Comments (6)
Thanks for the comment and opening the issue. I will have a look as soon as I get the time. Meanwhile, feel free to make a pull request with your changes if you want.
from pubmedclip.
Hello, I'm having trouble running the script for generating the input files (dictionaries, and pickles). One problem in lib/utils/run.sh runs python create_dictionary.py "../../data/data_slake" instead of /data_rad/. However, after changing the directory to data_rad more issues pop up including df columns not matching and I understand that most likely the file was not modified perfectly for generating both datasets' inputs.
It took a while to get them all working, but it would be nice to see a fix.
Hello,
Could you please share the preprocess data on data_rad, I found some troubles in generating the files. Thanks!
from pubmedclip.
Thanks @lycutter and @zyzkevin for reporting this issue.
Both create_dictionary.py
and create_label.py
should be fixed now and work for both VQA_RAD
and VQA_SLAKE
datasets.
Let me know if any other issues shall arise!
from pubmedclip.
Thanks @lycutter and @zyzkevin for reporting this issue.
Both
create_dictionary.py
andcreate_label.py
should be fixed now and work for bothVQA_RAD
andVQA_SLAKE
datasets.Let me know if any other issues shall arise!
Thank for your replying, I update these two files and use them to generate the input files. However, it occured some bugs too, suah as key error 'answer[image_name] ' in the data_RAD.py, dimension mismatch when loading the type_classifer.pth. The train.json file and test.json file I use are from https://github.com/aioz-ai/MICCAI19-MedVQA. I don't know whether these bugs are related to these two .json files. Could you plz share all the completed input files.
Thanks!
from pubmedclip.
@lycutter The scripts in this repo should work for the official datasets released in the original VQA_RAD
paper. But maybe you can use the data from https://github.com/Awenbocc/med-vqa/tree/master/data?
If the error in data_RAD.py
still appears, I would appreciate it if you could make another issue and write the error you get there. Let's keep this thread for issues arising from lib/utils/run.sh
.
from pubmedclip.
@lycutter The scripts in this repo should work for the official datasets released in the original
VQA_RAD
paper. But maybe you can use the data from https://github.com/Awenbocc/med-vqa/tree/master/data?If the error in
data_RAD.py
still appears, I would appreciate it if you could make another issue and write the error you get there. Let's keep this thread for issues arising fromlib/utils/run.sh
.
Thanks for your help! It works now.
from pubmedclip.
Related Issues (16)
- Question about answer+"#" HOT 3
- Validation Set for SLAKE dataset
- Questions about reproducibility
- Use PubMedCLIP as a pretrained model HOT 2
- imgid2idx.json HOT 1
- pretrained_ae.pth HOT 2
- embed_tfidf_weights
- Cannot access trained models on GDrive HOT 2
- No such file or directory:radiologytraindata.csv HOT 1
- Validation set & test/train answer differences HOT 1
- How to save a model in local machine ? HOT 1
- why can run.sh create datasets files? HOT 4
- No such operator image::read_file HOT 3
- VQA_RAC preprocessing dictionary dimension HOT 2
- Issue with VQA RAD training 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 pubmedclip.