MLBEDSW-3602: Output mismatch on some mobilenet_v1 int8 and int16
- The failing tests contain operations with dynamic tensors which
are not supported and therefore they should be placed on the CPU.
However, a bug in the removal of RESHAPEs which contain a dynamic
shape prevented this happening.
- This change adds a check to make sure that RESHAPE ops with a
dynamic shape tensor are not removed and instead are placed on the
CPU.
Signed-off-by: Tim Hall <tim.hall@arm.com>
Change-Id: I2d7481f7f80f99a0f01df100d956933777e6875a
diff --git a/ethosu/vela/tflite_model_semantic.py b/ethosu/vela/tflite_model_semantic.py
index 51d1f07..b783bb7 100644
--- a/ethosu/vela/tflite_model_semantic.py
+++ b/ethosu/vela/tflite_model_semantic.py
@@ -160,7 +160,7 @@
valid, extra = constraint(op)
if not valid:
print(
- f"Warning: unsupported TensorFlow Lite semantics for {ext_type} '{op.name}'. Placing on CPU instead"
+ f"Warning: Unsupported TensorFlow Lite semantics for {ext_type} '{op.name}'. Placing on CPU instead"
)
print(f" - {constraint.__doc__}")
if extra: