Comments (2)
Hi,
Yes, there is a difference between my repo and the one from lucidrains. I do not know if the official repository use the same strategy since they do not release the training script.
-
I think that keeping the prediction on the 'known (unmasked)' token will help to quickly see if the network is learning or not, for debugging purposes. I do not think that the prediction will be biased towards the 'known (unmasked)' tokens because the masking ratio is high (i.e. arccos scheduler) and the loss for 'known (unmasked)' tokens will be very low very quickly.
-
Here is the learning curve from the shared model. It shows some picking in the gradient curve (epoch 8, 33, and 85) that might be eliminated by more drastic gradient_norm_clipping.
from maskgit-pytorch.
Thank you for the respose. The loss curve plot is very helpful for me.
from maskgit-pytorch.
Related Issues (14)
- Regarding training a mask model with my own data, could you please provide guidance on the steps involved HOT 1
- train vqgan HOT 3
- Sampling with CFG = 0 HOT 2
- About the training intermediate result. HOT 1
- Question about the DataPreprocessing when training ImageNet HOT 4
- Training loss jumping up when resuming training. HOT 3
- Clarification on Additional Token Usage and Embedding in Maskgit-pytorch Transformer HOT 1
- Warm-up of CFG weight HOT 2
- Unneccesary Dropout layer in FeedForward network HOT 2
- Has anyone successfully run the code HOT 2
- reproducibility HOT 2
- How can I use my own dataset to train maskgit? HOT 2
- questions about two stage training HOT 8
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 maskgit-pytorch.