Comments (5)
Dear Andrew,
I would really appreciate it if you can share what you have right now.
Good luck for the grad school application !
from swapnet.
I need to retrain them because I was simply prototyping SwapNet before, and deleted them by mistake. But note the implementation is only 90% finished. There are still two things to implement/fix, namely (1) Copy the face data in the final result (issue #6), and (2) debug the perceptual loss to achieve high texture quality (issue #7). A released model at this time would not have those included. Would you like a model with this status or do you prefer to wait for a final product?
I'm also currently busy until mid-December (working on grad school applications). The earliest I can promise is late December.
from swapnet.
Hey folks, thanks once again for uploading this unbelievable repo. Did you get any joy uploading your training weights?
from swapnet.
Hi all, thank you for your patience! And thank you @Larkinnjm1 for the reminder. I just started training a model for upload. Going to let it run overnight, then upload tomorrow evening.
from swapnet.
Update: models have finished training. Download here and extract under the project root: https://drive.google.com/open?id=1kaeHlGf9h3vZLBxr4D5yQUgToxEUWuMh
Please note that these models are far from perfect. I have yet to properly implement the Perceptual Loss, which is crucial for proper texture transfer. See #7 .
Let me know if there are any issues!
from swapnet.
Related Issues (20)
- How does the inference command work for clothing transfer, exactly? HOT 4
- Make preprocessing easier
- Labels are off by 1, hats are missing HOT 1
- SwapNet Checkpoint Models for Inference
- Colab notebook
- Rehaul the code to use PyTorch Lightning
- ModuleNotFoundError: No module named 'model' HOT 3
- Is it different from MGN? If so, how? HOT 1
- Training Warp stage stops at epoch 3 HOT 3
- inference img HOT 1
- Is there any pre-trained model that can be used in handy? HOT 1
- How to test? HOT 1
- Testing error HOT 2
- Without training trying to test
- Error(s) in loading state_dict() for WrapModule HOT 2
- RuntimeError when training HOT 2
- KeyError: Caught KeyError in DataLoader worker process 0. HOT 6
- Help wanted !! KeyError: Caught KeyError in DataLoader worker process 0. HOT 1
- seaborn dependency not included in environment.yml
- loss.py needs small changes.
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 swapnet.