-
We have been exploring SimCLR as an auxiliary loss, but one could also just train SimCLR *directly*, skipping GANs entirely. One could probably use the official Google codebase, which already has TPU …
gwern updated
10 months ago
-
In CycleGAN implementation, [PyTorch-GAN/implementations/cyclegan/cyclegan.py](https://github.com/eriklindernoren/PyTorch-GAN/blob/master/implementations/cyclegan/cyclegan.py) line 180 and 181:
```py…
-
Hi! Thanks for the very neat training code!
In the generator training part (line 142 of train.py). Shouldn't you be updating the parameters of encoder network instead of the decoder (referred to as…
-
I was trying to train for the first time using the example:
"python train.py --name cat_train_5 --batch 16 --dataroot_sketch ./data/sketch/by_author/cat --dataroot_image ./data/image/cat --l_image…
-
https://github.com/NVIDIA/BigVGAN?tab=readme-ov-file#news
-
### Metadata
- Authors: Zichao Yang, Zhiting Hu, Chris Dyer, Eric P. Xing, Taylor Berg-Kirkpatrick
- Organization: CMU and DeepMind
- Conference: NIPS 2018
- Paper: https://arxiv.org/pdf/1805.1174…
-
Thanks for such a modular project in easy to understand coding style ,i'm new to using github repositories for projects so my issue might seem naive .I did download the cifar 10 dataset into dataset d…
-
Hi authors:
This is a great work and I have some questions about the AE training process. In the paper, you mentioned that the training contains two stages: unsupervised training with unlabeled d…
-
So i have a simple GAN with dense layers and leakyReLU activation, nothing special.
When the GAN is training correctly and the generated samples look good, the training loss looks like this:
![image…
-
### Running Latest Version
- [X] I am running the latest version
### What do you want Mochi Diffusion to do?
Like in many webUIs, I'd love to find a "GFP-GAN" Face restoration option (with a % of s…