Re: [Scikit-learn-general] MNIST benchmark

2014-08-18 Thread Lars Buitinck
2014-08-17 7:26 GMT+02:00 Amey : > Zero-one classification Loss as : 0.0426 > > I would like somebody to help me interpret this in terms of benchmarks : > http://yann.lecun.com/exdb/mnist/ > > What is the test error % metric given on the link corresponding to the > metrics I have computed? It's ze

[Scikit-learn-general] MNIST benchmark

2014-08-16 Thread Amey
Hello folks, I'm very new and I was trying out a simple algorithm to do classification using MNIST. I trained on the first 6 data points and did prediction on remaining 1 data points. The metrics I used are : accuracy_score : 0.9574 classification_report : Precision - 0.96 Recall - 0.96