[MO] Clean up Model Optimizer options, help, and documentation (#10653)

* [MO] Clean-up MO cmd-line options Remove the following Model Optimizer deprecated options that are no longer used for several releases: disable_fusing, disable_gfusing, generate_deprecated_IR_V7, legacy_ir_generation, keep_shape_ops, move_to_preprocess Deprecate through CLI the following options for which functionality triggered from POT or automatically: disable_weights_compression, disable_nhwc_to_nchw, disable_resnet_optimization, finegrain_fusing. Correct and extend description of each MO option to be printed during model conversion. Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com> * Correct documentation about input shapes Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com> * Perform final corrections in documentation Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com> * Remove legacy_ir_generation overall Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com> * Clean-up tests from deprecated options Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com> * Recover disable_fusing option as deprecated Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com> * Fix keys for static_shape and extensions Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com> * Remove extension key that does not work Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com> * Apply feedback: remove disable_gfusing, correct docs Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com> * Recover disable_fusing option for unit-tests Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com> * Apply feedback for documentation Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com> * Apply feedback about parameters use_legacy_frontend and use_new_frontend Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com> * DO minor fixes for indentation of MO logs Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com> * Revert log.error for fallback message Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com> * Revert disable_weights_compression parameter for tests Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
2022-03-01 10:57:24 +03:00
1 parent 9da124544a
commit 6c78715749
@@ -24,7 +24,7 @@
 To convert the model to the Intermediate Representation (IR), run Model Optimizer using the following command:

 ```sh
-mo --input_model INPUT_MODEL --output_dir <OUTPUT_MODEL_DIR>
+mo --input_model INPUT_MODEL
 ```

 The output directory must have write permissions, so you can run Model Optimizer from the output directory or specify an output path with the `--output_dir` option.
@@ -71,12 +71,9 @@ Framework-agnostic parameters:
                        square brackets, for example [1,3,227,227] or
                        (1,227,227,3), where the order of dimensions depends
                        on the framework input layout of the model. For
-                        example, [N,C,H,W] is used for Caffe* models and
-                        [N,H,W,C] for TensorFlow* models. Model Optimizer
-                        performs necessary transformations to convert the
-                        shape to the layout required by Inference Engine
-                        (N,C,H,W). The shape should not contain undefined
-                        dimensions (? or -1) and should fit the dimensions
+                        example, [N,C,H,W] is used for ONNX* models and
+                        [N,H,W,C] for TensorFlow* models. The shape can contain 
+                        undefined dimensions (? or -1) and should fit the dimensions
                        defined in the input operation of the graph. Boundaries 
                        of undefined dimension can be specified with ellipsis, 
                        for example [1,1..10,128,128]. One boundary can be undefined, 
@@ -156,13 +153,12 @@ Framework-agnostic parameters:
                        original model is in FP32 and --data_type=FP16 is
                        specified, all model weights and biases are compressed
                        to FP16.
-  --disable_fusing      Turn off fusing of linear operations to Convolution
+  --disable_fusing      [DEPRECATED] Turn off fusing of linear operations to Convolution.
  --disable_resnet_optimization
-                        Turn off resnet optimization
+                        [DEPRECATED] Turn off ResNet optimization.
  --finegrain_fusing FINEGRAIN_FUSING
-                        Regex for layers/operations that won't be fused.
+                        [DEPRECATED] Regex for layers/operations that won't be fused.
                        Example: --finegrain_fusing Convolution1,.*Scale.*
-  --disable_gfusing     Turn off fusing of grouped convolutions
  --enable_concat_optimization
                        Turn on Concat optimization.
  --extensions EXTENSIONS
@@ -187,7 +183,7 @@ Framework-agnostic parameters:
                        to `Constant`). Changing model input shape using
                        the OpenVINO Runtime API in runtime may fail for such an IR.
  --disable_weights_compression
-                        Disable compression and store weights with original
+                        [DEPRECATED] Disable compression and store weights with original
                        precision.
  --progress            Enable model conversion progress display.
  --stream_output       Switch model conversion progress display to a
@@ -195,8 +191,13 @@ Framework-agnostic parameters:
  --transformations_config TRANSFORMATIONS_CONFIG
                        Use the configuration file with transformations
                        description.
-  --use_new_frontend    Force the usage of new frontend API for model processing.
-  --use_legacy_frontend Force the usage of legacy API for model processing.
+  --use_new_frontend    Force the usage of new Frontend of Model Optimizer for model conversion into IR.
+                        The new Frontend is C++ based and is available for ONNX* and PaddlePaddle* models.
