rjduan / advcam-hide-adv-with-natural-styles Goto Github PK
View Code? Open in Web Editor NEWCode for "Adversarial Camouflage: Hiding Physical World Attacks with Natural Styles" (CVPR 2020)
Code for "Adversarial Camouflage: Hiding Physical World Attacks with Natural Styles" (CVPR 2020)
Hi,
I tried installing and using your code on different operating systems, but each time get some issues with installing Cuda. I would appreciate it if you let me know what was the OS you were working on.
Hello, thanks for your code. I have some problem when I try it.
When I want to try the Pikachu.jpg in your data, I don't know how I transfer its style.
Should I set the Pikachu.jpg as content, and choose a style to transfer it?
Or set it as style, and set T-shirt as content?
I look forward to hearing from you.
Hi, I have another problem.
Could I just call some function to test some result in your code?
I found there are many different versions about vgg19_test, and all of them couldn't work after I trying it.
I look forward to hearing from you.
sh run.sh
2022-11-25 19:58:32.674867: I tensorflow/core/platform/cpu_feature_guard.cc:140] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA
2022-11-25 19:58:32.676762: I tensorflow/core/common_runtime/process_util.cc:63] Creating new thread pool with default inter op setting: 2. Tune using inter_op_parallelism_threads for best performance.
('Top1: ', 'n06794110 street sign', 0.38263422)
('Top5: ', [('n06794110 street sign', 0.38263422), ('n02840245 binder, ring-binder', 0.1255164), ('n04141975 scale, weighing machine', 0.06438678), ('n07248320 book jacket, dust cover, dust jacket, dust wrapper', 0.053751726), ('n03666591 lighter, light, igniter, ignitor', 0.039573323)])
Setting up style layer: <conv1_1/Relu:0>
Setting up style layer: <conv2_1/Relu:0>
Setting up style layer: <conv3_1/Relu:0>
Setting up style layer: <conv4_1/Relu:0>
Setting up style layer: <conv5_1/Relu:0>
Traceback (most recent call last):
File "advcam_main.py", line 84, in
attack(args)
File "/home/hutao/AdvCam-Hide-Adv-with-Natural-Styles/advcam_physical_attack.py", line 205, in attack
],feed_dict={physical_adaptor.background: physical_adaptor.select_random_background(content_width,content_height)})
File "/home/hutao/AdvCam-Hide-Adv-with-Natural-Styles/physical_adaption_utils.py", line 91, in select_random_background
files = os.listdir(self.bg_path)
FileNotFoundError: [Errno 2] No such file or directory: ''
Hello, can you upload a complete set of data sets used in your paper? I can't find this picture in this path./data/content/banana1-style.jpg. Can you upload a complete data set when you have time? Thank you.
Hi
I am trying to run your project and I am getting the following error:
ImportError: libcudnn.so.7: cannot open shared object file: No such file or directory
I already installed the libcudnn and I am not sure what is causing this issue.
appreciate if you can help me fix that.
Thanks
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.