NXP backend: Turn off bias tensor reuse in Convolution converter

roman-janik-nxp · robert-kalmar · commit 9614a3f24622 · 2025-09-09T22:45:54.000+02:00
diff --git a/backends/nxp/backend/ir/converter/node_converters/ops_converters/convolution_converter.py b/backends/nxp/backend/ir/converter/node_converters/ops_converters/convolution_converter.py
@@ -263,7 +263,7 @@ def _convert_unpadded_2D(
                 )
 
             b = self.builder.create_zeros_tensor(
-                [output_channels], "zero_bias", bias_type, True
+                [output_channels], "zero_bias", bias_type, False
             )
 
             # Compute scale and zero point for bias tensor

Original file line number	Diff line number	Diff line change
`@@ -263,7 +263,7 @@ def _convert_unpadded_2D(`
`263`	`263`	`)`
`264`	`264`
`265`	`265`	`b = self.builder.create_zeros_tensor(`
`266`		`- [output_channels], "zero_bias", bias_type, True`
	`266`	`+ [output_channels], "zero_bias", bias_type, False`
`267`	`267`	`)`
`268`	`268`
`269`	`269`	`# Compute scale and zero point for bias tensor`