search

nelson1425 / EfficientAD

Unofficial implementation of EfficientAD https://arxiv.org/abs/2303.14535
https://arxiv.org/abs/2303.14535
Apache License 2.0
240 stars 62 forks source link

Convolutions' padding - student/teacher model #4

Closed lorenzolat1 closed 1 year ago

lorenzolat1 commented 1 year ago

Hi! I want to congratulate with you for the implementation of EfficientAD, thank you for your work. I would like to better understand some parts of your implementations, specifically the student/teacher model. In the paper the model has a fixed value for the padding in the convolutions resulting in an output with the shape 384x64x64, instead in your implementation the padding is set by the boolean's variable and the output's shape might be different (384x56x56). Is there a reason behind it?

nelson1425 commented 1 year ago

Yes it is to follow the paper where padding can be disabled to speed up the inference.

lorenzolat1 commented 1 year ago

Thank you for the explanation