I am trying to create a classifier for raven vs crow and observed that my input images are getting cropped like this:
Is this expected?
I am trying to create a classifier for raven vs crow and observed that my input images are getting cropped like this:
Is this expected?
Can you also show your transforms step (How you created your data = ImageDataBunch?) and also show how your image looks -
from PIL import Image
Image.open(<your image filename>)
Your original images have white borders on them. Our data augmentation (which we’ll learn about soon) is augmenting the white borders too.
Oh, will the images being in this format result in loss of accuracy during training? I couldn’t get my model to be better than 33% error rate. I tried running more epochs/unfreezing and retraining/setting a learning rate from lr_find/all of the above on resnet50.
You could also try turning off some of the Data augmentation step in get_transforms
call from their default values, particularly the warp (set to zero) -
Because Raven and Crow are close to each other unless seen up close, it might be hard to distinguish them even for ourselves. For example in the top row middle image, I would not been able to distinguish them. You may need lot of examples to distinguish them.
Also, you could try to get a Human Level Accuracy (ideally from someone other than yourself) to see how best someone can distinguish them manually from these same pictures.
Ah thanks, guess I should start with an easier classification problem.