inputting dataset to development

astorfi / 3D-convolutional-speaker-recognition

:speaker: Deep Learning & 3D Convolutional Neural Networks for Speaker Verification

Apache License 2.0

780 stars 274 forks source link

inputting dataset to development #22

Closed lucasalin closed 6 years ago

lucasalin commented 6 years ago

Hi astorfi,

I'm trying to train my own data set on your model. Is there also an update for the development files to feed dataset from input_features.py? It looks like train_softmax.py still takes in an hdf5 file.

Thanks, Lucas

astorfi commented 6 years ago

Yes, please ignore that and feed your specific input customized for your dataset. HDF5 is not required. You only need to feed the data using feed_dict.