PyPI - mct-nightly - Versions diffs - 1.11.0.20240313.post405__tar.gz → 1.11.0.20240315.post349__tar.gz - Mend

mct-nightly 1.11.0.20240313.post405tar.gz → 1.11.0.20240315.post349tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (484) hide show

{mct-nightly-1.11.0.20240313.post405 → mct-nightly-1.11.0.20240315.post349}/PKG-INFO RENAMED Viewed

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: mct-nightly
-Version: 1.11.0.20240313.post405
+Version: 1.11.0.20240315.post349
 Summary: A Model Compression Toolkit for neural networks
 Home-page: UNKNOWN
 License: UNKNOWN
@@ -64,11 +64,11 @@ Description: # Model Compression Toolkit (MCT)
         | Python 3.11 | | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python311_pytorch20.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python311_pytorch20.yml) | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python311_pytorch21.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python311_pytorch21.yml) |
-        |             | TensorFlow 2.12                                                                                                                                                                                                                        | TensorFlow 2.13                                                                                                                                                                                                                        | TensorFlow 2.14                                                                                                                                                                                                                        |
-        |-------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
-        | Python 3.9  | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python39_keras212.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python39_keras212.yml)   | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python39_keras213.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python39_keras213.yml)   | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python39_keras214.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python39_keras214.yml)   |
-        | Python 3.10 | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python310_keras212.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python310_keras212.yml) | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python310_keras213.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python310_keras213.yml) | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python310_keras214.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python310_keras214.yml) |
-        | Python 3.11 | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python311_keras212.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python311_keras212.yml) | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python311_keras213.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python311_keras213.yml) | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python311_keras214.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python311_keras214.yml) |
+        |             | TensorFlow 2.12                                                                                                                                                                                                                        | TensorFlow 2.13                                                                                                                                                                                                                        | TensorFlow 2.14                                                                                                                                                                                                                        | TensorFlow 2.15                                                                                                                                                                                                        |
+        |-------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+        | Python 3.9  | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python39_keras212.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python39_keras212.yml)   | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python39_keras213.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python39_keras213.yml)   | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python39_keras214.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python39_keras214.yml)   | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python39_keras215.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python39_keras215.yml)   |
+        | Python 3.10 | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python310_keras212.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python310_keras212.yml) | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python310_keras213.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python310_keras213.yml) | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python310_keras214.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python310_keras214.yml) | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python310_keras215.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python310_keras215.yml) |
+        | Python 3.11 | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python311_keras212.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python311_keras212.yml) | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python311_keras213.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python311_keras213.yml) | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python311_keras214.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python311_keras214.yml) | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python311_keras215.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python311_keras215.yml) |
         ## Supported Features

{mct-nightly-1.11.0.20240313.post405 → mct-nightly-1.11.0.20240315.post349}/README.md RENAMED Viewed

@@ -58,11 +58,11 @@ Currently, MCT is being tested on various Python, Pytorch and TensorFlow version
 | Python 3.11 | | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python311_pytorch20.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python311_pytorch20.yml) | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python311_pytorch21.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python311_pytorch21.yml) |
-|             | TensorFlow 2.12                                                                                                                                                                                                                        | TensorFlow 2.13                                                                                                                                                                                                                        | TensorFlow 2.14                                                                                                                                                                                                                        |
-|-------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
-| Python 3.9  | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python39_keras212.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python39_keras212.yml)   | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python39_keras213.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python39_keras213.yml)   | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python39_keras214.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python39_keras214.yml)   |
-| Python 3.10 | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python310_keras212.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python310_keras212.yml) | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python310_keras213.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python310_keras213.yml) | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python310_keras214.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python310_keras214.yml) |
-| Python 3.11 | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python311_keras212.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python311_keras212.yml) | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python311_keras213.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python311_keras213.yml) | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python311_keras214.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python311_keras214.yml) |
+|             | TensorFlow 2.12                                                                                                                                                                                                                        | TensorFlow 2.13                                                                                                                                                                                                                        | TensorFlow 2.14                                                                                                                                                                                                                        | TensorFlow 2.15                                                                                                                                                                                                        |
+|-------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| Python 3.9  | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python39_keras212.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python39_keras212.yml)   | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python39_keras213.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python39_keras213.yml)   | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python39_keras214.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python39_keras214.yml)   | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python39_keras215.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python39_keras215.yml)   |
+| Python 3.10 | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python310_keras212.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python310_keras212.yml) | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python310_keras213.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python310_keras213.yml) | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python310_keras214.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python310_keras214.yml) | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python310_keras215.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python310_keras215.yml) |
+| Python 3.11 | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python311_keras212.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python311_keras212.yml) | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python311_keras213.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python311_keras213.yml) | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python311_keras214.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python311_keras214.yml) | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python311_keras215.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python311_keras215.yml) |
 ## Supported Features