+                        Model optimizer uses new Frontend for ONNX* and PaddlePaddle* by default that means
+                        `--use_new_frontend` and `--use_legacy_frontend` options are not specified.
+  --use_legacy_frontend Force the usage of legacy Frontend of Model Optimizer for model conversion into IR.
+                        The legacy Frontend is Python based and is available for TensorFlow*, ONNX*, MXNet*,
+                        Caffe*, and Kaldi* models.
 ```

 The sections below provide details on using particular parameters and examples of CLI commands.
@@ -218,7 +219,8 @@ There is no a universal recipe for determining the mean/scale values for a parti
 * Open the model in a visualization tool and check for layers performing subtraction or multiplication (like `Sub`, `Mul`, `ScaleShift`, `Eltwise` etc) of the input data. If such layers exist, pre-processing is probably part of the model.

 ## When to Specify Input Shapes <a name="when_to_specify_input_shapes"></a>
-There are situations when the input data shape for the model is not fixed, like for the fully-convolutional neural networks. In this case, for example, TensorFlow\* models contain `-1` values in the `shape` attribute of the `Placeholder` operation. Inference Engine does not support input layers with undefined size, so if the input shapes are not defined in the model, the Model Optimizer fails to convert the model. The solution is to provide the input shape(s) using the `--input` or `--input_shape` command line parameter for all input(s) of the model or provide the batch size using the `-b` command line parameter if the model contains just one input with undefined batch size only. In the latter case, the `Placeholder` shape for the TensorFlow\* model looks like this `[-1, 224, 224, 3]`. 
+There are situations when Model Optimizer is unable to deduce input shapes of the model, for example, in case of model cutting due to unsupported operations.
+The solution is to provide input shapes of a static rank explicitly.

 ## When to Reverse Input Channels <a name="when_to_reverse_input_channels"></a>
 Input data for your application can be of RGB or BRG color input order. For example, OpenVINO Samples load input images in the BGR channels order. However, the model may be trained on images loaded with the opposite order (for example, most TensorFlow\* models are trained with images in RGB order). In this case, inference results using the OpenVINO samples may be incorrect. The solution is to provide `--reverse_input_channels` command line parameter. Taking this parameter, the Model Optimizer performs first convolution or other channel dependent operation weights modification so these operations output will be like the image is passed with RGB channels order.
@@ -231,54 +233,50 @@ Resulting Intermediate Representation will not be resizable with the help of Ope

 Launch the Model Optimizer for the Caffe bvlc_alexnet model with debug log level:
 ```sh
-mo --input_model bvlc_alexnet.caffemodel --log_level DEBUG --output_dir <OUTPUT_MODEL_DIR>
+mo --input_model bvlc_alexnet.caffemodel --log_level DEBUG
 ```

 Launch the Model Optimizer for the Caffe bvlc_alexnet model with the output IR called `result.*` in the specified `output_dir`:
 ```sh
-mo --input_model bvlc_alexnet.caffemodel --model_name result --output_dir /../../models/
+mo --input_model bvlc_alexnet.caffemodel --model_name result --output_dir <OUTPUT_MODEL_DIR>
 ```

 Launch the Model Optimizer for the Caffe bvlc_alexnet model with one input with scale values:
 ```sh
-mo --input_model bvlc_alexnet.caffemodel --scale_values [59,59,59] --output_dir <OUTPUT_MODEL_DIR>
+mo --input_model bvlc_alexnet.caffemodel --scale_values [59,59,59]
 ```

 Launch the Model Optimizer for the Caffe bvlc_alexnet model with multiple inputs with scale values:
 ```sh
-mo --input_model bvlc_alexnet.caffemodel --input data,rois --scale_values [59,59,59],[5,5,5] --output_dir <OUTPUT_MODEL_DIR>
+mo --input_model bvlc_alexnet.caffemodel --input data,rois --scale_values [59,59,59],[5,5,5]
 ```

 Launch the Model Optimizer for the Caffe bvlc_alexnet model with multiple inputs with scale and mean values specified for the particular nodes:
 ```sh
-mo --input_model bvlc_alexnet.caffemodel --input data,rois --mean_values data[59,59,59] --scale_values rois[5,5,5] --output_dir <OUTPUT_MODEL_DIR>
+mo --input_model bvlc_alexnet.caffemodel --input data,rois --mean_values data[59,59,59] --scale_values rois[5,5,5]
 ```

 Launch the Model Optimizer for the Caffe bvlc_alexnet model with specified input layer, overridden input shape, scale 5, batch 8 and specified name of an output operation:
 ```sh
