Closed trylaarsdam closed 1 year ago
It looks like the solution was providing signatures to TF before the conversion to TFLite which sets a fixed input size. I used this notebook as a template: https://colab.research.google.com/gist/tiruk007/f05a6e2a47943ae1e04495f306ef5c71/58668.ipynb
Cancel that, the input and output dimension sizes are reporting as large negative numbers (about -160,000,000), so something is still up. I can convert and see in Netron that all the operations listed there are in all_ops_resolver, but it still crashes my Portenta H7
"This issue is being marked as stale due to inactivity. Remove label or comment to prevent closure in 5 days."
"This issue is being closed because it has been marked as stale for 5 days with no further activity."
Hi there,
I'm trying to run a 5 LSTM layer keras model on a Portenta H7, which when I translate it to TFLite requires the
SELECT_TF_OPS
option to be enabled. When I allocate tensors on the M7 core of the Portenta using a freshly generated TFLM library from this repo, I get the following error: From what I can tell, theCUSTOM
operation is actually referring to theStateless_While
operator in TFLite, as when I compile with the non-experimental converter it gives me errors about no support forStateless_While
when I do not haveSELECT_TF_OPS
enabled.Here is my model structure for reference: (linking since it's a very tall image) https://user-images.githubusercontent.com/50586094/236851325-cf519093-5fe1-4c6f-9663-545cb5a9ff88.png
So here are my questions:
Thanks