Vision: Easy for humans difficult problem for computers @TensorFlo @YazSantissi #ODSCpic.twitter.com/A0jCADKLSP
You can add location information to your Tweets, such as your city or precise location, from the web and via third-party applications. You always have the option to delete your Tweet location history. Learn more
Vision: Easy for humans difficult problem for computers @TensorFlo @YazSantissi #ODSCpic.twitter.com/A0jCADKLSP
Python image library, wherein images r represented as matrices of numbers, & can do edge & texture detection. @TensorFlo @YazSantissi #ODSCpic.twitter.com/Ks6RCV1jQb
But obviously edge cases, like an orange coloured apple can't be done so simply! @TensorFlo @YazSantissi #ODSCpic.twitter.com/9V49ZuJPrF
Something about thinking about French fries.
/s
@TensorFlo @YazSantissi #ODSCpic.twitter.com/RuGs5MCAix
Retraining @google's inception deep neural network specifically looking at flowers @TensorFlo @docker @YazSantissipic.twitter.com/0OaBxPbpXK
Bottlenecks, training accuracy, validation accuracy, cross entropy, final test accuracy. @TensorFlo @YazSantissi #ODSCpic.twitter.com/dezCwZMDL6
Various run time metrics on our network while it's being retrained @TensorFlo @YazSantissi #ODSCpic.twitter.com/BVaniiDnbm
Our retrained network classifying an unseen photo of a flower @TensorFlo @YazSantissi #ODSCpic.twitter.com/uGWupunl5k
One line to get TF: docker run -it http://gcr.io/tensorflow/tensorflow:latest-devel …
@docker @TensorFlo @YazSantissi #ODSC
Don't fear the basilisk/singularity/rise of AI. Cos it's not really happening in the way they say. (jk not jk) @TensorFlo @YazSantissi #ODSC
(apologies to those who dunno what Roko's basilisk is) @TensorFlo @YazSantissi #ODSC
missed this :( looks awesome.
we're still going, till 11, if I'm not mistaken.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.