Caryox / adversarial-robustness

Robustness of Adversial Neural Networks

3 stars 0 forks source link

Few2Decide - Implementation #49

Closed daniel-knape closed 2 years ago

daniel-knape commented 2 years ago

6 is EPIC

Implement as described in documentation #33

kostovI commented 2 years ago

We need to extract values of last layer from our base model. For this purpose we need to have a forward hook to store the activation.

https://discuss.pytorch.org/t/how-can-l-load-my-best-model-as-a-feature-extractor-evaluator/17254/5

daniel-knape commented 2 years ago

Use https://github.com/Caryox/adversial-robustness/blob/e3462338a51411aa72d5c8bcb274c7ca6acc4fbb/src/Models/upgraded_net.py