Closed jamessergeant closed 7 years ago
As per the Lip Reading experiment in the paper, it would be ideal to have the ability to manually set and disable learning of Tau and s.
I'm currently having a go at it myself but am only new to TensorFlow. I have added a new boolean input argument to PhasedLSTMCell.
Based on this parameter being True, I've modified the following:
init_ops.constant_initializer
k = tf.select(tf.logical_or(is_up,is_down), tf.to_float(is_up), self.alpha * phi)
Would appreciate any comments on this method and am happy to contribute.
@Enny1991 FYI in case you haven't seen it https://channel9.msdn.com/Events/Neural-Information-Processing-Systems-Conference/Neural-Information-Processing-Systems-Conference-NIPS-2016/Phased-LSTM-Accelerating-Recurrent-Network-Training-for-Long-or-Event-based-Sequences
As per the Lip Reading experiment in the paper, it would be ideal to have the ability to manually set and disable learning of Tau and s.
I'm currently having a go at it myself but am only new to TensorFlow. I have added a new boolean input argument to PhasedLSTMCell.
Based on this parameter being True, I've modified the following:
init_ops.constant_initializer
in place of the random methods, setting each to tau_init and 0, respectively.Would appreciate any comments on this method and am happy to contribute.