Comments (4)
Thanks for you repling. But i still don't understand.
I don't know why use temperature to balance adversarial training and class conditioning.
gen_acml_loss += self.contrastive_lambda*self.contrastive_criterion(cls_embed_fake, cls_proxies_fake, fake_cls_mask, fake_labels, t, self.margin)
did't this value (contrastive_lambda i ) already balanced them?
from pytorch-studiogan.
Hi,
The additional temperature (t) is multiplied for a balance between adversarial training and class conditioning.
However, as you can see in src/configs, all temperatures in ContraGAN.json are fixed at 1.0.
Sorry for the late reply.
Thank you.
from pytorch-studiogan.
Hello.
I noticed that multiplying both the temperature and self.contrastive_lambda is redundant.
I will revise the code in the main branch (actually it is already reflected in the renew_cfgs branch (worker.py line 293), which will officially be released at the end of this month).
Thank you.
from pytorch-studiogan.
OK.Thanks a lot
from pytorch-studiogan.
Related Issues (20)
- [CVPR 2023] Adding NoisyTwins Regularization to StyleGAN2 HOT 2
- how to instantiate a model, load a checkpoint and visualize some generated images? HOT 5
- Training a cGAN on MNIST HOT 3
- ContraGAN code HOT 1
- Can the latest pytorch be installed to avoide: Error of pip's dependency? HOT 1
- Segmentation fault (core dumped) HOT 1
- contraGan HOT 1
- CIFAR-10: Training set and test set for Pretrained checkpoints. HOT 1
- Evaluate.py ResNet50 Syntax Error
- DINO evaluation question HOT 1
- Building GAN with 96x96 images HOT 1
- PermissionError: [WinError 32] HOT 3
- Baby-ImageNet link is not working HOT 2
- Using 4 GPUs for training takes the same time as using just 1 HOT 1
- Possibility of Loading various checkpoints during --eval_backbone for ResNet50_torch HOT 3
- Ambiguity on the method used HOT 2
- Request: is it possible to add BigBiGAN (BigGan architecture with Encoder Network) ?
- ContraGAN model
- Generate synthetic images in Colab environment HOT 1
- DCGAN loss does not comply with literature
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from pytorch-studiogan.