCodeStart":71,"sourceCodeEnd":107,"githubUrl":"https://github.com/tensorflow/models/blob/e006f5f0d534913e49c1f1dae87364039fa607e2/official/legacy/bert/input_pipeline.py#L71-L107","documentation":"Error \"%s does not match any files.\" thrown in tensorflow/models.","triggerScenarios":"Thrown at official/legacy/bert/input_pipeline.py:89 when the library encounters an invalid state.","commonSituations":"See trigger scenarios.","solutions":[],"exampleFix":null,"handlingStrategy":null,"validationCode":null,"typeGuard":null,"tryCatchPattern":null,"preventionTips":[],"tags":[],"backgroundTag":null,"analyzedSha":"e006f5f0d534913e49c1f1dae87364039fa607e2","analyzedAt":"2026-08-24T14:09:15.576Z","schemaVersion":2},"datasetVersion":"2026-08-24T17:17:21.512Z"}