-mo --input_model bvlc_alexnet.caffemodel --input "data[1 3 224 224]" --output pool5 -s 5 -b 8 --output_dir <OUTPUT_MODEL_DIR>
-```
-Launch the Model Optimizer for the Caffe bvlc_alexnet model with disabled fusing for linear operations to Convolution and grouped convolutions:
-```sh
-mo --input_model bvlc_alexnet.caffemodel --disable_fusing --disable_gfusing --output_dir <OUTPUT_MODEL_DIR>
+mo --input_model bvlc_alexnet.caffemodel --input data --output pool5 -s 5 -b 8
 ```

 Launch the Model Optimizer for the Caffe bvlc_alexnet model with reversed input channels order between RGB and BGR, specified mean values to be used for the input image per channel and specified data type for input tensor values:
 ```sh
-mo --input_model bvlc_alexnet.caffemodel --reverse_input_channels --mean_values [255,255,255] --data_type FP16 --output_dir <OUTPUT_MODEL_DIR>
+mo --input_model bvlc_alexnet.caffemodel --reverse_input_channels --mean_values [255,255,255] --data_type FP16
 ```

 Launch the Model Optimizer for the Caffe bvlc_alexnet model with extensions listed in specified directories, specified mean_images binaryproto 
 file. For more information about extensions, please refer to the [OpenVINO™ Extensibility Mechanism](../../../Extensibility_UG/Intro.md).
 ```sh
-mo --input_model bvlc_alexnet.caffemodel --extensions /home/,/some/other/path/ --mean_file /path/to/binaryproto --output_dir <OUTPUT_MODEL_DIR>
+mo --input_model bvlc_alexnet.caffemodel --extensions /home/,/some/other/path/ --mean_file /path/to/binaryproto
 ```

 Launch the Model Optimizer for TensorFlow* FaceNet* model with a placeholder freezing value. 
 It replaces the placeholder with a constant layer that contains the passed value.
 For more information about FaceNet conversion, please refer to [this](tf_specific/Convert_FaceNet_From_Tensorflow.md) page.
 ```sh
-mo --input_model FaceNet.pb --input "phase_train->False" --output_dir <OUTPUT_MODEL_DIR>
+mo --input_model FaceNet.pb --input "phase_train->False"
 ```
 Launch the Model Optimizer for any model with a placeholder freezing tensor of values. 
 It replaces the placeholder with a constant layer that contains the passed values.
@@ -287,7 +285,7 @@ Tensor here is represented in square brackets with each value separated from ano
 If data type is set in the model, this tensor will be reshaped to a placeholder shape and casted to placeholder data type.
 Otherwise, it will be casted to data type passed to `--data_type` parameter (by default, it is FP32).
 ```sh
-mo --input_model FaceNet.pb --input "placeholder_layer_name->[0.1 1.2 2.3]" --output_dir <OUTPUT_MODEL_DIR>
+mo --input_model FaceNet.pb --input "placeholder_layer_name->[0.1 1.2 2.3]"
 ```


@@ -28,7 +28,8 @@ from openvino.tools.mo.middle.pattern_match import for_graph_and_each_sub_graph_
 from openvino.tools.mo.pipeline.common import prepare_emit_ir, get_ir_version
 from openvino.tools.mo.pipeline.unified import unified_pipeline
 from openvino.tools.mo.utils import import_extensions
-from openvino.tools.mo.utils.cli_parser import check_available_transforms, get_caffe_cli_options, \
+from openvino.tools.mo.utils.cli_parser import check_available_transforms, \
+    get_advanced_cli_options, get_caffe_cli_options, \
    get_common_cli_options, get_freeze_placeholder_values, get_kaldi_cli_options, get_layout_values, \
    get_mean_scale_dictionary, get_meta_info, get_model_name, get_mxnet_cli_options, get_onnx_cli_options, \
    get_placeholder_shapes, get_tf_cli_options, get_tuple_values, parse_transform, parse_tuple_pairs
@@ -61,6 +62,7 @@ def print_argv(argv: argparse.Namespace, is_caffe: bool, is_tf: bool, is_mxnet:
    print('Model Optimizer arguments:')
    props = OrderedDict()
    props['common_args'] = get_common_cli_options(model_name)
+    props['advanced_args'] = get_advanced_cli_options()
    if is_caffe:
        props['caffe_args'] = get_caffe_cli_options()
    if is_tf:
@@ -74,6 +76,7 @@ def print_argv(argv: argparse.Namespace, is_caffe: bool, is_tf: bool, is_mxnet:

    framework_specifics_map = {
        'common_args': 'Common parameters:',
+        'advanced_args': 'Advanced parameters:',
        'caffe_args': 'Caffe specific parameters:',
        'tf_args': 'TensorFlow specific parameters:',
        'mxnet_args': 'MXNet specific parameters:',
@@ -245,9 +248,6 @@ def arguments_post_parsing(argv: argparse.Namespace):
    # This is just to check that transform key is valid and transformations are available
    check_available_transforms(parse_transform(argv.transform))

-    if argv.legacy_ir_generation and len(argv.transform) != 0:
-        raise Error("--legacy_ir_generation and --transform keys can not be used at the same time.")