{mct-nightly-1.11.0.20240313.post405 → mct-nightly-1.11.0.20240315.post349}/mct_nightly.egg-info/PKG-INFO RENAMED Viewed

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: mct-nightly
-Version: 1.11.0.20240313.post405
+Version: 1.11.0.20240315.post349
 Summary: A Model Compression Toolkit for neural networks
 Home-page: UNKNOWN
 License: UNKNOWN
@@ -64,11 +64,11 @@ Description: # Model Compression Toolkit (MCT)
         | Python 3.11 | | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python311_pytorch20.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python311_pytorch20.yml) | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python311_pytorch21.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python311_pytorch21.yml) |
-        |             | TensorFlow 2.12                                                                                                                                                                                                                        | TensorFlow 2.13                                                                                                                                                                                                                        | TensorFlow 2.14                                                                                                                                                                                                                        |
-        |-------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
-        | Python 3.9  | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python39_keras212.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python39_keras212.yml)   | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python39_keras213.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python39_keras213.yml)   | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python39_keras214.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python39_keras214.yml)   |
-        | Python 3.10 | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python310_keras212.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python310_keras212.yml) | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python310_keras213.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python310_keras213.yml) | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python310_keras214.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python310_keras214.yml) |
-        | Python 3.11 | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python311_keras212.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python311_keras212.yml) | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python311_keras213.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python311_keras213.yml) | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python311_keras214.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python311_keras214.yml) |
+        |             | TensorFlow 2.12                                                                                                                                                                                                                        | TensorFlow 2.13                                                                                                                                                                                                                        | TensorFlow 2.14                                                                                                                                                                                                                        | TensorFlow 2.15                                                                                                                                                                                                        |
+        |-------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+        | Python 3.9  | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python39_keras212.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python39_keras212.yml)   | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python39_keras213.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python39_keras213.yml)   | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python39_keras214.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python39_keras214.yml)   | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python39_keras215.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python39_keras215.yml)   |
+        | Python 3.10 | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python310_keras212.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python310_keras212.yml) | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python310_keras213.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python310_keras213.yml) | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python310_keras214.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python310_keras214.yml) | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python310_keras215.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python310_keras215.yml) |
+        | Python 3.11 | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python311_keras212.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python311_keras212.yml) | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python311_keras213.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python311_keras213.yml) | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python311_keras214.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python311_keras214.yml) | [![Run Tests](https://github.com/sony/model_optimization/actions/workflows/run_tests_python311_keras215.yml/badge.svg)](https://github.com/sony/model_optimization/actions/workflows/run_tests_python311_keras215.yml) |
         ## Supported Features

{mct-nightly-1.11.0.20240313.post405 → mct-nightly-1.11.0.20240315.post349}/model_compression_toolkit/core/common/fusion/layer_fusing.py RENAMED Viewed

