search

Walleclipse / Deep_Speaker-speaker_recognition_system

Keras implementation of ‘’Deep Speaker: an End-to-End Neural Speaker Embedding System‘’ (speaker recognition)
246 stars 81 forks source link

the problem when run pretraining.py #2

Closed zhangshyang closed 5 years ago

zhangshyang commented 5 years ago

In constants.py, I set the batch_size= 16. When run the pretraining.py, I always get the error which "tensorflow.python.framework.errors_impl.InvalidArgumentError: Inputs to operation training/Adam/gradients/AddN_2 of type _MklAddN must have the same size and shape. Input 0: [983040] != input 1: [48,10,4,512]". Who know it and help me.

Walleclipse commented 5 years ago
  1. You want to check the preprocessed data audio/LibriSpeechSamples/train-clean-100-npy/*.npy .and check the shape
  2. I think this may caused by tensorflow and keras version incompatibility.I used tensorflow-gpu==1.8.0