muhammedtalo / covid-19 Goto Github PK

HI there,
I was testing your model for the 3 classes using the images you provided...I tested it several times and the best accuracy was 80%... I even got better results using Densenet..

I took random images and from the dataset and set them as validation... am i doing something wrong?

Hello @muhammedtalo where are you training the model on? I am using google colab and it is taking so much time. Do you have a high performance machine or do I need to change any settings in the colab. Please do respond.

Hi,

I am unable to find the k-fold cross validation code for fastai v1. I have to use it for my research work. Could you please guide through it?

I am trying to run this code in 2021, and quite a few things have been updated or changed since this code was originally written. Can someone please tell me the exact package versions or builds on which you were successfully able to run this code.

Hi! Thanks for making the code public and for the great work!
My question is regarding the train/val/test splits in the notebooks. I can see that you create a train/val split:

data = ImageDataBunch.from_folder(path, train="Train", valid ="Valid",
        ds_tfms=get_transforms(), size=(256,256), bs=32, num_workers=4).normalize() 

And then later you do a classification report on the validation split:
probs,targets = learn.get_preds(ds_type=DatasetType.Valid)

Do you have an unseen during training dataset that you compute your metrics on for each fold?

Thanks!

Code not working/Incomplete code for binary classes for covid detection.

The kfold is not done in the code and moreover not able to run the code despite adding.

Changing the code to bug free and complete version would be helpful!

I'm trying to run this notebook but at start I have installed fastai version 2 after I changed to version 1 but still not working.

hi, i want to see the requirement.txt....would you like to share it?
thanks!

Hi,

I am testing your model, but i am not getting the desired output. I think i am not distributing the data properly in train and valid folders.

Please let me know how you are creating the folder structure and loading the images for train and valid datasets. This is for binary classification

Hi Muhammed,
Thanks for your paper. It inspires me to develop a research topic on transfer learning of Chest X-rays related to COVID-19.

Since the data you use in this paper are quite suitable for my research, I would like to use the images you collected here. However, transfer learning needs RGB images to be compatible with the pre-trained weight, but some images of your dataset are grey. So I was wondering if you have those images in the RGB version, or would you have any suggestions for me to do image processing?

It would be appreciated if I could have your suggestions.
Rita