- Sort Score
- Result 10 results
- Languages All
Results 1 - 2 of 2 for executing_eagerly (0.23 sec)
-
tensorflow/compiler/mlir/quantization/tensorflow/python/representative_dataset.py
the set of expected input keys. """ # When running in graph mode (TF1), tf.Tensor types should be converted to # numpy ndarray types to be compatible with `make_tensor_proto`. if not context.executing_eagerly(): with session.Session() as sess: repr_ds = replace_tensors_by_numpy_ndarrays(repr_ds, sess) expected_input_keys = self.expected_input_key_map.get( signature_def_key, None )
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Fri Mar 22 22:55:22 UTC 2024 - 14.2K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/tensorflow/python/py_function_lib.py
# `signature_keys` is guaranteed to have only one element after the # validation. representative_dataset_map = {signature_keys[0]: representative_dataset} try: if context.executing_eagerly() and not force_graph_mode_calibration: logging.info('Calibration step is executed in eager mode.') _run_graph_for_calibration_eager_mode( float_model_dir, tags, representative_dataset_map )
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Fri May 31 05:32:11 UTC 2024 - 27.4K bytes - Viewed (0)