-
Hello,
I have almost no knowledge regarding GANs but the possibly megalomaniac idea of training a GAN to create landscapes based on my own dataset of landscapes. From the example images you have up…
czkaa updated
4 years ago
-
Hi!
I tried the example and felt very cool!
But when I trained my model, an error occurred in batch = [1501/20695].
The content is as follows:
--------------- ------------------ ------------------…
-
["Improving GAN Training with Probability Ratio Clipping [PPO] and Sample Reweighting", Wu et al 2020](https://arxiv.org/abs/2006.06900)/["Top-_k_ Training of GANs: Improving GAN Performance by Throwi…
gwern updated
3 years ago
-
[ARGAN: Fast Converging GAN for Animation Style Transfer](https://ieeexplore.ieee.org/document/9738752)
This works seems simply copy the work from AnimeGAN. The network architecture and losses desi…
-
Overview: Showcasing a prototype that uses GANs to auto-generate 3D models using multi-point 2D images.
Use Cases:
1. Using an image captured from depth cameras to a create precise 3D objects
2…
-
I am using train_dcgan.py to train the network over outdoor_64 images. However, after about 10 epochs of training, the generated images by the network become gray. Here is an example output file:
![…
-
### 上周工作
1.这篇论文Multi-Content GAN for Few-Shot Font Style Transfer翻译完了。
2.看了李宏毅的关于GAN网络的部分视频。
3.看了[深度 | 从入门到精通：卷积神经网络初学者指南（附论文）](https://mp.weixin.qq.com/s?__biz=MzA3MzI4MjgzMw==&mid=2650717691&idx=…
-
論文: https://arxiv.org/abs/1706.07068
ブログ: https://hackernoon.com/can-creative-adversarial-network-explained-1e31aea1dfe8
Artについて、創造的な絵をGenerateするGAN. 従来のGANはDiscreminatorからreal/fakeの判定結果をGenerator…
-
Hi~ thank you for converting styleGAN to its pytorch version, which is pretty meaningful. I've noticed that there are some people who can not get resonable training results. Unfortunately, i am one o…
-
Hi, I was kind of confused why the self.G_loss only contains the feature loss and the style loss?
If so, i think it might not be a GAN's advresarial training process, because you only update the par…