Comments (1)
We trained our models on single V100 GPUs. Using a smaller batch size other GPUs with less RAM should work, too. Training is quite fast due to the frozen CLIP backbone, we trained for around 5 to 6 hours.
from clipseg.
Related Issues (19)
- How can we run training? HOT 8
- Is there a way to set a seed? HOT 1
- Weights are missing HOT 1
- owncloud.gwdg.de is not responding HOT 1
- import error HOT 1
- import error in clipseg.py HOT 1
- Huggingface's Tranformers implementation? HOT 3
- image with mask prompt for one shot HOT 1
- Adding CLIPSeg to HuggingFace Transformers 🤗 HOT 6
- How to download PhraseCut.tar? HOT 1
- Evaluated on referring image seg datasets on RefCOCO, RefCOCO+ , and G-Ref HOT 1
- import file missing HOT 1
- Import error in pfe_dataset.py HOT 1
- LICENSE of this repository HOT 1
- UnpicklingError: invalid load key, 'v'. HOT 2
- only image with mask HOT 1
- Increasing the resolution of the mask HOT 5
- Unable to download weights 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 clipseg.