Model doesn't learn

[gkrisp98]

Hi, I am new to the field of medical images. I am working with 435 MRIs and I have to classify them to 5 classes. I have created a subject dataset both for nifti and DICOM files but neither of them is learning. The training and validation accuracy range from 20 to 22% which is just random.
I used the transforms RandomAffine(), RescaleIntensity(), RandomNoise and CropOrPad() to make the shape of the objects (160,224,224) as it was (160,384,384).
As of now I used a efficient net 3D, a resnet3d and a resnet18 from monai but neither of them seems to learn anything.
Is there any advice for what I can do to make my models start learning ?

[fepegar]

Hi, @gkrisp98. There are a thousand potential causes. Take a look at Andrej Karpathy's recipe.

If you're using MONAI's tools, I suggest you ask on their GitHub, as TorchIO might be unrelated to the issue.

[gkrisp98]

Update: I think I found it! Thanks a lot.

[fepegar]

Have you gone through the tutorials?

[gkrisp98]

I will check them again.

[gkrisp98]

Is there any tutorial for classification ?

[fepegar]

I don't think so. But classification is just a particular case of segmentation, so the segmentation tutorials should suffice.