Comments (4)
Hi, the main issue is astroNN built-in data normalizer ignored mode=255 due to this faulty commit f8fb024 lead to the normalizer does nothing to normalize MNIST images and blow up the gradient. I am kinda still on holiday and will go back to research work on the coming Monday so the bug will be fully patched next week probably.
But I have updated some codes in the latest commit and there are some workarounds need to be done in your Jupyter Notebook as I do not want to modify the notebook yet.
add linenet.mc_num = 25
afternet = MNIST_BCNN()
due to a performance issue, so do less Monte Carlo passes as a workaroundchangepred, pred_std = net.test(x_test[test_idx])
topred, pred_std = net.test_old(x_test[test_idx])
due to thetest()
refers to the new fast MC inference on GPU now which turns out not handling classification task correctly and the oldtest()
is renamed totest_old()
changepred_rot, pred_rot_std = net.test(test_rot)
topred_rot, pred_rot_std = net.test_old(test_rot)
for the same reason
This issue will remain open until the issue is fully resolved
To-do list for me:
Add test cases to prevent similar issues (check Nan especially)Done!!The losses now have some kind of performance issue (Painfully slow even on GPU, definitely some operation(s) are being ran on CPU for some reasons)50% Done!!The new accelerated test() for BNN is not handling classification task correctly (and add test case!!!)Done!!
from astronn.
It should have fully resolved, no modification in the Uncertainty_Demo_MNIST.ipynb
is needed
from astronn.
Thanks for the quick update!
Now I can get reasonable loss from the second cell. Great.
However, in the third cell (Test the neural network on random MNIST images),
the total uncertainty (entropy) I got are all 1.0.
As in the following link
https://i.imgur.com/VaVfdsb.jpg
Could you suggest why?
Thanks!
from astronn.
I acknowledge the issue.
My apology, I use regression only for my research so classification-related things are not tested regularly, the current continuous integration test cases only make sure things run without error but not reasonable result. I am looking into it.
from astronn.
Related Issues (15)
- Parrallel odeint integration wrt func or parameter HOT 2
- Galaxy-10 missing images HOT 1
- tensorflow 2.4.1 HOT 3
- ApogeeBCNN() dimensions HOT 11
- Issue loading the Galaxy10 dataset HOT 5
- DR16 astroNN catalog of distances produces incorrect parsec values for Md and Mg stars HOT 8
- Transfer learning & Fine-tuning HOT 8
- Loading Galaxy10 dataset HOT 3
- Keras's fit_generator failed when use_multiprocessing=True on WIndows only HOT 1
- Bugs in 3 of the demo_tutorial/NN_uncertainty_analysis HOT 1
- Current .h5 dataset loading mechanism is problematic
- Complete Tensorflow support without installing Keras separately HOT 3
- Weird errors raised by running the new accelerated BNN test() method HOT 2
- ODE example on tensorflow 2.2.0 HOT 3
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 astronn.