@@ -31,9 +31,10 @@ def filter_fusing_patterns(fusing_patterns: List[List[Any]], node: BaseNode, idx
         fusing_patterns after filtering non-relevant fusions
     """
     valid_fusing_patterns = []
-    for i,fusing_pattern in enumerate(fusing_patterns):
+    for i, fusing_pattern in enumerate(fusing_patterns):
         if idx < len(fusing_pattern):
-            if (type(fusing_pattern[idx]) == LayerFilterParams and node.is_match_filter_params(fusing_pattern[idx])) or fusing_pattern[idx] == node.type:
+            if (type(fusing_pattern[idx]) == LayerFilterParams and node.is_match_filter_params(fusing_pattern[idx])) or \
+                    node.is_match_type(fusing_pattern[idx]):
                 valid_fusing_patterns.append(fusing_pattern)
     # Return only valid patterns for this node
@@ -44,7 +45,7 @@ def is_valid_fusion(fusing_patterns: List[List[Any]], nodes: List[BaseNode]) ->
     """
     Check if the fusion is valid: exist in fusing_patterns
     Args:
-        fusing_patterns: supported fusings
+        fusing_patterns: supported fusing patterns
         nodes: nodes which are participating in fusion
     Returns:
         whether the fusion in valid
@@ -56,8 +57,9 @@ def is_valid_fusion(fusing_patterns: List[List[Any]], nodes: List[BaseNode]) ->
         if fusion_depth != len(fusing_pattern):
             continue
         counter = 0
-        for i,layer in enumerate(fusing_pattern):
-            if (type(layer) == LayerFilterParams and nodes[i].is_match_filter_params(layer)) or layer == nodes[i].type:
+        for i, layer in enumerate(fusing_pattern):
+            if (type(layer) == LayerFilterParams and nodes[i].is_match_filter_params(layer)) or \
+                    nodes[i].is_match_type(layer):
                 counter += 1
         if counter == fusion_depth:
             return True
@@ -107,7 +109,7 @@ def fusion(graph: Graph, tpc: TargetPlatformCapabilities) -> Graph:
         if node in fused_nodes:
             continue
         # Start fusing search
-        fusing_nodes = [] # nodes that are candidates for participating in fusing
+        fusing_nodes = []  # nodes that are candidates for participating in fusing
         patterns = copy.deepcopy(fusing_patterns)
         next_nodes = [node]
         for i in range(max_layers_fusing):

{mct-nightly-1.11.0.20240313.post405 → mct-nightly-1.11.0.20240315.post349}/model_compression_toolkit/core/common/graph/base_node.py RENAMED Viewed

@@ -14,7 +14,7 @@
 # ==============================================================================
 import copy
-from typing import Dict, Any, Tuple, List
+from typing import Dict, Any, Tuple, List, Type
 import numpy as np
@@ -556,6 +556,19 @@ class BaseNode:
             return tpc.layer2qco.get(self.type)
         return tpc.tp_model.default_qco
+    def is_match_type(self, _type: Type) -> bool:
+        """
+        Check if input type matches the node type, either in instance type or in type name. Checking the
+        name string is required because of function types changes that occurred in TF 2.15.
+        Args:
+            _type: other node type
+        Returns:
+            Whether _type matches the self node type
+        """
+        return _type == self.type or _type.__name__ == self.type.__name__
     def is_match_filter_params(self, layer_filter_params: LayerFilterParams) -> bool:
         """
         Check if the node matches a LayerFilterParams according to its
@@ -572,7 +585,7 @@ class BaseNode:
             return False
         # Check the node has the same type as the layer in LayerFilterParams
-        if layer_filter_params.layer != self.type:
+        if not self.is_match_type(layer_filter_params.layer):
             return False
         # Get attributes from node to filter

{mct-nightly-1.11.0.20240313.post405 → mct-nightly-1.11.0.20240315.post349}/model_compression_toolkit/core/common/graph/graph_matchers.py RENAMED Viewed

