SheenaF.

Hi, thanks for the quick response. I think it's common to have a bias vector per layer or one (float) value per neuron in the layer. I was checking out...

Yes, I substituted it with sigmoid and relu and they didn't get an error.

I tried substituting the LSTM layer with the GRU as well, but it gave the same error. I also closely followed this implementation here: https://colab.research.google.com/github/tensorflow/tensorflow/blob/master/tensorflow/lite/examples/experimental_new_converter/Keras_LSTM_fusion_Codelab.ipynb#scrollTo=tB1NZBUHDogR but to no avail. :(

Thanks a lot! That will be very helpful.

> @expeon07 could you please share with me the code for converting the LSTM model to TFLite? I have not succeeded in the conversion. Thank you Hi, I unrolled the...

> @expeon07 please I am not getting it clear. Is that turning of unroll=True (default to false) was done during model training of during model conversion (TFliteConverter)? kindly, I request...

Hi, I am also having a problem with loading my tensorflow model with a Lattice layer. My model was able to compile and predict without a problem, and I saved...