Deep Learning Benchmarks

Re:Deep Learning Benchmarks by mjhirn on Friday March 04, 2016 @03:48PM (#11226747)

We would love to include those, but we didn't find the implementation for the tested models for Theano, yet. Do you have link? You can also submit your own Benchmarks via PR, if you'd like to.

[ Parent | on HN ]

Re:Deep Learning Benchmarks by viksit on Friday March 04, 2016 @05:14PM (#11227238)

Oh actually: https://github.com/uoguelph-mlrg/theano_alexnet and

VGG: https://gist.github.com/baraldilorenzo/07d7802847aaad0a35d3

For Googlenet, sadly not yet: https://github.com/fchollet/keras/issues/302

I'd also try some non conv, RNN/LSTM stuff btw. Those are of special interest to me, but also, keras has some great models there.

[ Parent | on HN ]

Re:Deep Learning Benchmarks by viksit on Friday March 04, 2016 @05:11PM (#11227218)

Ah. I'd look at keras examples - they have alexnet and VGG right now. Although, an exact implementation may be hard to find - the best you can do is an "alexnet~ish" implementation keeping some keras graph limitations on convs.

I haven't run any in a while so I don't have the data myself, unfortunately.

Great work btw.

What was the motivation to build leaf?

[ Parent | on HN ]

Re:Deep Learning Benchmarks by mjhirn on Saturday March 05, 2016 @03:19AM (#11228862)

Great input, thank you so much for the links. I will try to get them to work and publish the results. Same with Keras and LSTMs, very curious to see those.

[ Parent | on HN ]