Anastasiia

Results 12 comments of Anastasiia

[RNN] Stateful LSTM can't be converted to TF Lite with Integer Quantization

[LSTMlayer.txt](https://github.com/tensorflow/tensorflow/files/7049052/LSTMlayer.txt) Please rename this file to .onnx, because I can't upload .onnx file to github.

[RNN] Stateful LSTM can't be converted to TF Lite with Integer Quantization

Hi @lintian06, Thank you for your attention! I've seen those articles and colab. In the article in the part "Known issues/limitations" actually written: > 1. Currently there is support only...

[RNN] Stateful LSTM can't be converted to TF Lite with Integer Quantization

Hi @lintian06 , I have tried to do something similar by "fixing" the size of the input variables with concrete_function (code based on [collab](https://colab.research.google.com/github/tensorflow/tensorflow/blob/master/tensorflow/lite/examples/experimental_new_converter/Keras_LSTM_fusion_Codelab.ipynb)): ``` model = tf.keras.models.Sequential([ tf.keras.layers.LSTM(20, stateful=True,...

[RNN] Stateful LSTM can't be converted to TF Lite with Integer Quantization

Hi @jakobwowy, Thank you for this link, I'll try it. Regarding NN with multiple LSTM layers: I had a similar problem in the onnx_tf convertor and I used a workaround...

[RNN] Stateful LSTM can't be converted to TF Lite with Integer Quantization

Unfortunately, this solution didn't help me because I need to work with format converted from ONNX (TensorFlowRep) - it's not Keras...

[RNN] Stateful LSTM can't be converted to TF Lite with Integer Quantization

Hi @lintian06, Could you please provide an example of > defining a signature_def specifying inputs and outputs when exporting a saved model when I don't have a Keras model? Only...

[RNN] Stateful LSTM can't be converted to TF Lite with Integer Quantization

Hi @lzc16 , Unfortunately, no. Issue isn't solved. In my case failure is in the process of conversion.

[RNN] Stateful LSTM can't be converted to TF Lite with Integer Quantization

Hi @lzc16 , I have managed to convert my model using the nightly version. But I also have an error in the runtime. ``` Could not find variable lstm_kernel_lstm_31. This...

[RNN] Stateful LSTM can't be converted to TF Lite with Integer Quantization

Hi @lzc16 , I have the same path - 'torch -> onnx -> tflite' so I can't use keras. I just trying to find a solution or some workaround. Best...

[RNN] Stateful LSTM can't be converted to TF Lite with Integer Quantization

Hi @lzc16, I can see from that [issue ](https://github.com/tensorflow/tensorflow/issues/52041) that the problem was in onnx-tf conversion. In my case, the TF model works ok, and the TFLite model with float16...