- Sort Score
- Result 10 results
- Languages All
Results 1 - 3 of 3 for force_graph_mode_calibration (0.25 sec)
-
tensorflow/compiler/mlir/quantization/tensorflow/python/py_function_lib.py
def _run_graph_for_calibration( float_model_dir: str, signature_keys: Sequence[str], tags: Collection[str], representative_dataset: rd.RepresentativeDatasetOrMapping, force_graph_mode_calibration: bool, ) -> None: """Runs the graph for calibration using representative datasets. Args: float_model_dir: Path to the model to calibrate.
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Fri May 31 05:32:11 UTC 2024 - 27.4K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/tensorflow/python/quantize_model.py
) # Set `force_graph_mode_calibration` to True to avoid skipping op execution, # which are not connected to return ops, during calibration execution. # TODO: b/335031954 - Bring back support to run calibration in Eager mode. logging.debug( 'Setting `force_graph_mode_calibration = True` to ensure the calibration' ' mode is executed properly.' )
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Fri May 17 03:36:50 UTC 2024 - 34.2K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/tensorflow/python/quantize_model.cc
saved_model_path, tags, signature_def_map); py_function_library.RunCalibration( calibration_saved_model_dir, signature_keys, tags, quantization_options.force_graph_mode_calibration(), representative_dataset_file_map_serialized); } if (absl::Status status = AddCalibrationStatistics( *module_ref, calibration_data_dir,
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Fri May 17 03:36:50 UTC 2024 - 23.8K bytes - Viewed (0)