Does TenserRT2.1 support the LSTM layer with peephole and projection, like the one described in the paper: “Long Short-Term Memory Recurrent Neural Network Architectures for Large Scale Acoustic Modeling”?
Thank you : )
Does TenserRT2.1 support the LSTM layer with peephole and projection, like the one described in the paper: “Long Short-Term Memory Recurrent Neural Network Architectures for Large Scale Acoustic Modeling”?
Thank you : )