Comments (3)
wanzysky
commented on August 30, 2024
If you aim at training with higher resolution, the answer is currently no. Nevertheless, inference on high-resolution images is supported by Laplace transformation. Try demo with your customized dataset to check it.
from psgan.
DanielMao2015
commented on August 30, 2024
@wanzysky Thanks for your reply!! I am curious about the reason about the impossibility. As I know, if I change the input size, and modify the size of AMM and other corresponding hyperparameter, why is it impossible to produce high resolution? By the way, I have no idea how to inference on high-resolution with Laplace transformation, it would be appreciated of you to provide some explanation or some links. Thank you !!
from psgan.
wanzysky
commented on August 30, 2024
The main reason against the higher resolution is the limitation of GPU memory. Laplace transformation has been implemented in psgan/postprocess.py. It is actually a direct idea to alleviate the distortion caused by bilinear interpolation.
from psgan.
Related Issues (20)
- Download training dataset HOT 8
- landmark and segments file HOT 3
- partial makeup example HOT 3
- Test result HOT 4
- CUDA out of memory HOT 6
- Histogram loss on lip and eyes HOT 10
- PSGAN++ HOT 3
- about 'affine' param in InstanceNorm2d HOT 1
- white spots in the generated image HOT 5
- 如果使用自己的数据集训练 seg与landmark如何生成 HOT 1
- Download makeup-wild Dataset HOT 2
- Error occurred when i run demo.py HOT 5
- how to get attention map? HOT 1
- RuntimeError: 'weight' must be 2-D HOT 1
- Some advice about license compliance
- Histogram Loss Doesn't Match Paper
- How do I get the png image under the landmark folder
- training result is not good
- How to convert to ONNX?
- ImportError: cannot import name 'load_state_dict_from_url' from 'torchvision.models.vgg'
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 psgan.