@@ -35,7 +35,7 @@ class NodeOperationMatcher(node_matcher.BaseNodeMatcher):
         self.operation = operation
-    def apply(self, input_node_object: Any) -> bool:
+    def apply(self, input_node_object: BaseNode) -> bool:
         """
         Check if input_node_object matches the matcher condition.
@@ -47,7 +47,7 @@ class NodeOperationMatcher(node_matcher.BaseNodeMatcher):
             return nothing.
         """
-        if input_node_object.type == self.operation:
+        if input_node_object.is_match_type(self.operation):
             return True

{mct-nightly-1.11.0.20240313.post405 → mct-nightly-1.11.0.20240315.post349}/model_compression_toolkit/core/keras/graph_substitutions/substitutions/shift_negative_activation.py RENAMED Viewed

@@ -109,7 +109,8 @@ def create_add_node(add_value: float,
                               quantization_attr={},
                               layer_class=TFOpLambda,
                               op_call_args=[np.array(add_value, dtype=np.float32).reshape([1] * len(input_shape))],
-                              op_call_kwargs={})
+                              op_call_kwargs={},
+                              functional_op=tf.add)
     return add_node
@@ -157,7 +158,8 @@ def create_pad_node(next_node_name: str,
                               layer_class=TFOpLambda,
                               op_call_args=[],
                               op_call_kwargs={'paddings': num_elements_to_pad,
-                                              'constant_values': value_to_pad})
+                                              'constant_values': value_to_pad},
+                              functional_op=tf.pad)
     return pad_node

{mct-nightly-1.11.0.20240313.post405 → mct-nightly-1.11.0.20240315.post349}/model_compression_toolkit/core/keras/kpi_data_facade.py RENAMED Viewed

@@ -36,7 +36,6 @@ if FOUND_TF:
     def keras_kpi_data(in_model: Model,
                        representative_data_gen: Callable,
                        core_config: CoreConfig = CoreConfig(mixed_precision_config=MixedPrecisionQuantizationConfig()),
-                       fw_info: FrameworkInfo = DEFAULT_KERAS_INFO,
                        target_platform_capabilities: TargetPlatformCapabilities = KERAS_DEFAULT_TPC) -> KPI:
         """
         Computes KPI data that can be used to calculate the desired target KPI for mixed-precision quantization.
@@ -46,7 +45,6 @@ if FOUND_TF:
             in_model (Model): Keras model to quantize.
             representative_data_gen (Callable): Dataset used for calibration.
             core_config (CoreConfig): CoreConfig containing parameters for quantization and mixed precision of how the model should be quantized.
-            fw_info (FrameworkInfo): Information needed for quantization about the specific framework (e.g., kernel channels indices, groups of layers by how they should be quantized, etc.). `Default Keras info <https://github.com/sony/model_optimization/blob/main/model_compression_toolkit/core/keras/default_framework_info.py>`_
             target_platform_capabilities (TargetPlatformCapabilities): TargetPlatformCapabilities to optimize the Keras model according to.
         Returns:
@@ -82,7 +80,7 @@ if FOUND_TF:
                                 representative_data_gen,
                                 core_config,
                                 target_platform_capabilities,
-                                fw_info,
+                                DEFAULT_KERAS_INFO,
                                 fw_impl)
 else:

{mct-nightly-1.11.0.20240313.post405 → mct-nightly-1.11.0.20240315.post349}/model_compression_toolkit/core/keras/reader/node_builder.py RENAMED Viewed

