{"record":{"id":"eb111d230baf67e2","repo":"tensorflow/models","slug":"dataset-dataset-name-r-is-missing-split-folder","errorCode":null,"errorMessage":"Dataset {dataset_name!r} is missing split folder: {split_input_dir}","messagePattern":"Dataset (.+?) is missing split folder: (.+?)","errorType":"exception","errorClass":"FileNotFoundError","httpStatus":null,"severity":"error","filePath":"official/projects/waste_identification_ml/data_generation/auto_labeler_pipeline/segmentation.py","lineNumber":591,"sourceCode":"      classifier_output_dir: Path to the classifier dataset root.\n      split_names: Split subfolder names to iterate, e.g. ``('train', 'val')``.\n      processor: SAM3 processor instance.\n      detection_config: Validated detection thresholds for this prompt.\n      prompt: Text prompt for detection.\n      crop_variants: Sequence of crop variant names to save.\n      max_cpu_workers: Size of the CPU thread pool.\n      queue_maxsize: Maximum in-flight CPU jobs before the GPU loop blocks.\n\n  Raises:\n      FileNotFoundError: If a configured split is missing.\n  \"\"\"\n  print(f\"\\n=== Dataset: {dataset_name} ===\")\n  dataset_start = time.perf_counter()\n\n  for split_name in split_names:\n    split_input_dir = os.path.join(input_dir, split_name)\n    if not os.path.isdir(split_input_dir):\n      raise FileNotFoundError(\n          f\"Dataset {dataset_name!r} is missing split folder: {split_input_dir}\"\n      )\n\n    class_folder = os.path.join(classifier_output_dir, split_name, dataset_name)\n    log_label = f\"{dataset_name}/{split_name}\"\n\n    process_split(\n        split_input_dir,\n        class_folder,\n        log_label,\n        processor,\n        detection_config,\n        prompt,\n        crop_variants,\n        max_cpu_workers,\n        queue_maxsize,\n    )\n","sourceCodeStart":573,"sourceCodeEnd":609,"githubUrl":"https://github.com/tensorflow/models/blob/e006f5f0d534913e49c1f1dae87364039fa607e2/official/projects/waste_identification_ml/data_generation/auto_labeler_pipeline/segmentation.py#L573-L609","documentation":"Error \"Dataset {dataset_name!r} is missing split folder: {split_input_dir}\" thrown in tensorflow/models.","triggerScenarios":"Thrown at official/projects/waste_identification_ml/data_generation/auto_labeler_pipeline/segmentation.py:591 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"}