TensorFI
TensorFI copied to clipboard
TensorFI is a fault injection framework for injecting both hardware and software faults into applications written using the TensorFlow framework. You can find more information about TensorFI in the pa...
I got this following error. I noticed in the source code `def injectFaultMean(a, b)`, there is a FIXME - `This only works if we call np.mean on b[0]. Need to...
Hi, As far as I understand, TensorFI is capable of injecting faults at the level of nodes but not in the nodes rather the output of one node acts as...
Hi, While running the logistic_regression.py test case, I am encountering an error. **System Information:** Python=2.7 TensorFlow=1.1.5 (GPU Support) **Command used:** `python Tests/logistic_regression.py` **Log** WARNING:tensorflow:From Tests/logistic_regression.py:19: read_data_sets (from tensorflow.contrib.learn.python.learn.datasets.mnist) is deprecated...
Hi, I am trying to run TensorFI on an object detection framework. I am using TensorFlow 1.15 and the algorithm of Object Detection is implemented in Python 2.7 and tested...
While specifying the path for config file, I am getting this error: Traceback (most recent call last): File "train/test.py", line 516, in test_from_rgb_detection(FLAGS.output+'.pickle', FLAGS.output) File "train/test.py", line 298, in test_from_rgb_detection...
### Environment info Operating System: NAME="Ubuntu" VERSION="20.04.1 LTS (Focal Fossa)" ID=ubuntu ID_LIKE=debian PRETTY_NAME="Ubuntu 20.04.1 LTS" VERSION_ID="20.04" HOME_URL="https://www.ubuntu.com/" SUPPORT_URL="https://help.ubuntu.com/" BUG_REPORT_URL="https://bugs.launchpad.net/ubuntu/" PRIVACY_POLICY_URL="https://www.ubuntu.com/legal/terms-and-policies/privacy-policy" VERSION_CODENAME=focal UBUNTU_CODENAME=focal Installed version of CUDA and cuDNN: None (please...
We've experienced an error during testing a CapsuleNet implementation and it gives this error: `ERROR:root:Encountered exception exceptions.TypeError: injectFaultPack() takes exactly 2 arguments (3 given) [[Node: fi_import/primarycap_reshape/Reshape/shape = PyFunc[Tin=[DT_INT32, DT_INT32, DT_INT32],...
When running VGG model provided in the repo, I get a `TypeError: Unknown type `. For now, TensorFI supports four types - int and floats of 32 and 64, it...
For the "oneFaultPerRun" mode, faults were injected into operators sampled from a uniform probability distribution. However it makes more sense to sample across the operator state space as it is...
Injecting operators like `Shape` should be excluded. Accuracy reported might be wrong in these cases, as number of elements changes. Also, curate a list of operators which just get values...