muffnn
muffnn copied to clipboard
civisanalytics
Multilayer Feed-Forward Neural Network predictive model implementations with TensorFlow and scikit-learn
# Patching CVE-2007-4559 Hi, we are security researchers from the Advanced Research Center at [Trellix](https://www.trellix.com). We have began a campaign to patch a widespread bug named CVE-2007-4559. CVE-2007-4559 is a...
Curiously, the master branch (updated about two months ago) has had the builds all [passed](https://travis-ci.org/civisanalytics/muffnn/jobs/614077823?utm_medium=notification&utm_source=github_status), while the exact same code now apparently [cannot pass the builds](https://travis-ci.org/civisanalytics/muffnn/jobs/648573246?utm_medium=notification&utm_source=github_status). The test failures are...
The TensorFlow dependency is currently [pinned](https://github.com/civisanalytics/muffnn/blob/be3a67e3f1ff6ff534481d18e4b38d0b77decee6/setup.py#L23) at `>=1.12.1,
The `keep_prob` parameter for dropout is deprecated. We should update `muffnn` to the new usage. Per https://www.tensorflow.org/api_docs/python/tf/nn/dropout, "Warning: SOME ARGUMENTS ARE DEPRECATED: (keep_prob). They will be removed in a future...
It'd be nice to have the ability to do multioutput regression.
The `MLPClassifier` automatically encodes single columns of string targets to integers, but does not do so with multioutput problems. It should allow users to enter an array of targets such...
The latest TF versions recommend feeding data via the Datasets API (https://www.tensorflow.org/programmers_guide/datasets) and claim it is more efficient. We should probs do some testing and switch if it is warranted.
Moving to this for training would have a number of benefits. 1. Improved support for model inspection via TensorBoard 2. Better recovery from failure and check pointing, automatic loading of...
Metadata
Owner
Metadata
Multilayer Feed-Forward Neural Network predictive model implementations with TensorFlow and scikit-learn