-
    # For C++ frontends there are no specific Python installation requirements, check only generic ones
    if moc_front_end:
        ret_code = check_requirements()
@@ -434,13 +434,12 @@ def emit_ir(graph: Graph, argv: argparse.Namespace):

        return_code = "not executed"
        try:
-            if not argv.legacy_ir_generation:
-                from openvino.tools.mo.back.offline_transformations import apply_offline_transformations
-                apply_offline_transformations(orig_model_name, argv)
-                if "compress_fp16" in argv and argv.compress_fp16:
-                    # restore data_type cmd parameter
-                    argv.data_type = 'FP16'
-                return_code = 0
+            from openvino.tools.mo.back.offline_transformations import apply_offline_transformations
+            apply_offline_transformations(orig_model_name, argv)
+            if "compress_fp16" in argv and argv.compress_fp16:
+                # restore data_type cmd parameter
+                argv.data_type = 'FP16'
+            return_code = 0
        except Exception as e:
            return_code = "failed"
            log.error(e)
@@ -77,12 +77,11 @@ class Fusing(MiddleReplacementPattern):
            for_graph_and_each_sub_graph_recursively(graph, fuse_linear_ops)
            for_graph_and_each_sub_graph_recursively(graph, lambda G: G.clean_up())

-        if not argv.disable_gfusing:
-            for_graph_and_each_sub_graph_recursively(graph, grouped_convolutions_fusing)
+        for_graph_and_each_sub_graph_recursively(graph, grouped_convolutions_fusing)
+        for_graph_and_each_sub_graph_recursively(graph, lambda G: G.clean_up())
+        if not argv.disable_fusing:
+            for_graph_and_each_sub_graph_recursively(graph, fuse_linear_ops)
            for_graph_and_each_sub_graph_recursively(graph, lambda G: G.clean_up())
-            if not argv.disable_fusing:
-                for_graph_and_each_sub_graph_recursively(graph, fuse_linear_ops)
-                for_graph_and_each_sub_graph_recursively(graph, lambda G: G.clean_up())

        for_graph_and_each_sub_graph_recursively(graph, normalize_eltwise_inputs)
        for_graph_and_each_sub_graph_recursively(graph, lambda G: G.clean_up())
@@ -66,7 +66,7 @@ def import_core_modules(silent: bool, path_to_module: str):
        ie_version = str(get_version())
        mo_version = str(v.get_version())  # pylint: disable=no-member,no-name-in-module

-        print("\t- {}: \t{}".format("OpenVINO runtime found in", os.path.dirname(openvino.__file__)))
+        print("{}: \t{}".format("OpenVINO runtime found in", os.path.dirname(openvino.__file__)))
        print("{}: \t{}".format("OpenVINO runtime version", ie_version))
        print("{}: \t{}".format("Model Optimizer version", mo_version))

@@ -34,6 +34,13 @@ class DeprecatedStoreTrue(argparse.Action):
        setattr(namespace, self.dest, True)


+class DeprecatedOptionCommon(argparse.Action):
+    def __call__(self, parser, args, values, option_string):
+       dep_msg = "Use of deprecated cli option {} detected. Option use in the following releases will be fatal. ".format(option_string)
+       log.error(dep_msg, extra={'is_warning': True})
+       setattr(args, self.dest, values)
+
+
 class IgnoredAction(argparse.Action):
    def __init__(self, nargs=0, **kw):
        super().__init__(nargs=nargs, **kw)
@@ -254,10 +261,8 @@ def get_common_cli_parser(parser: argparse.ArgumentParser = None):
                                   'Shape is defined as a comma-separated list of integer numbers enclosed in '
                                   'parentheses or square brackets, for example [1,3,227,227] or (1,227,227,3), where '
                                   'the order of dimensions depends on the framework input layout of the model. '
-                                   'For example, [N,C,H,W] is used for Caffe* models and [N,H,W,C] for TensorFlow* '
-                                   'models. Model Optimizer performs necessary transformations to convert the shape to '
-                                   'the layout required by Inference Engine (N,C,H,W). The shape could contain '
-                                   'undefined dimensions (-1) and should fit the dimensions defined in the input '
+                                   'For example, [N,C,H,W] is used for ONNX* models and [N,H,W,C] for TensorFlow* '
+                                   'models. The shape can contain undefined dimensions (? or -1) and should fit the dimensions defined in the input '
                                   'operation of the graph. Boundaries of undefined dimension can be specified with '
                                   'ellipsis, for example [1,1..10,128,128]. One boundary can be undefined, for '
