search

WissingChen / VLCI

Visual-Linguistic Causal Intervention for Radiology Report Generation
45 stars 8 forks source link

MixTokenizer Mimic-CXR Dataset Annotation Path Bug #5

Closed mkara44 closed 1 year ago

mkara44 commented 1 year ago

Hi!

Thanks for the implementation. I am working on your repository and I realized that your MixTokenizer reads only IU Xray annotations. Even Mimic-CXR annotation.json path is defined above code lines, IU Xray's json path is given for Mimic-CXR too. Also your pretrained models were trained with this bug. They are only loaded with this configuration. You can see the wrong line from the link below.

https://github.com/WissingChen/VLCI/blob/216038fe28e1fb9e3d2fee5b7c76b8dc843c4397/utils/tokenizers.py#LL132C53-L132C53

WissingChen commented 1 year ago

I'm sorry, I have fixed the bug, please look at the latest version.