Using YAMNet in android

[paleomoon]

System information

• Have I written custom code (as opposed to using a stock example script provided in TensorFlow): N/A
• OS Platform and Distribution (e.g., Linux Ubuntu 16.04): N/A
• Mobile device (e.g., Pixel 4, Samsung Galaxy 10) if the issue happens on mobile device: Android 9
• TensorFlow installed from (source or binary): source
• TensorFlow version (use command below): 1.13.1
• Python version: 3.6
• Bazel version (if compiling from source): 0.19.1
• GCC/Compiler version (if compiling from source): N/A
• CUDA/cuDNN version: N/A
• GPU model and memory: N/A
• NDK: r18b

Please provide the entire URL of the model you are using?

https://github.com/tensorflow/models/tree/master/research/audioset/yamnet Describe the current behavior I'm using YAMNet in android, I compiled Tensorflow 1.13 from source in Ubuntu 16.04 for android platform, so I can use native c++ to do inference in android. But now I get no output of YAMNet. This is the logcat in android studio, seems the 'RFFT' op is not supported?

D/Mudra: Graph /data/user/0/com.example.sd/cache/yamnet.pb read successfully! 
I/Mudra: Create TensorFlow Session: Invalid argument: No OpKernel was registered to support Op 'RFFT' used by {{node log_mel_features/stft/rfft}}with these attrs: []
    Registered devices: [CPU]
    Registered kernels:
      <no registered kernels>

         [[{{node log_mel_features/stft/rfft}}]]

Describe the expected behavior I test the pb model in windows, tensorflow 1.14, it works fine. Code to reproduce the issue

N/A Other info / logs

N/A

[paleomoon]

It seems to be a tf version problem, I will try to compile tf 1.14 again, though failed before.