Comments (1)
The start token is inherited from Informer. You're right that there's no new information there... it is mostly included as a trick to improve decoding performance. We are generating entire sequences of predictions in one forward pass instead of the autoregressive format you'd see in LSTM time series models (and generative language Transformers). Without a start token, the decoder sequence would be empty values and there wouldn't be much information for the early self-attention layers to work with. The start token lets information from the recent encoder sequence values go straight to the decoder self-attention. That info probably becomes redundant after the first cross-attention layer can access it from the end of the encoder sequence. This is just a guess but I think if we switched to autoregressive decoding we could drop the start token sequence and just use a single "start token" embedding like in NLP.
from spacetimeformer.
Related Issues (20)
- Multivariate sequence to univariate sequence
- Module pytorch_lightning not found HOT 1
- module 'tqdm' has no attribute 'auto' HOT 3
- AttributeError: module 'tqdm' has no attribute 'auto' HOT 8
- how should I find the datas for example
- Colab installation
- Random seed
- TypeError: accuracy() missing 1 required positional argument: 'task' HOT 1
- MisconfigurationException: `configure_optimizers` must include a monitor when a `ReduceLROnPlateau` scheduler is used HOT 5
- Training with custom dataset. Error: object is not callable HOT 2
- colab
- Pip installation
- Error while resuming training from saved checkpoint
- Huggingface Integration HOT 1
- Memory requirements to replicate on Pems-Bay HOT 2
- Working with custom dataset, IndexError: index out of range in self HOT 1
- ValueError: SyncBatchNorm layers only work with GPU modules HOT 2
- prediction vs labels
- Unable to reproduce results for spacetimeformer HOT 2
- `configure_optimizers` must include a monitor when a `ReduceLROnPlateau` scheduler is used. For example: {"optimizer": optimizer, "lr_scheduler": scheduler, "monitor": "metric_to_track"} HOT 2
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 spacetimeformer.