privacy
privacy copied to clipboard
tensorflow
Library for training machine learning models with privacy for training data
Traceback (most recent call last): File "D:\Anaconda2\envs\tf1\lib\site-packages\tensorflow_core\python\framework\ops.py", line 1607, in _create_c_op c_op = c_api.TF_FinishOperation(op_desc) tensorflow.python.framework.errors_impl.InvalidArgumentError: Dimension size must be evenly divisible by 250 but is 1 for 'training/Reshape' (op: 'Reshape')...
Hi all, In DP-SGD, given a constant number of minibatches, let us say 256, I was wondering why increasing the number of microbatches has a bad effect on the performance....
Is tensorflow-privacy compatible with tensorflow-gpu1.4 ?
Trying to import `tensorflow_privacy` I get the following error. My tensorflow version is 1.14.0 and I am trying to import the command on a jupyter notebook. I install the library...
Some algorithms like DP Federated Averaging need to support weighted DP means. The "weight" could be an argument to preprocess_record, but not all DPQueries need to support weighted records. An...
How to return a vector loss in Keras Custom Loss function, So that I don't have a issue with the following error: ValueError: Dimension size must be evenly divisible by...
I'm running the vectorized tutorial (tf-gpu 1.14) and the per epoch training time on GPU (Nvidia Tesla M10) is slower than the non-vectorized implementation: GPU Vectorized : 203.55 seconds/epoch Non-vectorized...
Is there any guidance how to choose parameters in conjunction with the Keras ImagedataGenerator? I experience InvalidArgumentError during the last quarter of the 1st epoch. I guess the issue is...
Example was outdated. Fixed to use keras L2 regularizer.
I am trying to add privacy to my WGAN. With Adam optimizer without DP, my WGAN works well. But after I change it to optimizer = DPAdamGaussianOptimizer( l2_norm_clip=3, noise_multiplier=0.5, num_microbatches=1,...
Metadata
Owner
Metadata
Library for training machine learning models with privacy for training data