Comments (8)
We didn't use the MEGA data these appear to have been added after we were done with the project. Not sure if one is a subset of the other. If you are going to retrain with more data, then might make sense to download both these archives and check.
And as I mentioned earlier, we are using NMSLib for searching in the HF-spaces demo.
from clip-rsicd.
Hmm, found this link from somewhere https://mega.nz/folder/wCpSzSoS#RXzIlrv--TDt3ENZdKN8JA
from clip-rsicd.
Hi @INF800 hope this is enough information to start:
- you can download the images and captions directly from the RSICD repository (https://github.com/201528014227051/RSICD_optimal) -- the link is also available from the README.md file for this project.
- once done, you can download one of our models (again link and example code available on README.md) and generate the vectors from the image-caption pairs.
- at this point I suspect you would be ready to upload them to your Elasticsearch instance. We used NMSLib for the demo (code and demo links available in README.md) but in another variation we used the Vespa engine, which offers text, vector and hybrid (text+vector) searching.
from clip-rsicd.
I am stuck at the first step currently. (Because I am also looking at the training code which I will use in future)
These two files are actually downloadable
- The new download source of RSICD-MEGA
dataset.json (2.8MB) imgs.rar (252.9MB)
- The new download source of Sydney-captions and UCM-catpions-MEGA.
annotations_rsicd.rar (836KB) RSICD_images.rar (459.8MB)
- The first file ( 252MB) is subset of second file (459MB) right? Or are they both different?
- And are we using only second file (459MB) for training the best model(s) ?
from clip-rsicd.
And also, can I know what are we using for searching in HF spaces? The speed is appreciable.
from clip-rsicd.
@sujitpal for the data used, does the RSICD data also contain Sydney and UCM-Merced data? If not, did you use all three in your training or only the RSICD data?
from clip-rsicd.
For the training I believe we used RSICD plus the Sydney and UCM-Merced datasets, but I will defer to @arampacha for the authoritative answer.
from clip-rsicd.
IIRC the data is not overlapping and we used all 3 datasets. This is also consistent with model cards we have. And don't see a reason not to trust those ;)
from clip-rsicd.
Related Issues (20)
- Streamlit Demo: Text-to-image and Image-to-image retrieval HOT 2
- Cannot run streamlit demo locally HOT 5
- Update README based on First evaluation feedback HOT 1
- Update Demo based on evaluation feedback HOT 2
- fine tuning procedure. HOT 1
- Classification task evaluation
- Measure model "forgetful-ness"
- Measure generalization capabilities of CLIP-RSICD model HOT 1
- Getting erro while Using this script to fine tune(Urgent) HOT 9
- Training logs HOT 1
- Image encoding with clip-rscidv2 and clip-rscidv2 transformer doesn't work HOT 2
- Remote sensing image captioning HOT 2
- Load fine tuned model with customised data set in demo
- Finetuning Script HOT 1
- PyTorch version
- Model currently unavailable on HuggingFace
- Loss curve anomalies HOT 1
- fine-tuned model
- Isn't the evaluation criteria a bit simplistic.
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 clip-rsicd.