Bug-fixes and re-factoring for the rewrite module

- Fix input shape of rewrite replacement:
  During and after training of the replacement model for a rewrite the
  Keras model is converted and saved in TensorFlow Lite format. If the
  input shape does not match the teacher model exactly, e.g. if the
  batch size is undefined, the TFLiteConverter adds extra operators
  during conversion.
- Fix rewritten model output
  - Save the model output with the rewritten operator in the output dir
  - Log MAE and NRMSE of the rewrite
- Remove 'verbose' flag from rewrite module and rely on the logging
  mechanism to control verbose output.
- Re-factor utility classes for rewrites
  - Merge the two TFLiteModel classes
  - Move functionality to load/save TensorFlow Lite flatbuffers to
    nn/tensorflow/tflite_graph
- Fix issue with unknown shape in datasets
  After upgrading to TensorFlow 2.12 the unknown shape of the
  TFRecordDataset is causing problems when training the replacement models
  for rewrites. By explicitly setting the right shape of the tensors we
  can work around the issue.
- Adapt default parameters for rewrites. The training steps especially
  had to be increased significantly to be effective.

Resolves: MLIA-895, MLIA-907, MLIA-946, MLIA-979
Signed-off-by: Benjamin Klimczak <benjamin.klimczak@arm.com>
Change-Id: I887ad165aed0f2c6e5a0041f64cec5e6c5ab5c5c

1 files changed, 0 insertions, 33 deletions

diff --git a/tests/test_nn_rewrite_core_utils.py b/tests/test_nn_rewrite_core_utils.py
deleted file mode 100644
index d806a7b..0000000
--- a/tests/test_nn_rewrite_core_utils.py
+++ /dev/null
@@ -1,33 +0,0 @@
-# SPDX-FileCopyrightText: Copyright 2023, Arm Limited and/or its affiliates.
-# SPDX-License-Identifier: Apache-2.0
-"""Tests for module mlia.nn.rewrite.utils."""
-from pathlib import Path
-
-import pytest
-import tensorflow as tf
-from tensorflow.lite.python.schema_py_generated import ModelT
-
-from mlia.nn.rewrite.core.utils.utils import load
-from mlia.nn.rewrite.core.utils.utils import save
-from tests.utils.rewrite import models_are_equal
-
-
-def test_load_save(test_tflite_model: Path, tmp_path: Path) -> None:
-    """Test the load/save functions for TensorFlow Lite models."""
-    with pytest.raises(FileNotFoundError):
-        load("THIS_IS_NOT_A_REAL_FILE")
-
-    model = load(test_tflite_model)
-    assert isinstance(model, ModelT)
-    assert model.subgraphs
-
-    output_file = tmp_path / "test.tflite"
-    assert not output_file.is_file()
-    save(model, output_file)
-    assert output_file.is_file()
-
-    model_copy = load(str(output_file))
-    assert models_are_equal(model, model_copy)
-
-    # Double check that the TensorFlow Lite Interpreter can still load the file.
-    tf.lite.Interpreter(model_path=str(output_file))