                                   'example [1,..100] or [1,3,1..,1..]. If there are multiple inputs in the model, '
@@ -371,23 +376,18 @@ def get_common_cli_parser(parser: argparse.ArgumentParser = None):
                                   'Available transformations: "LowLatency2", "MakeStateful"',
                              default="")
    common_group.add_argument('--disable_fusing',
-                              help='Turn off fusing of linear operations to Convolution',
+                              help='[DEPRECATED] Turn off fusing of linear operations to Convolution.',
                              action=DeprecatedStoreTrue)
    common_group.add_argument('--disable_resnet_optimization',
-                              help='Turn off resnet optimization',
-                              action='store_true')
+                              help='[DEPRECATED] Turn off ResNet optimization.',
+                              action=DeprecatedStoreTrue, default=False)
    common_group.add_argument('--finegrain_fusing',
-                              help='Regex for layers/operations that won\'t be fused. ' +
-                                   'Example: --finegrain_fusing Convolution1,.*Scale.*')
-    common_group.add_argument('--disable_gfusing',
-                              help='Turn off fusing of grouped convolutions',
-                              action=DeprecatedStoreTrue)
+                              help='[DEPRECATED] Regex for layers/operations that won\'t be fused. ' +
+                                   'Example: --finegrain_fusing Convolution1,.*Scale.*',
+                              action=DeprecatedOptionCommon)
    common_group.add_argument('--enable_concat_optimization',
-                              help='Turn on Concat optimization.',
-                              action='store_true')
-    common_group.add_argument('--move_to_preprocess',
-                              help='Move mean values to IR preprocess section',
-                              action=DeprecatedStoreTrue)
+                              help='[DEPRECATED] Turn on Concat optimization.',
+                              action=DeprecatedStoreTrue, default=False)
    # we use CanonicalizeDirCheckExistenceAction instead of readable_dirs to handle empty strings
    common_group.add_argument("--extensions",
                              help="Directory or a comma separated list of directories with extensions. To disable all "
@@ -417,19 +417,14 @@ def get_common_cli_parser(parser: argparse.ArgumentParser = None):
                                   'It will be DEPRECATED in future releases. '
                                   'Use --input option to specify a value for freezing.',
                              default=None)
-    common_group.add_argument('--generate_deprecated_IR_V7',
-                              help=argparse.SUPPRESS, action=IgnoredAction, default=False)
    common_group.add_argument('--static_shape',
                              help='Enables IR generation for fixed input shape (folding `ShapeOf` operations and '
                                   'shape-calculating sub-graphs to `Constant`). Changing model input shape using '
-                                   'the Inference Engine API in runtime may fail for such an IR.',
+                                   'the OpenVINO Runtime API in runtime may fail for such an IR.',
                              action='store_true', default=False)
-    common_group.add_argument('--keep_shape_ops',
-                              help=argparse.SUPPRESS,
-                              action=IgnoredAction, default=True)
    common_group.add_argument('--disable_weights_compression',
-                              help='Disable compression and store weights with original precision.',
-                              action='store_true', default=False)
+                              help='[DEPRECATED] Disable compression and store weights with original precision.',
+                              action=DeprecatedStoreTrue, default=False)
    common_group.add_argument('--progress',
                              help='Enable model conversion progress display.',
                              action='store_true', default=False)
@@ -442,13 +437,16 @@ def get_common_cli_parser(parser: argparse.ArgumentParser = None):
                                   'from the current directory, as absolute path or as a'
                                   'relative path from the mo root directory',
                              action=CanonicalizeTransformationPathCheckExistenceAction)
-    common_group.add_argument('--legacy_ir_generation',
-                              help=argparse.SUPPRESS, action=DeprecatedStoreTrue, default=False)
