MURA exprtiment questions

[ricky-696]

Hello, I'd like to inquire whether you employed different models for distinct parts when working with the MURA dataset or if a single model was used to predict all parts.

If multiple models were utilized, how were the 1000 and 400 images divided during the experiment?

[Re-dot-art]

Hello, I'd like to inquire whether you employed different models for distinct parts when working with the MURA dataset or if a single model was used to predict all parts.

If multiple models were utilized, how were the 1000 and 400 images divided during the experiment?

I think the same model should be used to train the data in the MURA dataset, only to distinguish whether there is a disease, that is, binary classification. The label images should be randomly selected from each type. Also, can you provide the usage code for the MURA dataset? I found that this part is not included in the open source code. Thank you!