diff options
author | Benjamin Klimczak <benjamin.klimczak@arm.com> | 2023-07-19 16:35:57 +0100 |
---|---|---|
committer | Benjamin Klimczak <benjamin.klimczak@arm.com> | 2023-10-11 16:06:17 +0100 |
commit | 3cd84481fa25e64c29e57396d4bf32d7a3ca490a (patch) | |
tree | ad81fb520a965bd3a3c7c983833b7cd48f9b8dea /src/mlia/nn/rewrite/core/graph_edit/cut.py | |
parent | f3e6597dd50ec70f043d692b773f2d9fd31519ae (diff) | |
download | mlia-3cd84481fa25e64c29e57396d4bf32d7a3ca490a.tar.gz |
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
Diffstat (limited to 'src/mlia/nn/rewrite/core/graph_edit/cut.py')
-rw-r--r-- | src/mlia/nn/rewrite/core/graph_edit/cut.py | 8 |
1 files changed, 4 insertions, 4 deletions
diff --git a/src/mlia/nn/rewrite/core/graph_edit/cut.py b/src/mlia/nn/rewrite/core/graph_edit/cut.py index 2707eb1..13a5268 100644 --- a/src/mlia/nn/rewrite/core/graph_edit/cut.py +++ b/src/mlia/nn/rewrite/core/graph_edit/cut.py @@ -9,8 +9,8 @@ import tensorflow as tf from tensorflow.lite.python.schema_py_generated import ModelT from tensorflow.lite.python.schema_py_generated import SubGraphT -from mlia.nn.rewrite.core.utils.utils import load -from mlia.nn.rewrite.core.utils.utils import save +from mlia.nn.tensorflow.tflite_graph import load_fb +from mlia.nn.tensorflow.tflite_graph import save_fb os.environ["TF_CPP_MIN_LOG_LEVEL"] = "3" tf.compat.v1.logging.set_verbosity(tf.compat.v1.logging.ERROR) @@ -138,8 +138,8 @@ def cut_model( output_file: str, ) -> None: """Cut subgraphs and simplify a given model.""" - model = load(model_file) + model = load_fb(model_file) subgraph = model.subgraphs[subgraph_index] cut_subgraph(subgraph, input_names, output_names) simplify(model) - save(model, output_file) + save_fb(model, output_file) |