Comments (7)
Hey @evancasey
This tends to happen with high learning rates, could you try decreasing the learning rate https://github.com/preddy5/Im2Vec/blob/master/configs/emoji.yaml#L23 to 0.0001 and see if the changes anything.
from im2vec.
I'm starting to see better results after reducing LR to 0.0001, however it takes much longer to train than your logged results. Would you suggest tuning LR some more or are there any other hyperparameters that come to mind?
from im2vec.
from im2vec.
After 2000 epochs it still does not converge
from im2vec.
Hey @evancasey I think you might have to tune the LR a bit, could you try 0.0002 maybe, also increasing https://github.com/preddy5/Im2Vec/blob/master/configs/emoji.yaml#L8 the radius helps with the initial part of the optimization maybe try 20. Hopefully, this helps with the optimization.
from im2vec.
Same here. Tried everything. Almost 3000 epochs and it still does not converge.
There are 3 logical possibilities:
1 - The code in this repository is not the one used in the paper (i.e. notebooks?)
2 - There is a secret way to tune those parameters with a separate tool/script
3 - The results in the paper are made up
Excluding the third, both the 1st and the 2nd explanations are easy to solve.
You just need to merge/add the source code of the notebook or of the tool with this repo.
Are you still under deadlines? I hope you will find a moment to fix this. This is an important work.
Thanks. 👍
from im2vec.
Hey @Emasoft
There are many reasons why the network might not have converged when you train it.
The repo includes an example training run please use that for debugging your training. For each new training run, the code also creates a copy of the training code in the log directory, so the example training run also contains a backup of the code used for that specific training and trained weights, you can use them for debugging as well.
Hope that helps.
from im2vec.
Related Issues (20)
- the loss is NAN when train model HOT 7
- problems when training HOT 8
- training on real images?
- Why are there many copies in the dataset? HOT 2
- Post-decoding process HOT 3
- emoji dataset is settled to 4 parts, and every parts is filled with a constant color, does this mean im2vec can only deal with HOT 5
- Segmentation tool HOT 4
- Speeding up training and using attention HOT 1
- Chamfer distance code
- Can't install dependencies HOT 1
- Training example from README wont work
- Dependency Conflict with Pillow
- MisconfigurationException in Training Example
- pip install -r requirements.txt. ERRORS HOT 1
- About training details HOT 6
- RuntimeError: stack expects a non-empty TensorList HOT 3
- The difference between VectorVAE and VectorVAEnLayers
- No module named 'pydiffvg' HOT 1
- How to train with celeba dataset? HOT 2
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 im2vec.