@@ -12,7 +12,7 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 # ==============================================================================
-from typing import Any, Callable, Dict
+from typing import Any, List, Dict
 import tensorflow as tf
 from tensorflow.python.util import tf_inspect
@@ -45,19 +45,32 @@ is_const = lambda x: isinstance(x, (tf.Variable, tf.Tensor, np.ndarray))
 is_tensor = lambda x: isinstance(x, KerasTensor)
-def get_kwargs2index(tf_func: Callable) -> Dict[str, int]:
+def get_tf_function_symbols() -> List[str]:
+    """
+    Create a list of tf function symbols, as they are created in the TFOpLambda layer. The
+    symbols are serializations of the function names.
+    Returns:
+         A list of TF function symbols,
+    """
+    return [TFOpLambda(f).symbol for f in [tf.add, tf.multiply, tf.subtract, tf.divide,
+                                           tf.truediv, tf.pow, tf.matmul]]
+def get_kwargs2index(tfoplambda_layer: TFOpLambda) -> Dict[str, int]:
     """
     Positional weights are saved according to their index in the node's call arguments, so
     need to know the function arguments' names in case the weights are in the kwargs.
     Args:
-        tf_func: functional node function.
+        tfoplambda_layer: TFOpLambda layer.
     Returns:
         A dictionary with argument number and index: {arg_name: arg_index}.
     """
-    if tf_func in [tf.add, tf.subtract, tf.divide, tf.truediv, tf.multiply, tf.pow,
-                   tf.matmul, tf.image.crop_and_resize, tf.image.combined_non_max_suppression]:
-        return {arg_name: i for i, arg_name in enumerate(tf_inspect.getfullargspec(tf_func).args)}
+    if tfoplambda_layer.function in [tf.add, tf.subtract, tf.divide, tf.truediv, tf.multiply, tf.pow,
+                                     tf.matmul, tf.image.crop_and_resize, tf.image.combined_non_max_suppression] or \
+            tfoplambda_layer.symbol in ['__operators__.add', 'math.add', 'math.multiply', 'linalg.matmul', 'concat']:
+        return {arg_name: i for i, arg_name in enumerate(tf_inspect.getfullargspec(tfoplambda_layer.function).args)}
     else:
         return {}
@@ -110,7 +123,7 @@ def build_node(node: KerasNode,
         # a flag to indicate that.
         inputs_as_list = __is_functional_inputs_a_list(op_call_args)
-        kwarg2index = get_kwargs2index(keras_layer.function)
+        kwarg2index = get_kwargs2index(keras_layer)
         # Functional nodes do not have weights, but may have constants in their call_args and\or
         # call kwargs. Therefore, we extract these constants and save them in the node's weights as
@@ -122,10 +135,10 @@ def build_node(node: KerasNode,
             Logger.error('Functional nodes are not expected to have weights in framework')
         # read weights from call args
+        tf_function_symbols = get_tf_function_symbols()
         for i, arg in enumerate(op_call_args[0] if inputs_as_list else op_call_args):
             if is_const(arg) or (
-                    keras_layer.function in [tf.add, tf.multiply, tf.subtract, tf.divide, tf.truediv, tf.pow,
-                                             tf.matmul] and
+                    keras_layer.symbol in tf_function_symbols and
                     isinstance(arg, (tuple, list))):
                 weights.update({i: to_numpy(arg, is_single_tensor=True)})
         # remove weights and KerasTensors and weights from op_call_args

{mct-nightly-1.11.0.20240313.post405 → mct-nightly-1.11.0.20240315.post349}/model_compression_toolkit/core/pytorch/kpi_data_facade.py RENAMED Viewed

@@ -39,7 +39,6 @@ if FOUND_TORCH:
     def pytorch_kpi_data(in_model: Module,
                          representative_data_gen: Callable,
                          core_config: CoreConfig = CoreConfig(mixed_precision_config=MixedPrecisionQuantizationConfig()),
-                         fw_info: FrameworkInfo = DEFAULT_PYTORCH_INFO,
                          target_platform_capabilities: TargetPlatformCapabilities = PYTORCH_DEFAULT_TPC) -> KPI:
         """
         Computes KPI data that can be used to calculate the desired target KPI for mixed-precision quantization.
@@ -49,7 +48,6 @@ if FOUND_TORCH:
             in_model (Model): PyTorch model to quantize.
             representative_data_gen (Callable): Dataset used for calibration.
             core_config (CoreConfig): CoreConfig containing parameters for quantization and mixed precision
-            fw_info (FrameworkInfo): Information needed for quantization about the specific framework (e.g., kernel channels indices, groups of layers by how they should be quantized, etc.). `Default PyTorch info <https://github.com/sony/model_optimization/blob/main/model_compression_toolkit/core/pytorch/default_framework_info.py>`_
             target_platform_capabilities (TargetPlatformCapabilities): TargetPlatformCapabilities to optimize the PyTorch model according to.
         Returns:
@@ -85,7 +83,7 @@ if FOUND_TORCH:
                                 representative_data_gen,
                                 core_config,
                                 target_platform_capabilities,
-                                fw_info,
+                                DEFAULT_PYTORCH_INFO,
                                 fw_impl)
 else:

