Comments (1)
- The naive algorithm and custom kernel primarily differ in memory usage. The naive algorithm materializes the Cauchy matrix which needs O(NL) ops and O(NL) space, while the custom kernel reduces the space to O(N+L). We did benchmark these to verify the space savings
- Yes, the kernel is only used during training. The Cauchy kernel is only used to compute the convolution kernel K bar (equation 5). In settings where we don't use the convolution mode - such as Table 8 which is about autoregressive generation using recurrent mode - the kernel is not used. Table 8 shows the speedup achieved from using recurrence
- In recurrent mode, I think most of the ops are roughly equally expensive; the MLP and other parts might even be dominant. The S4 part is just a simple matmul, like an RNN
from s4.
Related Issues (20)
- 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?
- Passing a video to S4ND
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.