Open chenchenxiong opened 5 years ago
I was wrong , the version of cuda is 8.0
I used cuda 7.5, cudnn 5.1, theano 0.9.0. But you should be able to run the code with cuda 8.0, cudnn 6.0, and theano 1.0.
Thank you very much!I still have some questions about your code. what is the role of this 'mask' in ‘K.cast(mask , K.floatx())’ , what is the value of the 'mask', and why it should be converted to float ?
I want to know the version of cuda that you have used, because the version of cuda that I have used is 2.0, but the aspect.log file that is running is different from yours. I checked the configuration file of theano. The above shows that the cuda version will get different results.