chunseoklee

@seanshpark Do you have any idea how to identify node index with multiple subgraph ? (AFAIK, each subgraph has its own indices starting at 0 )

ref : https://gcc.gnu.org/gcc-11/porting_to.html > Header dependency changes Some C++ Standard Library headers have been changed to no longer include other headers that were being used internally by the library. As...

Considering the objective in https://github.com/Samsung/ONE/projects/9( _"RNN Model with single while loop of non-dynamic tensor"_ ), while loop is required.

In Candidate 2, by replacing GRU with LSTM, we will get a model without WHILE and with UnidirectionalLSTM, which is an operation on TFLite. [model_LSTM_keras.zip](https://github.com/Samsung/ONE/files/8377917/model_LSTM_keras.zip)

cc @ragmani I tried to obtain full(w8a8) quantized model as the follows, but fail to get full quantized one. ```python3 # !pip install tensorflow==2.7.0 import numpy as np import tensorflow...

@ragmani https://github.com/Samsung/ONE/files/9630977/model_body.0.import.0.opt.zip consists of two graphs.

> > @ragmani , I can't distinghish by the diff, what module has changed? > > > > I haven't changed any modules. I just added `;` at the end...

> concrete example You mean a set of partitioned circle and partitioned tvn from a source circle file ? Since there is no tool for that. We need to generate...

@binarman IMHO, We need to make sure that our target model will be generated in the way we have done. Have you heard anything about this ?

> @chunseoklee , PTAL at above GRU model for OneRT. If this op is passed as custom op, ONERT can process it by implementing it(not that hard). But, at a...