Comments (14)
I fixed another issue and retrained horse2zebra. The results are quite promising.
A screenshot after 87 epochs:
from cyclegan-tensorflow.
@TX2012LH just 1 line but critical 960d1b0. G and F of cycle loss were reversed 😳
from cyclegan-tensorflow.
Thank you for your information.
I've just realized that my implementation of PatchGAN was incorrect and I'm working on it.
Regards,
from cyclegan-tensorflow.
Thanks, this work is very meaningfull, cause original can not even predict single image, If you worked out, update repo let me know, I'd like to follow this project.
from cyclegan-tensorflow.
Hey man, thanks for your awesome repository. Everything is set up awesomely, Tensorboard and all, and I'd love to get this to work.
Unfortunately, I can confirm @jinfagang observation that the resulting models are not good at all. I spent like 20 USD on an AWS EC2 GPU instance until I realized this. Maybe until you fix this issue, mention this in the readme so other people don't waste their time as well.
Thanks!
from cyclegan-tensorflow.
I've removed the wrong part of PatchGAN and now the results should be better. But it takes time to confirm.
from cyclegan-tensorflow.
@
Would you add some test image result for current made? Have some sample result could be better I think.
from cyclegan-tensorflow.
Results on training set after 37 epochs.
- apple2orange:
- orange2apple:
from cyclegan-tensorflow.
I tried on horse2zebra dataset but the results are still blurry. Maybe it is more difficult to translate horse2zebra than orange2apple.
Did you train horse2zebra with the original pytorch version?
from cyclegan-tensorflow.
I have trained original summer2winter and apple2orange, both get in some level fair result, at least the resolution are more clear.
from cyclegan-tensorflow.
@vanhuyz Hi, I also managed predict using original torch version and reconstruct a production version, here is the repo https://github.com/jinfagang/pytorch_cycle_gan, I have some results, seems original still more clear, what did you see? Maybe we can discuss about the difference detail, do you have wechat ?
from cyclegan-tensorflow.
What does the another issue
mean? Could you please point it out specifically?
from cyclegan-tensorflow.
@jinfagang Sorry I don't have wechat. How about via email?
from cyclegan-tensorflow.
This is my email [email protected], you can send me some information
from cyclegan-tensorflow.
Related Issues (20)
- Missing the ngf parameter for F generator HOT 2
- CPU 100%, but training never starts HOT 2
- verbosity error HOT 4
- can be used to remove the watermark ? HOT 1
- Nothing in cityscapes downloaded by download_dataset.sh HOT 1
- Error happen trying to export. HOT 1
- Control dependencies in CycleGAN optimizer
- image size, default: 256
- 怎么使用预训练的模型啊
- Observing backward pass while running inference.py with a pb file, which is consuming lot of time
- NO FILE IN THE Checkpoints AFTER Train
- ops.py重的Instance Normalization是不是有个地方搞错了? HOT 2
- Use python train.py --load_model XXXX problem
- can this
- Can this code work with gray scale image or rectangle img?
- How to deal with high contrast background colors?
- How to convert the ckpt model into savedmodel HOT 1
- The training doesn't start
- Training doesn't start HOT 1
- pretrained examples: freezed or not? any data preprocessing?
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 cyclegan-tensorflow.