Closed flybirp closed 7 years ago
First, in the infoGAN tutorial, the tf.concat and tf.split still uses the old ordering of arguments. second, by running the code, after several iterations, the program generates NaN in Gen and Disc losses
Hi flybirp. I've edited the code to support TF1.0 syntax. Thanks for pointing it out.
First, in the infoGAN tutorial, the tf.concat and tf.split still uses the old ordering of arguments. second, by running the code, after several iterations, the program generates NaN in Gen and Disc losses