From 843ecad3ccce5ec22fcca802513534b2aa17ff6f Mon Sep 17 00:00:00 2001 From: Shawn Shan Date: Wed, 15 Jul 2020 09:16:12 -0500 Subject: [PATCH] Update README.md --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index 4beb8a0..c3959a2 100644 --- a/README.md +++ b/README.md @@ -43,6 +43,7 @@ when --mode is `custom`: - Select the best mode for your need. `Low` protection is effective against most model trained by individual trackers with commodity face recongition model. `mid` is robust against most commercial models, such as Facebook tagging system. `high` is robust against powerful modeled trained using different face recongition API. - The perturbation generation takes ~60 seconds per image on a CPU machine, and it would be much faster on a GPU machine. Use `batch-size=1` on CPU and `batch-size>1` on GPUs. - Turn on separate target if the images in the directory belong to different person, otherwise, turn it off. +- Run on GPU. The current fawkes package and binary does not support GPU. To use GPU, you need to clone this, install the required packages in `setup.py`, and replace tensorflow with tensorflow-gpu. Then you can run fawkes by `python3 fawkes/protection.py [args]`. ### How do I know my images are secure?