wav2tfr infinite loop?

[wsr692]

ubuntu 16.04, Python 3.6.8, tensorflow-gpu 1.5.0, ffmpeg all installed,
but when running wav2tfr.py, sess.run seems to fall into a loop (like pasted below)

2019-02-18 13:18:28.817333: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1195] Creating TensorFlow device (/device:GPU:0) -> (device: 0, name: TITAN Xp, pci bus id: 0000:01:00.0, compute capability: 6.1)
2019-02-18 13:18:28.872601: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1195] Creating TensorFlow device (/device:GPU:0) -> (device: 0, name: TITAN Xp, pci bus id: 0000:01:00.0, compute capability: 6.1)
2019-02-18 13:18:28.919834: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1195] Creating TensorFlow device (/device:GPU:0) -> (device: 0, name: TITAN Xp, pci bus id: 0000:01:00.0, compute capability: 6.1)
2019-02-18 13:18:28.965536: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1195] Creating TensorFlow device (/device:GPU:0) -> (device: 0, name: TITAN Xp, pci bus id: 0000:01:00.0, compute capability: 6.1)

any insights on this issue?

[lmxyy]

I have the same issue but I haven't figured out why?

[lmxyy]

I found the issue was from tf.contrib.ffmpeg.decode_audio, but I haven't figured out why this function caused issues.