Zhu, Lingchen

icon indicating a website link https://zhulingchen.github.io/

icon company Schlumberger icon location Cambridge, MA, USA icon location Senior Research Scientist at Schlumberger - Doll Research

Results 2 comments of Zhu, Lingchen

This code is outdated seriously

Hi ylmao, I implemented my version of Info-Wasserstein-GAN-Gradient Penalty-Consistency Term (Info-WGAN-GP-CT) in my repository: https://github.com/zhulingchen/deep-generative-models with Keras and TensorFlow (tested under the platform os Ubuntu 18.04 LTS, CUDA 9.2, cuDNN...

Variable <tf.Variable 'conv2d_flipout_3/kernel_posterior_loc:0' shape=(3, 3, 1, 32) dtype=float32> has `None` for gradient. Please make sure that all of your ops have a gradient defined (i.e. are differentiable). Common ops without gradient: K.argmax, K.round, K.eval.

Hi Xi, I have encountered the same problem at the very beginning of this journey: Please take a look at this issue I sent to the TFP team: https://github.com/tensorflow/probability/issues/511 Hope...