Comments (2)
Hi Chen,
Thanks for pointing it out. Usually, we don't use the activation layer in the end. To be consistent, you can either add a ReLU layer or delete the batchnorm layer at line 132. In practice, we observe it doesn't influence the result much.
Thanks,
Zongyi
from neuraloperator.
Hi Zongyi,
Thanks very much for instructions! Yes, I have tried Relu layer at line 132 and to be honest the result after the same number of epochs is worse a little bit for my acoustic wave equation problem. This may due to the fact that the wavefield should be having both positive and negative values and the Relu mutes the negative so the FC layers after it has to contain more information to add those back. This also reminds me to try other activation layers for the Green's function part such as sigmoid.
Have a nice day!
Chen Qi
from neuraloperator.
Related Issues (20)
- Fixing gradient backprop in #233
- MLP dropout > 0.5 causes error HOT 1
- DDP wireup requires calling from MPI
- import error in Training a TFNO on Darcy-Flow example HOT 1
- Training the neural operator in 3D spatial domain HOT 3
- Reproducing the published results
- Potential models to implement and merge
- Reproducing GINO
- loss sometimes jumps at restart
- How to create darcy dataset on different resolution? HOT 1
- U-NO on Darcy-Flow (Gallery of example) don't run on cuda
- [Request] Dataset creation and acquisiton documentation HOT 2
- coordinates in the darcy flow example HOT 2
- Question about differentiation
- Training logs no longer appear in update 0.3.0 HOT 3
- Question regarding avg_loss
- Understanding the Darcy flow dataset HOT 2
- (<class 'RuntimeError'>, RuntimeError('Unsupported dtype Half'), <traceback object at 0x7ff3c12f6280>) HOT 2
- AttentionKernelLayer fails test due to error in Einsum HOT 1
- Multi channel output support
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 neuraloperator.