* enable --compress_to_fp16 by default in MO
* corrected docs, added warning if user did't specify --compress_to_fp16 explicitly
* fix failing MO unit-tests
* do not wipe out data_type if user defined it explicitly by cli argument
* updated warning message and docs
* corrected phrasing
* corrected phrasing in FP16_Compression.md
* set compress_to_fp16=False for convert tests
* leftover: set compress_to_fp16=False for convert tests
* minor correction
* print info message in main.py, som minor changes
* typos fix
* fix losing information whether arguments set by user or got from defaults
* returned back default values instead of None
* more selective correcting of test_mo_convert_pytorch.py; added test for cases when compression is enabled/disabled or left by default
* fix test_mo_convert_pytorch.py
It turned out that NormalizeL2 is absent in tf.raw_ops api
and always presented in the decomposed form.
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* [TF FE] Refactor LogSoftmax translator and layer test
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Work around for the legacy frontend
* Update src/frontends/tensorflow_common/src/op/log_softmax.cpp
---------
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* [WIP]: poc: integrate pt fe to mo.convert_model
* temporaly resolve names using signature inspection
* fix logic
* move to moc frontend
* add rank and data type setting
* add input signature
* apply comments
* move after convert processing
* support work without example_input, provide parameters description
* ignore extensions on fe side
* upd tests
* more tests
* add notes about extensions support and removing onnx path
* remove debug prints
* refactoring
* update BOM
* [TF FE] Fix FusedBatchNormV3 in case of mean and variance empty tensors
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Add to nightly
---------
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* [TF FE] Refactor ZerosLike and add layer test
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Fix test for Wide and Deep model
---------
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* [TF FE] Support TensorList operations and RNN layers
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Remove TensorList operations from the fallback
* Fix computation of dummy tensor size
---------
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* [TF FE] Refactor LinSpace translator and add layer test
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Remove start_shape from test parameters
---------
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* [TF FE] Refactor LeakyRelu and add layer tests
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Support LeakyRELU for TensorFlow Lite
---------
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
