-
Notifications
You must be signed in to change notification settings - Fork 76
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Error with nntool with keras recurrent models #253
Comments
Follow-up: I can produce the same error when trying to use a vanilla LSTM model:
Therefore the problem does not seem to be associated with the custom NCP model I was using. I am going to update the title of the post to reflect this. Does |
I've also tried |
Further information, I've tried converting to |
Could you send us a failing tflite file please. We support both LSTM and RNN import from TFLITE. |
Attached is a zip file that contains the tflite file: To reproduce (overwrite the existing
|
The TFLITE converter is not converting the model correctly. THe LSTM layer is not being converted to a fused TFLITE LSTM operator. Please take a look at https://www.tensorflow.org/lite/convert/rnn. Particularly the notebook referenced on the page. Using netron you should see no while operators in the TFLITE graph. |
Thank you! This seems to be the right direction. I've successfully converted an LSTM using nntool. |
My issue is similar in theme to issue #247, however it results in a completely different error, thus I wanted to open a separate issue.
I am attempting port a custom keras model to GAP8 with
nntool
. For whatever it's worth, the model is a "neural circuit policy" built with thekeras-ncp
library which uses a modifiedAbstractRNNCell
.I can successfully convert my trained model to
.tflite
using a slightly modified version ofh5_to_tflite.py
. However, when I attempt to open the.tflite
model withnntool
, I get the errorI am not sure if this is a bug I need to debug within the
keras-ncp
library or if it is something that needs to be debugged withinnntool
library, so I am asking in both places in the hopes someone might perceive a simple fix.The text was updated successfully, but these errors were encountered: