search

jorgenkg / python-neural-network

This is an efficient implementation of a fully connected neural network in NumPy. The network can be trained by a variety of learning algorithms: backpropagation, resilient backpropagation and scaled conjugate gradient learning. The network has been developed with PYPY in mind.
BSD 2-Clause "Simplified" License
297 stars 98 forks source link

How to measure accuracy? #14

Open hwsamuel opened 7 years ago

hwsamuel commented 7 years ago

Is there a function to measure accuracy?

jhoelzl commented 7 years ago

Would be nice to have a function that provides precision, recall, and f1 score...

jorgenkg commented 7 years ago

There is currently no implementation of accuracy measuring functions as I believed that the end user would implement the specific measuring functions they needed for their use case. However, nimblenet does feature a quality measurement which (tries to) describe how well the network is fitted to the dataset.

However, I shall remember to extend nimblenet with a few functions when I get the time.