LSTM tensorflow to caffe error

[yulinhuyang]

Platform (like ubuntu 16.04/win10):ubuntu 16.04

Python version: 3.6

Source framework with version (like Tensorflow 1.4.1 with GPU): tensorflow

Destination framework with version (like CNTK 2.3 with GPU): caffe

Pre-trained model path (webpath or webdisk path): LSTM

Running scripts:mmconvert -sf tensorflow -iw speaker_detection_model9472.pb --inNodeName input --inputShape 1,25,1 --dstNodeName softmax/Softmax -df caffe -om tf_speak

[XiaoXYe]

@yulinhuyang ,thank you for your feedback, MMdnn caffe emitter doesnt have RNN related operations support currently