When I try to run the code with a different dataset I get unwanted results. about covid-caps HOT 2 CLOSED

First of all, forget about warnings for now. You'll usually see lots of them when using with Tensorflow.

About your issue:
This model is pre-trained on X-ray images so it can't produce reasonable results for CT scans.
However, if you want to continue with this implementation, you can train your model from scratch completely based on CT scans but you should do the followings in the "binary.after.py":

1. comment this line of code so the pre-training is discarded.

• model.load_weights('pre-train.h5')

2. Make sure that the size and dimension of your input are compatible with the model, otherwise you can change the input size in this line of code:

• input_image = Input(shape=(None, None, 3))
  Note that CT scan is a 3D data containing several 2D images (slices). This model can take only 2D images as an input so you have to feed it with 2D images (slices) only.

from covid-caps.

Thank you @ShahinSHH for your kind response.

I trained my dataset from scratch using the binary.py file and tried normalizing my CT Scan image dataset by using the data_augmentation() function in binary.py file and reduced the learning rate to 1e-4 while keeping the dataset untouched and it’s working now.

Best Regards,
Harsh

from covid-caps.