Replicating paper's results about covidaid HOT 5 CLOSED

Apologies - I just figured out I was pointing to the wrong trained network! Everything looks good now.

from covidaid.

batch_size at test time does not matter. You can use any size which fits in your GPU memory. For training, see sec. 3.3 of our paper for hyper-parameters.

from covidaid.

I just lowered the batch size and it runs fine (testing bs shouldn't matter - you're right).
A more urgent question: I created the ROCs and CMs for the data split in the code (which reflects the paper). When I want to replicate the results using:
["--mode","test","--freeze","--checkpoint","path_to/CovidAID_transfered.pth.tar","--bs","8","--cm_path","path_to/plots/cm_best","--roc_path","path_to/plots/roc_best","--combine_pneumonia"]
I get the following ROC and CM:

from covidaid.

Which pre-trained model did you use? Did you use the correct model?

from covidaid.

Which pre-trained model did you use? Did you use the correct model?

I followed your steps. The only difference is that I had to make the model torch>1.0 compatible but I didn't change any weights or so, only the names of the layers - that shouldn't really matter right?
FYI: test.txt

from covidaid.