search

syang1993 / gst-tacotron

A tensorflow implementation of the "Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis"
368 stars 110 forks source link

tensorflow.python.framework.errors_impl.InvalidArgumentError: Incompatible shapes: [12,2262,80] vs. [12,2000,80] #30

Closed ErnstTmp closed 5 years ago

ErnstTmp commented 5 years ago

Hi, thank you very much for creating Tacotron GST!

I have to run on Titan X, and I had to change the batchsize to 16.

after 32 iteration I get

tensorflow.python.framework.errors_impl.InvalidArgumentError: Incompatible shapes: [12,2262,80] vs. [12,2000,80]

Have you seen this before? I am running Tensorflow 1.12. Thanks and kind regards Ernst

syang1993 commented 5 years ago

@ErnstTmp Hi, it is because your data is too long. outputs_per_step * max_iters is the maximum number of training data. Your can change the max_iters to fit your data or throw these too long data (if there are only a little long sentences).

ErnstTmp commented 5 years ago

@syang1993: thanks a lot for the fast answer. I forget to mention I am trying the blizzard2013 dataset. I changed max_iters from 1000 to 600, ut I got the same error.

syang1993 commented 5 years ago

@ErnstTmp It's the maximum number of your data, you should increase the max_iters. Or you can decrease the _max_out_length to make it less than 2000 in blizzard2013.py.

ErnstTmp commented 5 years ago

Great, that works - thanks!!!