Is EfficientAD's argument pad_maps
in the paper?
#1368
Replies: 1 comment 6 replies
-
In the paper in the Appendix E:
So you can disable the padding in PDN like this, using parameter
But if you do this, you need to add padding to the output of the model before resizing it, because it would be smaller than the original image (for 256x256 it would be 56x56 instead of 64x64). You can also check this answer. |
Beta Was this translation helpful? Give feedback.
-
The argument
anomalib/src/anomalib/models/efficient_ad/torch_model.py
Line 234 in c97762c
in the torch model
anomalib/src/anomalib/models/efficient_ad/torch_model.py
Line 214 in c97762c
is used at inference time (
else
isnot self.training
)anomalib/src/anomalib/models/efficient_ad/torch_model.py
Lines 334 to 347 in c97762c
before the bilinear interpolation.
I could not understand where is operation is referenced in the paper.
Anyone could clarify? @nelson1425 ?
Beta Was this translation helpful? Give feedback.
All reactions