Closed ghost closed 5 years ago
The success rate is simply the images that successfully fooled the network divided by the total number of attack images: success_images / total_images
. The calculation is performed by attack_stats()
inside helper.py
.
Does that answer your question?
Thanks sir...
On Fri, Apr 12, 2019, 21:11 Dan Kondratyuk <notifications@github.com wrote:
The success rate is simply the images that successfully fooled the network divided by the total number of attack images: success_images / total_images. The calculation is performed by attack_stats() inside helper.py.
— You are receiving this because you modified the open/close state. Reply to this email directly, view it on GitHub https://github.com/Hyperparticle/one-pixel-attack-keras/issues/12#issuecomment-482622344, or mute the thread https://github.com/notifications/unsubscribe-auth/ApFr6dPCTtkEPkqzcSIKywQimnPJds3gks5vgKkcgaJpZM4cmLv7 .
Hello, could you please tell me about how to calculate success rate for LeNet in case of targeted attack? is there any formulas? thanks!