Error

[ArthurConan]

I tried to execute attack on ImageNet with first example command:
python3 test_all.py --untargeted -a black -d imagenet -n 150 --solver adam -b 1 -c 10.0 --use_resize --reset_adam -m 1500 -p 10 -s "imagenet_untargeted"

Can anyone help me with error. Don't know what to do. Thanks in advance.

Traceback (most recent call last):
File "test_all.py", line 262, in
main(args)
File "test_all.py", line 102, in main
data, model = ImageNet(), InceptionModel(sess, use_log)
File "/root/Documents/python/ZOO-Attack-master/setup_inception.py", line 223, in init
create_graph()
File "/root/Documents/python/ZOO-Attack-master/setup_inception.py", line 123, in create_graph
FLAGS.model_dir, 'frozen_inception_v3.pb'), 'rb') as f:
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/platform/flags.py", line 84, in getattr
wrapped(_sys.argv)
File "/usr/local/lib/python3.6/dist-packages/absl/flags/_flagvalues.py", line 630, in call
name, value, suggestions=suggestions)
absl.flags._exceptions.UnrecognizedFlagError: Unknown command line flag 'untargeted'

[huanzhang12]

I am aware of this issue, and will push a fix soon. This is caused by certain tensorflow versions. Thanks for reporting!

[huanzhang12]

@ArthurConan Can you try the latest commit and see if it solves this issue? Thanks!

[kakacharles10]

Hi Huan! Do you have the generated attack images of cifar-10?

[kakacharles10]

Also is it necessary to run the train_model.py before running the test_attack.py? Since I am running out of memory. Thanks a lot!

[huanzhang12]

Yes it is necessary to run train_model.py to train the models before you start the attack.
I don't have any images at this time, except for those ones presented in our paper.

[kakacharles10]

Thanks Huan! Do you know is there any online resource that has attack data that is available for downloading?