Implement Keras in LSTMCell (the class uses additional peep-hole connections, additional cell cut-off and additional projection layer).

Question

In my opinion, Keras LSTM cell is similar to Tensorflow

BasicLSTMCell (RNNCell) . However, I am looking for a Tensorflow implementation

LSTMCell (RNNCell) in Keras (LSTMCell: the class uses additional connections with punch holes, an additional compartment cut-off and an additional projection layer). https://github.com/tensorflow/tensorflow/blob/master/tensorflow/python/ops/rnn_cell_impl.py https://research.google.com/pubs/archive/43905.pdf Hasim Sack, Andrew Star and Francoise Böfeis . "Long-term short-term standby neural network memory architectures for large-scale acoustic modeling." INTERSPEECH, 2014.

I am wondering without writing a custom layer, is there any way to use this Tensorflow LSTMCell in Keras or is it already available?