Comments (2)
It seems I can change the selection of 5 attributes in data_loader.py.
What changes would be required if I want to add more than 5?
from stargan.
@petergerten If you want to add more than 5 attributes, you should change c_dim=5
to c_dim=(# of attributes you choose)
when running the command python main.py --mode='train' ...
.
As you mentioned, some part of the code was hardcoded to cover the case of hair color (black/blond/brown). The code ensures that the target label does not have more than one hair color at the same time.
If the attribute you added change the indices of Black_Hair/Blond_Hair/Brown_Hair
attributes (the original indices are 1th, 2nd, and 3rd), you need to modify the code here. For example, if you add the Bangs
attribute, the indices of Black_Hair/Blond_Hair/Brown_Hair
are changed to 2nd, 3rd, 4th. You can check the order (or index) of each attribute below.
FYI, these are all available attributes:
'5_o_Clock_Shadow', 'Arched_Eyebrows', 'Attractive', 'Bags_Under_Eyes', 'Bald', 'Bangs', 'Big_Lips',
'Big_Nose', 'Black_Hair', 'Blond_Hair', 'Blurry', 'Brown_Hair', 'Bushy_Eyebrows', 'Chubby',
'Double_Chin', 'Eyeglasses', 'Goatee', 'Gray_Hair', 'Heavy_Makeup', 'High_Cheekbones', 'Male',
'Mouth_Slightly_Open', 'Mustache', 'Narrow_Eyes', 'No_Beard', 'Oval_Face', 'Pale_Skin', 'Pointy_Nose',
'Receding_Hairline', 'Rosy_Cheeks', 'Sideburns', 'Smiling', 'Straight_Hair', 'Wavy_Hair', 'Wearing_Earrings',
'Wearing_Hat', 'Wearing_Lipstick', 'Wearing_Necklace', 'Wearing_Necktie', 'Young'
from stargan.
Related Issues (20)
- How to align Rafd dataset?
- Evaluation Metric "Classification Error" on RaFD dataset?
- Error when testing
- Got stuck at self.G.to(self.device) HOT 3
- Not using Epoch but Iteration to train HOT 1
- Manage domain (attribute) as StarGANv1 HOT 1
- Missing Classification loss in Discriminator for fake Images HOT 2
- Question about parameter adjustment when changing attributes
- Can you share your pre-trained model on RaFD dataset? HOT 1
- [Question] Mask vector in this paper
- how to save the generated images separated HOT 3
- zero vector order in the domain label vector
- Reverse attribute value
- How to get reconstructed images in test stage
- Hello, can you provide the multi-attribute translation task code of solver.py?
- Where does the extra dimension come from in the target labels list?
- Question: Instance Normalization with track_running_stats= True
- Dataset link is not working HOT 2
- Src loss for discriminator
- StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation HOT 1
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 stargan.