R2GenCMN
R2GenCMN copied to clipboard
[ACL-2021] The official implementation of Cross-modal Memory Networks for Radiology Report Generation.
Hello, Thank you for your good work. However, I saw that you use the key "report_masks" from annotation dictionary, but it is not included in file "annotation.json" you provided. Even...
Thanks for your work and sharing the code. I see the paper compute the mlc score about the mimic_cxr dataset, so how do we compute the mlc score?
使用cheXbert得到的csv中有一些label值为空,读入时会变成NaN,请问作者是怎么处理这些为空(没有标注为1,0或-1)的值? 如果都赋值为同一常数,会不会出现precision过高的情况? 非常感谢! 
Hi, thank you for this interesting work. I would like to know if there are the models weights available and ~~if there is a script to convert the xml files...
Why do the reports I infer using pre trained weights have a lot of duplicates?
I want to implement this project but I do not understand on which ide colab or vscode should i start putting codes can you please help
Hi, I am following your work and thank your for the open code! But one question is: If i want to predict the generated caption from a new medical image...
Could you explain what downsampling operation is done on the picture part of the mimic dataset
Thank you for your outstanding work. I am trying to run your code,and I need the annotation.json file of Mimic. I submitted the request for document access a week ago,...