MLBEDSW-4913 Fix inception_v1/v3 output diff

Fix inception_v1/v3 output diffs.
Removing the Squeeze operator in the graph optimisation step.
The squeeze operator removes dimensions of size 1 from tensor shape.
The memory layout is preserved.

Signed-off-by: Jonas Ohlsson <jonas.ohlsson@arm.com>
Change-Id: I4ceffcbb141af5ed50b0d1a9d1d67622e638c2a1
diff --git a/ethosu/vela/tflite_supported_operators.py b/ethosu/vela/tflite_supported_operators.py
index dc4e6f0..016d44e 100644
--- a/ethosu/vela/tflite_supported_operators.py
+++ b/ethosu/vela/tflite_supported_operators.py
@@ -86,7 +86,7 @@
     )
     split_ops = set((Op.Split, Op.SplitV, Op.StridedSlice, Op.Slice, Op.UnpackReshaped, Op.Unpack,))
     concat_ops = set((Op.Concat, Op.ConcatTFLite, Op.PackReshaped, Op.Pack,))
-    memory_only_ops = set((Op.Reshape, Op.QuantizedReshape,)) | concat_ops | split_ops
+    memory_only_ops = set((Op.Reshape, Op.QuantizedReshape, Op.Squeeze,)) | concat_ops | split_ops
     per_axis_quant_ops = convolution_like_ops  # per-axis/channel quantization only currently supported for conv ops
     supported_fused_activations = relu_ops | set((Op.Tanh, Op.Sigmoid, Op.LUT,))
     supported_operators = npu_pre_ops | mac_main_ops | elem_wise_main_ops | pad_ops | npu_post_ops | memory_only_ops