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

The source of teacher weights #22

Open WS-W opened 10 months ago

WS-W commented 10 months ago

According to the article, the Teacher network is distilled from WideResNet101 which is pretrained on ImageNet dataset. May I ask do you have the code of the distillation process?

abc-125 commented 9 months ago

You can find it in the pretraining.py.