tensorflow.python.framework.errors_impl.InvalidArgumentError: Incompatible shapes: [12,2262,80] vs. [12,2000,80]
Closed this issue · 4 comments
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
@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).
@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.
@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.
Great, that works - thanks!!!