Comments (8)
Hi Zabboud,
I'm working on my own implementation, so I can't comment on this exact codebase. But what I found: changing the initialisation (in this case from nn.init.kaiming_normal_(m.weight, mode='fan_in', nonlinearity='relu')
to nn.init.normal_(m.weight, std=0.001)
solves the problem for me.
Curious if you found some more information on this in the meantime!
from probabilistic-unet-pytorch.
Hi Zabboud,
I'm working on my own implementation, so I can't comment on this exact codebase. But what I found: changing the initialisation (in this case from
nn.init.kaiming_normal_(m.weight, mode='fan_in', nonlinearity='relu')
tonn.init.normal_(m.weight, std=0.001)
solves the problem for me.Curious if you found some more information on this in the meantime!
Actually changing the learning rate (decreasing it) fixed the problem for me. I'm still unsure as to why it happens, do you have an idea of why it happens? I'd be interested to test out the different initialization!
from probabilistic-unet-pytorch.
The model is quite sensitive and a too high learning rate and some initialization methods can cause the loss to go to NaN.
from probabilistic-unet-pytorch.
Thank you - I figured out that part -- I was wondering if you have some insight on why with other datasets the loss seems not to decrease, however, I can see that the predictions are improving through visual feedback -- any insight on this issue?
from probabilistic-unet-pytorch.
Hmm I think you should look at the 2 components of the loss function and how they evolve over time. Maybe this can give you some insight into why the loss is not decreasing while the predictions seem to improve.
from probabilistic-unet-pytorch.
Both the total ELBO loss and the KL loss are just stagnant - there's little to no change. Do you have any suggestions on what to tune from the parameters (whether it's latent dimension, gamma, beta, num_convs_fcomb)? I've been playing around with the preprocessing of the data (liver dataset) -but with no luck to make the model learn to predict lesion location.
I've tested the model on the lung dataset - and it works, I have some diversity in the predictions, and there's a progression in the loss - but unfortunately no progress on the liver dataset, whether in predicting liver or lesion.
from probabilistic-unet-pytorch.
I am not sure why that happens and guess that changing things like the latent dimension and num_convs_fcomb is not going to help. I've only tested it on the LIDC and although I sometimes had issues with the loss, it never remained stagnant. Good luck!
from probabilistic-unet-pytorch.
Thank you - I realized that often the KL divergence term goes to 0 -- what would be the cause of that? Probably an indicator of why the model is not training properly
from probabilistic-unet-pytorch.
Related Issues (20)
- Loding pickle file with python 3 HOT 1
- Posterior net input HOT 1
- Unet features HOT 2
- KL Divergence for Independent HOT 1
- kl loss is nan HOT 5
- reconstruction_loss is very large HOT 2
- data preprocessing HOT 1
- sample HOT 5
- Would you mind share the data preprocessing code? HOT 1
- Does it require multiple ground truth Y for each image X to train? HOT 2
- Hi, I'm getting an error of 'ValueError: The parameter loc has invalid values' while training the model with input channels as 1 and latent dim=2.
- data pre-processing HOT 1
- About the four expert labels HOT 1
- Why is the calculated IOU value very low
- Issues when training on my own datasets HOT 1
- Why you randomly sample one label from 4 lables in load_LIDC_data.py? HOT 1
- Sampling a Segmentation
- On the Problem of Pickle Dataset
- learning rate? 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 probabilistic-unet-pytorch.