    common_group.add_argument("--use_new_frontend",
-                              help="Force the usage of new frontend API for model processing",
+                              help='Force the usage of new Frontend of Model Optimizer for model conversion into IR. '
+                                   'The new Frontend is C++ based and is available for ONNX* and PaddlePaddle* models. '
+                                   'Model optimizer uses new Frontend for ONNX* and PaddlePaddle* by default that means '
+                                   '`--use_new_frontend` and `--use_legacy_frontend` options are not specified.',
                              action='store_true', default=False)
    common_group.add_argument("--use_legacy_frontend",
-                              help="Force the usage of legacy API for model processing",
+                              help='Force the usage of legacy Frontend of Model Optimizer for model conversion into IR. '
+                                   'The legacy Frontend is Python based and is available for TensorFlow*, ONNX*, MXNet*, '
+                                   'Caffe*, and Kaldi* models.',
                              action='store_true', default=False)
    return parser

@@ -471,14 +469,20 @@ def get_common_cli_options(model_name):
    d['scale'] = ['- Scale factor', lambda x: x if x else 'Not specified']
    d['data_type'] = ['- Precision of IR', lambda x: 'FP32' if x == 'float' else 'FP16' if x == 'half' else x]
    d['disable_fusing'] = ['- Enable fusing', lambda x: not x]
-    d['disable_gfusing'] = ['- Enable grouped convolutions fusing', lambda x: not x]
-    d['move_to_preprocess'] = '- Move mean values to preprocess section'
+    d['transform'] = ['- User transformations', lambda x: x if x else 'Not specified']
    d['reverse_input_channels'] = '- Reverse input channels'
-    d['use_legacy_frontend'] = '- Use legacy API for model processing'
+    d['static_shape'] = '- Enable IR generation for fixed input shape'
    d['transformations_config'] = '- Use the transformations config file'
    return d


+def get_advanced_cli_options():
+    d = OrderedDict()
+    d['use_legacy_frontend'] = '- Force the usage of legacy Frontend of Model Optimizer for model conversion into IR'
+    d['use_new_frontend'] = '- Force the usage of new Frontend of Model Optimizer for model conversion into IR'
+    return d
+
+
 def get_caffe_cli_options():
    d = {
        'input_proto': ['- Path to the Input prototxt', lambda x: x],
@@ -657,7 +661,7 @@ def get_tf_cli_parser(parser: argparse.ArgumentParser = None):
    tf_group.add_argument('--disable_nhwc_to_nchw',
                          help='[DEPRECATED] Disables the default translation from NHWC to NCHW. Since 2022.1 this option '
                               'is deprecated and used only to maintain backward compatibility with previous releases.',
-                          action='store_true')
+                          action=DeprecatedStoreTrue, default=False)
    return parser


@@ -48,7 +48,6 @@ def replaceArgsHelper(log_level='DEBUG',
                      model_name='abc',
                      input_model='abc.test_mo_mock_mdl',
                      transform=[],
-                      legacy_ir_generation=False,
                      scale=None,
                      output=None,
                      _input=None,
@@ -67,7 +66,6 @@ def replaceArgsHelper(log_level='DEBUG',
        model_name=model_name,
        input_model=input_model,
        transform=transform,
-        legacy_ir_generation=legacy_ir_generation,
        scale=scale,
        output=output,
        input=_input,
@@ -34,7 +34,6 @@ def base_args_config(use_legacy_fe:bool=None, use_new_fe:bool=None):
    args.input_model = None
    args.silent = True
    args.transform=[]
-    args.legacy_ir_generation = False
    args.scale = None
    args.output=None
    args.input=None
@@ -47,7 +46,6 @@ def base_args_config(use_legacy_fe:bool=None, use_new_fe:bool=None):
    args.transformations_config = None
    args.disable_fusing = None
    args.finegrain_fusing = None
-    args.disable_gfusing = None
    args.disable_resnet_optimization = None
    args.enable_concat_optimization = None
    args.static_shape = None
@@ -29,7 +29,6 @@ def base_args_config():
    args.input_model = None
    args.silent = True
    args.transform=[]
-    args.legacy_ir_generation = False
    args.scale = None
    args.output=None
    args.input=None
@@ -42,7 +41,6 @@ def base_args_config():
    args.transformations_config = None
    args.disable_fusing = None
    args.finegrain_fusing = None
-    args.disable_gfusing = None
    args.disable_resnet_optimization = None
    args.enable_concat_optimization = None
    args.static_shape = None