Comments (3)
For which configurations were they not set to trainable? For most of our best results, we do set them to be trainable. We will fix the configs if they're incorrect.
The end of Section 4 of the paper has some minor ablations with the parameters being trainable or not; setting them to be trainable generally improves performance a little, and I have since found other settings where training them helps even more.
from s4.
I was running the code incorrectly and thought most of the experiments were not set to trainable, sorry for that. But it seems that in s4-wt103, they are still not set to trainable. Could you take a look?
from s4.
They are supposed to be trainable. Could you point to where in the config indicates that they are not trainable? How are you running the code and how do you know that they are not trainable?
from s4.
Related Issues (20)
- The Issue only occurs in the aan dataset HOT 1
- Using Neumann series to compute the DFT of basis kernels directly HOT 5
- Several examples doesn't work (Sashimi checkpoints / sampleRNN training) HOT 4
- information mismatch in s4/models/s4/experiments.md
- Paper, Table 1, Convolution number of parameters HOT 2
- About `krylov()` HOT 1
- Missing or misplaced "old" config folder? HOT 4
- "pretrained_model" is not defined before being called in train.py HOT 2
- Question on HMDB51 Dataset (S4ND Video Experiment)
- Unable to generate the weather using generate.py with time Series training checkpoint
- Large difference of inference result between forward and step
- AttributeError: 'SSMKernelDPLR' object has no attribute 'kernel' HOT 1
- Training on 12bits audio instead of 8bit? (Question, what do I need to change?)
- S4 Listops have nan loss HOT 2
- Quantization for S4/ Hippo
- The dynamics of the latent state of the model
- segmentation fault when running python -m train pipeline=mnist model=s4 HOT 1
- how to use the S4Block .step()
- KeyError in train.py self.dataset = SequenceDataset.registry[self.hparams.dataset._name_]
- Why is Sashimi's effect in speech signal enhancement (denoisy) so bad?
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 s4.