{mct-nightly-1.11.0.20240313.post405 → mct-nightly-1.11.0.20240315.post349}/model_compression_toolkit/core/quantization_prep_runner.py RENAMED Viewed

@@ -68,7 +68,7 @@ def quantization_preparation_runner(graph: Graph,
                         fw_info,
                         core_config.quantization_config)  # Mark points for statistics collection
-    for _data in tqdm(representative_data_gen(), "Statistics Collection:"):
+    for _data in tqdm(representative_data_gen(), "Statistics Collection"):
         mi.infer(_data)
     if tb_w is not None:

{mct-nightly-1.11.0.20240313.post405 → mct-nightly-1.11.0.20240315.post349}/model_compression_toolkit/gptq/keras/quantization_facade.py RENAMED Viewed

@@ -113,12 +113,10 @@ if FOUND_TF:
                                  regularization_factor=regularization_factor)
-    def keras_gradient_post_training_quantization(in_model: Model,
-                                                  representative_data_gen: Callable,
+    def keras_gradient_post_training_quantization(in_model: Model, representative_data_gen: Callable,
                                                   gptq_config: GradientPTQConfig,
                                                   gptq_representative_data_gen: Callable = None,
                                                   core_config: CoreConfig = CoreConfig(),
-                                                  fw_info: FrameworkInfo = DEFAULT_KERAS_INFO,
                                                   target_platform_capabilities: TargetPlatformCapabilities = DEFAULT_KERAS_TPC) -> Tuple[Model, UserInformation]:
         """
         Quantize a trained Keras model using post-training quantization. The model is quantized using a
@@ -142,7 +140,6 @@ if FOUND_TF:
             gptq_config (GradientPTQConfig): Configuration for using gptq (e.g. optimizer).
             gptq_representative_data_gen (Callable): Dataset used for GPTQ training. If None defaults to representative_data_gen
             core_config (CoreConfig): Configuration object containing parameters of how the model should be quantized, including mixed precision parameters.
-            fw_info (FrameworkInfo): Information needed for quantization about the specific framework (e.g., kernel channels indices, groups of layers by how they should be quantized, etc.). `Default Keras info <https://github.com/sony/model_optimization/blob/main/model_compression_toolkit/core/keras/default_framework_info.py>`_
             target_platform_capabilities (TargetPlatformCapabilities): TargetPlatformCapabilities to optimize the Keras model according to.
         Returns:
@@ -192,7 +189,7 @@ if FOUND_TF:
         """
         KerasModelValidation(model=in_model,
-                             fw_info=fw_info).validate()
+                             fw_info=DEFAULT_KERAS_INFO).validate()
         if core_config.mixed_precision_enable:
             if not isinstance(core_config.mixed_precision_config, MixedPrecisionQuantizationConfig):
@@ -200,14 +197,14 @@ if FOUND_TF:
                              "MixedPrecisionQuantizationConfig. Please use keras_post_training_quantization "
                              "API, or pass a valid mixed precision configuration.")  # pragma: no cover
-        tb_w = init_tensorboard_writer(fw_info)
+        tb_w = init_tensorboard_writer(DEFAULT_KERAS_INFO)
         fw_impl = GPTQKerasImplemantation()
         tg, bit_widths_config, hessian_info_service = core_runner(in_model=in_model,
                                                                   representative_data_gen=representative_data_gen,
                                                                   core_config=core_config,
-                                                                  fw_info=fw_info,
+                                                                  fw_info=DEFAULT_KERAS_INFO,
                                                                   fw_impl=fw_impl,
                                                                   tpc=target_platform_capabilities,
                                                                   tb_w=tb_w)
@@ -217,7 +214,7 @@ if FOUND_TF:
                               gptq_config,
                               representative_data_gen,
                               gptq_representative_data_gen if gptq_representative_data_gen else representative_data_gen,
-                              fw_info,
+                              DEFAULT_KERAS_INFO,
                               fw_impl,
                               tb_w,
                               hessian_info_service=hessian_info_service)

