Comments (2)
kihyunU
commented on July 22, 2024
As you know, the contrastive learning is highly dependent on the batch size, so we recommend trying with a larger batch size.
from cxr-clip.
ChocoOreal
commented on July 22, 2024
I tried to evaluate I2T retrieval with the official weight but the results are still not comparable to the figures in your paper. Here is the results I got:
Can you share more details on the data used for evaluation?
from cxr-clip.
Related Issues (11)
- MIMIC-CXR Pretrain Dataset Pre-Processing HOT 6
- pre-trained checkpoints for CXR-CLIP?
- Some confusion about pre training datasets HOT 1
- How to resume my training? HOT 2
- [BOS] and [EOS] token missing HOT 1
- Some questions about data processing HOT 5
- How to tackle missing both impressions and findings sections HOT 1
- The RSNA Pneumonia dataset only contains binary labels for normal and pneumonia cases. Why is it possible to use this dataset for multi-label classification? HOT 1
- The checkpoints provided does not give expected result HOT 4
- About few-shot evaluation HOT 1
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 cxr-clip.