MuellerJY

Confusing Problems(Not a ndarray) occur when training wGAN with tensorflow.keras API : train_on_batch

9

Thanks to listen to my troubles! Previous issues on TensorFlow Issue: _https://github.com/tensorflow/tensorflow/issues/58429_ I hope more inspiration could be found here in Keras-team. I'm trying to train a wGAN with tensorflow.keras...

看到有人用中文留言了，所以我也就用中文了。 首先感谢您对这个代码构建的付出，谢谢！ 请教您一个问题：在cwgan-gp.py文件中 Line 106 和 Line 108这两个Input是否可以省略定义，直接沿用Line 68 和 Line 71里的定义，即 对于Line 110： img = self.generator([z_disc, label]) 不知道这样改动是否会影响generator和critic的训练。 期待您的回复，谢谢！

Problem occured when using model.refine

1

First of all, deeply appreciated to this contribution. Informed by the tutorial, I tried to use more girds in activation function approximation by `model.refine()` after training with less grids. However,...