{mct-nightly-1.11.0.20240313.post405 → mct-nightly-1.11.0.20240315.post349}/model_compression_toolkit/qat/keras/quantization_facade.py RENAMED Viewed

@@ -89,7 +89,6 @@ if FOUND_TF:
                                                             representative_data_gen: Callable,
                                                             core_config: CoreConfig = CoreConfig(),
                                                             qat_config: QATConfig = QATConfig(),
-                                                            fw_info: FrameworkInfo = DEFAULT_KERAS_INFO,
                                                             target_platform_capabilities: TargetPlatformCapabilities = DEFAULT_KERAS_TPC):
         """
          Prepare a trained Keras model for quantization aware training. First the model quantization is optimized
@@ -111,7 +110,6 @@ if FOUND_TF:
              representative_data_gen (Callable): Dataset used for initial calibration.
              core_config (CoreConfig): Configuration object containing parameters of how the model should be quantized, including mixed precision parameters.
              qat_config (QATConfig): QAT configuration
-             fw_info (FrameworkInfo): Information needed for quantization about the specific framework (e.g., kernel channels indices, groups of layers by how they should be quantized, etc.).  `Default Keras info <https://github.com/sony/model_optimization/blob/main/model_compression_toolkit/core/keras/default_framework_info.py>`_
              target_platform_capabilities (TargetPlatformCapabilities): TargetPlatformCapabilities to optimize the Keras model according to.
          Returns:
@@ -159,7 +157,7 @@ if FOUND_TF:
              Pass the model, the representative dataset generator, the configuration and the target KPI to get a
              quantized model:
-             >>> quantized_model, quantization_info, custom_objects = mct.qat.keras_quantization_aware_training_init_experimental(model, repr_datagen, kpi, core_config=config)
+             >>> quantized_model, quantization_info, custom_objects = mct.qat.keras_quantization_aware_training_init_experimental(model, repr_datagen, kpi, core_config=core_config)
              Use the quantized model for fine-tuning. For loading the model from file, use the custom_objects dictionary:
@@ -174,7 +172,7 @@ if FOUND_TF:
                        f"project https://github.com/sony/model_optimization")
         KerasModelValidation(model=in_model,
-                             fw_info=fw_info).validate()
+                             fw_info=DEFAULT_KERAS_INFO).validate()
         if core_config.mixed_precision_enable:
             if not isinstance(core_config.mixed_precision_config, MixedPrecisionQuantizationConfig):
@@ -182,7 +180,7 @@ if FOUND_TF:
                              "MixedPrecisionQuantizationConfig. Please use keras_post_training_quantization API,"
                              "or pass a valid mixed precision configuration.")
-        tb_w = init_tensorboard_writer(fw_info)
+        tb_w = init_tensorboard_writer(DEFAULT_KERAS_INFO)
         fw_impl = KerasImplementation()
@@ -190,16 +188,16 @@ if FOUND_TF:
         tg, bit_widths_config, _ = core_runner(in_model=in_model,
                                                representative_data_gen=representative_data_gen,
                                                core_config=core_config,
-                                               fw_info=fw_info,
+                                               fw_info=DEFAULT_KERAS_INFO,
                                                fw_impl=fw_impl,
                                                tpc=target_platform_capabilities,
                                                tb_w=tb_w)
-        tg = ptq_runner(tg, representative_data_gen, core_config, fw_info, fw_impl, tb_w)
+        tg = ptq_runner(tg, representative_data_gen, core_config, DEFAULT_KERAS_INFO, fw_impl, tb_w)
         _qat_wrapper = partial(qat_wrapper, qat_config=qat_config)
         qat_model, user_info = KerasModelBuilder(graph=tg,
-                                                 fw_info=fw_info,
+                                                 fw_info=DEFAULT_KERAS_INFO,
                                                  wrapper=_qat_wrapper,
                                                  get_activation_quantizer_holder_fn=partial(get_activation_quantizer_holder,
                                                                                             qat_config=qat_config)).build_model()

