Fix EfficientAD to use width and height of the input

[abc-125]

Description

AutoEncoder in EfficientAD uses both the width and height of the original image for upscaling, and the size of its output matches the output of other models.

• Fixes [Help][EfficientAD] How to change the input size of training processs? #1352, mentioned in this comment,
  Training of EfficientAD fails if the input image has a different width and height:

File "./anomalib/src/anomalib/models/efficient_ad/torch_model.py", line 322, in forward
    distance_ae = torch.pow(teacher_output_aug - ae_output_aug, 2)
RuntimeError: The size of tensor a (56) must match the size of tensor b (120) at non-singleton dimension 3
Epoch 0:   0%|          | 0/215 [00:00<?, ?it/s]  

Changes

Describe the changes you made

• Bug fix (non-breaking change which fixes an issue)
• Refactor (non-breaking change which refactors the code base)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• Documentation update

Checklist

Ensure that you followed the following

• I have added a summary of my changes to the CHANGELOG (not for minor changes, docs and tests).
• I have performed a self-review of my code
• I have commented my code, particularly in hard-to-understand areas (If applicable)
• I have made corresponding changes to the documentation (If applicable)
• I have added tests that prove my fix is effective or that my feature works (If applicable)

[samet-akcay]

Thanks for the fix. I only have one formatting suggestion to avoid CI to fail