Comments (2)
Hi Shun,
Thanks for your interest in our work! And your understanding is correct. Although prompt tuning could save storage cost after training, it still requires similar amount of (even more when you have many prompt tokens) GPU memory compared to full-finetuning, because just as you said, it still need a full back-propogation to do the optimization during training. You can find more discussion on this in our paper appendix "Empirical computational cost" part and figure 18.
from vpt.
Thank you so much for taking the time to respond to my question. Your prompt and positive feedback means a lot to me!
from vpt.
Related Issues (20)
- What is the use of grid search HOT 2
- How did you set the random seed of Table 1. HOT 1
- AssertionError: Datasets/Stanford_Dogs/train.json dir not found HOT 2
- About stanford cars HOT 1
- About your released performance file(xxxx.csv)
- How to evaluate if I get a checkpoint file? HOT 1
- After joining the prompt, has the dimension changed? HOT 1
- Compared with full fine-tuning, did the training time get reduced?
- Dataset Link Update HOT 1
- TypeError: int() argument must be a string, a bytes-like object or a number, not 'NoneType'
- Segmentation task
- CUB dataset HOT 2
- Wrong MoCo-v3 pretrained weights?
- How to perform segmentation task on my own segmentation dataset?
- How to train? HOT 1
- Run the final evaluation using the full training data? HOT 1
- Result summarization wrong?
- Hello, save model
- Hello, I would like to know about transfer_type
- For swin-B training in pad prompt
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 vpt.