{mct-nightly-1.11.0.20240313.post405 → mct-nightly-1.11.0.20240315.post349}/model_compression_toolkit/qat/pytorch/quantization_facade.py RENAMED Viewed

@@ -77,7 +77,6 @@ if FOUND_TORCH:
                                                               representative_data_gen: Callable,
                                                               core_config: CoreConfig = CoreConfig(),
                                                               qat_config: QATConfig = QATConfig(),
-                                                              fw_info: FrameworkInfo = DEFAULT_PYTORCH_INFO,
                                                               target_platform_capabilities: TargetPlatformCapabilities = DEFAULT_PYTORCH_TPC):
         """
          Prepare a trained Pytorch model for quantization aware training. First the model quantization is optimized
@@ -99,7 +98,6 @@ if FOUND_TORCH:
              representative_data_gen (Callable): Dataset used for initial calibration.
              core_config (CoreConfig): Configuration object containing parameters of how the model should be quantized, including mixed precision parameters.
              qat_config (QATConfig): QAT configuration
-             fw_info (FrameworkInfo): Information needed for quantization about the specific framework (e.g., kernel channels indices, groups of layers by how they should be quantized, etc.).  `Default Pytorch info <https://github.com/sony/model_optimization/blob/main/model_compression_toolkit/core/pytorch/default_framework_info.py>`_
              target_platform_capabilities (TargetPlatformCapabilities): TargetPlatformCapabilities to optimize the Pytorch model according to.
          Returns:
@@ -150,7 +148,7 @@ if FOUND_TORCH:
                              "MixedPrecisionQuantizationConfig. Please use pytorch_post_training_quantization API,"
                              "or pass a valid mixed precision configuration.")
-        tb_w = init_tensorboard_writer(fw_info)
+        tb_w = init_tensorboard_writer(DEFAULT_PYTORCH_INFO)
         fw_impl = PytorchImplementation()
         # Ignore trace hessian service as we do not use it here
@@ -162,12 +160,12 @@ if FOUND_TORCH:
                                                tpc=target_platform_capabilities,
                                                tb_w=tb_w)
-        tg = ptq_runner(tg, representative_data_gen, core_config, fw_info, fw_impl, tb_w)
+        tg = ptq_runner(tg, representative_data_gen, core_config, DEFAULT_PYTORCH_INFO, fw_impl, tb_w)
         _qat_wrapper = partial(qat_wrapper, qat_config=qat_config)
         qat_model, user_info = PyTorchModelBuilder(graph=tg,
-                                                   fw_info=fw_info,
+                                                   fw_info=DEFAULT_PYTORCH_INFO,
                                                    wrapper=_qat_wrapper,
                                                    get_activation_quantizer_holder_fn=partial(
                                                        get_activation_quantizer_holder,

{mct-nightly-1.11.0.20240313.post405 → mct-nightly-1.11.0.20240315.post349}/setup.cfg RENAMED Viewed

@@ -1,6 +1,6 @@
 [metadata]
 description-file = README.md
-version = 1.11.0.20240313-000405
+version = 1.11.0.20240315-000349
 [egg_info]
 tag_build =