[ MO ] Put FQ fuses under the disable_fusing key (#4829)

model-optimizer/extensions/middle/ReluQuantizeFuse.py

@@ -34,6 +34,7 @@ class ReluFakeQuantizeMark(MiddleReplacementPattern):
 
     """
     enabled = True
+    graph_condition = [lambda graph: not graph.graph['cmd_params'].disable_fusing]
 
     def run_after(self):
         return [BinarizeWeightsM1P1]

model-optimizer/extensions/middle/fusings.py

@@ -99,11 +99,12 @@ class Fusing(MiddleReplacementPattern):
         for_graph_and_each_sub_graph_recursively(graph, normalize_eltwise_inputs)
         for_graph_and_each_sub_graph_recursively(graph, lambda G: G.clean_up())
 
-        MarkNodesToFuseUpToFakeQuantize().find_and_replace_pattern(graph)
-        FakeQuantizeFuse().find_and_replace_pattern(graph)
-        AddFakeQuantizeFuse().find_and_replace_pattern(graph)
-        MulFakeQuantizeFuse().find_and_replace_pattern(graph)
-        for_graph_and_each_sub_graph_recursively(graph, lambda G: G.clean_up())
+        if not argv.disable_fusing:
+            MarkNodesToFuseUpToFakeQuantize().find_and_replace_pattern(graph)
+            FakeQuantizeFuse().find_and_replace_pattern(graph)
+            AddFakeQuantizeFuse().find_and_replace_pattern(graph)
+            MulFakeQuantizeFuse().find_and_replace_pattern(graph)
+            for_graph_and_each_sub_graph_recursively(graph, lambda G: G.clean_up())
 
         for_graph_and_each_sub_graph_recursively(graph, fuse_pad)
         for_graph_and_each_sub_graph_recursively(graph, lambda G: G.clean_up())

model-optimizer/extensions/middle/quantize_fuses.py

@@ -31,6 +31,7 @@ class MarkNodesToFuseUpToFakeQuantize(MiddleReplacementPattern):
 
     """
     enabled = True
+    graph_condition = [lambda graph: not graph.graph['cmd_params'].disable_fusing]
 
     def run_after(self):
         return [DeleteControlFlowEdges]
@@ -83,6 +84,7 @@ class FakeQuantizeFuse(MiddleReplacementPattern):
             replacer duplicates node to fuse (duplicate connections of inputs of node to fuse to duplicates of it)
     """
     enabled = True
+    graph_condition = [lambda graph: not graph.graph['cmd_params'].disable_fusing]
 
     def run_after(self):
         return [MarkNodesToFuseUpToFakeQuantize]