News for hackers. Stuff that matters.
Re:Show and Tell: Image captioning open sourced in TensorFlow by bahro on Thursday September 22, 2016 @10:50PM (#12561988)
Why on earth would they distribute this without a trained model? Several weeks of training time on a multi-thousand dollar piece of specialized hardware are required to actually run this.

Google clearly has many different trained versions of this network sitting around. It must have been a conscious decision not to release them. Is the point to artificially create a barrier to entry for hobbyists that might want to apply this research? If so, why bother releasing it at all? I'm really scratching my head here.

Re:Show and Tell: Image captioning open sourced in TensorFlow by Kabukks on Friday September 23, 2016 @02:30AM (#12562716)
I feel the same. Maybe we should pool some money to train it on AWS. Is there a community where Machine Learning hobbyists can pool money to train models that are open sourced afterwards?
Re:Show and Tell: Image captioning open sourced in TensorFlow by bahro on Friday September 23, 2016 @09:04AM (#12564238)
I haven't heard of one, but this is a good idea!