Comments (3)
In our implementation, each task is equipped with a specific number of prompt tokens, denoted as prompt_num. The code is designed to jointly train on all datasets simultaneously.
from units.
Thanks your splendid work,No offense!Then why it's called prompt_num since it's have no semantic meaning relationship with "forecasting" or "classification". Hope for an response.❤
from units.
Not sure I understand your question well. The prompt_num has the meaningful of the number of prompt tokens used for each data source.
from units.
Related Issues (20)
- How to run self supervised pretraining using UniTS on custom data? HOT 1
- The initialization of Category Embedding HOT 1
- Why there is no loss.backward in training process? HOT 1
- IncompatibleKeys Error when load pre-trained model to do the fine-tuning. HOT 4
- Should requirements.txt be updated including more packages? HOT 2
- Using UniTS on Unlabeled Data for Anomaly Detection Task HOT 2
- During the run of the UniTS_pretrain_x128.sh script the loss value encountered nan. HOT 1
- Validation set HOT 2
- Dataset Download HOT 1
- A question about fine-tuning
- Using UniTS for new tasks
- gluonts problem HOT 1
- Hello! Asking about Inference. HOT 2
- adjustment for anomaly detection HOT 2
- the meaning of prompt_num HOT 2
- About anomaly detection HOT 1
- If the pre-training of UniTS includes a test dataset, can it still be called ZS? HOT 10
- Scripts of single task setting of forecasting
- Can I use other model to replace the UNITS
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 units.