yuliang-zou / tf_videogan Goto Github PK

I would like to ask you a question: the paper's video data is what kind of format as input, debugging the code is the key to those places?

您好：
这两天刚了解了一下GAN，无意中发现您写的这个项目，感觉挺好玩的，就复现了一下您的代码，说实话，目前还是有很多地方不太懂，现在有两个问题希望您能给我解答一下，感谢！
1：我好像在您的代码里面没看到图片的输入，请问生成的短视频是来源哪些图片，假如我现在想输入自己的一张图片，生成一段视频，该如何进行
2：我看到您的代码中的鉴别器函数是空的，看了DCGAN中的代码实现，发现有鉴别器函数，缺失这个函数会不会导致生成视频效果不理想
再次感谢！期待您的回信。

Hello, Yuliang. : ) @Yuliang-Zou
I have been searching for torch7 to tensorflow model converters these days, but there are many converters for other DL framework except for torch7. I know this could be done by hand and your code inspires me.
BTW, do you have an useful torch7 to tensorflow model converter? Thank you.

hello! Is there any pretrained models in your code? The video dataset is too large and I can't train a model from the very beginning. Thank you

Hi Zou, im a student of AI from China.It seems that you were interested in the condition generation model,my own reappearing model is not good so i want to ask if you have a pre-train model about this part? It will be very helpful for me, thank you so much!