Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

TensorFlow MNIST accuracy test is failing #64

Closed
mahnerak opened this issue Jan 20, 2017 · 9 comments
Closed

TensorFlow MNIST accuracy test is failing #64

mahnerak opened this issue Jan 20, 2017 · 9 comments

Comments

@mahnerak
Copy link
Contributor

Completed model training.
Traceback (most recent call last):
File "test_mnist_accuracy.py", line 71, in
app.run()
File "/home/mahnerak/.local/lib/python2.7/site-packages/tensorflow/python/platform/app.py", line 44, in run
_sys.exit(main(_sys.argv[:1] + flags_passthrough))
File "test_mnist_accuracy.py", line 67, in main
assert float(accuracy) >= 0.98, accuracy
AssertionError: 0.9639

@goodfeli
Copy link
Contributor

It just passed three times in a row for me.

  • Could it be flaky? If you re-run it, does it still fail?
  • Are you running from a clean copy of the master branch?
  • What version of keras and tensorflow are you using?

@mahnerak
Copy link
Contributor Author

  • Tried just now. Failed 5 times in a row. For each run got ~0.96 accuracy.
  • Running from clean copy (current version) of the master branch
  • TensorFlow v0.12, Keras v1.2.0

One more thing. I noticed that Adadelta from TensorFlow behaves different than implementations found in Keras and Lasagne (Theano versions), when I was implementing theano version of FGSM. Then I ran Keras version of Adadelta on TensorFlow, and its results were also different than the ones from TensorFlow's default Adadelta. It was a bit confusing.

Today I updated TensorFlow, and its Adadelta behaves like the other implementations.

@npapernot
Copy link
Member

The test is passing on my machine as well

@goodfeli
Copy link
Contributor

@mahnerak : is there a 3rd digit to your tensorflow version? I am also running keras 1.2.0. My tensorflow is 0.12.1. Have you checked cleverhans.file to make sure your PYTHONPATH is set correctly and that you are in fact importing the clean unmodified master branch?
@npapernot : what are your versions?

@npapernot
Copy link
Member

TF: 0.10.0rc0 and same keras version

@mahnerak
Copy link
Contributor Author

TensorFlow version is 0.12-head (compiled from sources today).
Checked PYTHONPATH again, it's set correct.
I'll try to do clean install tensorflow (with prebuild binaries) and keras on another machine and run the tests.

@goodfeli
Copy link
Contributor

It's possible tensorflow 0.12-head is broken.
I suggest checking cleverhans.__file__ rather than checking PYTHONPATH.

@mahnerak
Copy link
Contributor Author

Installed 0.12.1 from prebuilt binaries. Tests are passing now.

@goodfeli
Copy link
Contributor

@mahnerak I would suggest reporting this on the tensorflow repository issues tracker if you haven't already

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants