MLBEDSW-3004: UnpackReshaped can't be serialised
This commit fixes a bug where a rewritten Unpack
operator is placed on the CPU and crashes Vela
during serialisation due to the type having
changed and there not being a mapping for the
modified op type.
The solution is to move the fixup_unpack_output
function to the graph optimisation pass B,
allowing the supported op check to run before it.
Signed-off-by: Dwight Lidman <dwight.lidman@arm.com>
Change-Id: Ic6bd4c70a478fd61adf377cb487f5b9253130314
diff --git a/ethosu/vela/operation.py b/ethosu/vela/operation.py
index 710511c..6e5b482 100644
--- a/ethosu/vela/operation.py
+++ b/ethosu/vela/operation.py
@@ -314,7 +314,7 @@
class Operation:
"""Class representing a Neural Network operation. Has a name, a type,
-input and output tensors, as well as an attribute dictionary."""
+ input and output tensors, as well as an attribute dictionary."""
__slots__ = (
"type",