-
I'm tweaking the code to do somewhat of a trivial example: Essentially running any image (in this case a scene, and not a texture), through the AdaIN, and having the style and content be the same imag…
-
190126~
-
Hi guys, I'm wondering about the possibility of training the models on 1 face only instead of 2.
The actual workflow makes it mandatory to train a model for a specific src/target pair which is not…
Clorr updated
6 years ago
-
## Generative Adversarial Networks(生成对抗网络)
- They are ML model that can image new things.
### Application(应用)
- GAN可以用于生成逼真的数据
- 例如说STACKGAN Model，它可以接收文本形式的描述，然后根据那个描述来生成相应的图片（这些图片都是被新创造出来的，不是从…
-
### 論文へのリンク
[[arXiv:2003.02683] Image Generation from Freehand Scene Sketches](https://arxiv.org/abs/2003.02683)
### 著者・所属機関
Chengying Gao, Qi Liu, Qi Xu, Jianzhuang Liu, Limin Wang, Changqin…
-
Tried different size of input images (including the examples at the bottom of the page) nothing seems to work. It calculates first then I just get an "Error" message. Tried CPU and GPU. Tried differen…
-
First of all, thanks for the code sharing.
I've been try to test cdeep3m with docker.
training(+retraining with pre-trained model) with my own dataset was just fine.
I'm faced octave error whe…
-
-
With the help of your advice, I reproduced the main part of the paper and succeed in training your model to ImageNet with specific classes, minibus, dog.
Now, I try to reproduce **6.8 conditional i…
-
### Is there an existing issue for this?
- [X] I have searched the existing issues and checked the recent builds/commits
### What happened?
since SD came out until yesterday I was able to gen…