Re:How a Japanese cucumber farmer is using deep learning and...
by orthoganol on Wednesday August 31, 2016 @04:02PM
(#12401062)
"Cucumber classification" seems almost identical to the letter classification task which is the beginner's tutorial on Tensorflow. I think anyone who knows Python and completed a Coursera or Udacity course could get something implemented.
[ Parent
| on HN ]
Re:How a Japanese cucumber farmer is using deep learning and...
by visarga on Thursday September 01, 2016 @02:19AM
(#12403404)
"Cucumber classification"can be solved easily with a C3NN (Cucumber Classification Convolutional Neural Network).
Re:How a Japanese cucumber farmer is using deep learning and...
by GFK_of_xmaspast on Wednesday August 31, 2016 @04:08PM
(#12401109)
> "Cucumber classification" seems almost identical to the letter classification task
Why do you say that?
Re:How a Japanese cucumber farmer is using deep learning and...
by sbierwagen on Wednesday August 31, 2016 @04:15PM
(#12401157)
You're looking at the shape of an object, and determining which category it belongs to. It is similar to looking at a handwritten "a" and determining if it belongs to the "a" category.
Re:How a Japanese cucumber farmer is using deep learning and...
by GFK_of_xmaspast on Wednesday August 31, 2016 @06:31PM
(#12401968)
That seems incredibly reductionist, and you might as well say they're the same because "you add a bunch of numbers together and see if the result is bigger or less than zero."
(Also how do you know or why would you expect that it's categorizing by shape? Neural networks are infamous for finding "irrelevant" features in training data).
Re:How a Japanese cucumber farmer is using deep learning and...
by sbierwagen on Friday September 02, 2016 @09:12PM
(#12417220)
I don't understand your objection. Letter recognition takes a bitmap, and sorts it into one of 26 categories, cucumber grading takes a bitmap, and sorts it into one of 9 categories.
Of course it's reductionist. Generalizing an abstraction across many things that superficially look different is what programmers do. Reducing problem complexity to make something easier to automate is what programming is for.
Saying cucumber grading is like letter recognition is a true generalization that is also useful. Saying that they're both "adding a bunch of numbers" is a true generalization that is less useful. Programming, and (way more) broadly, science and engineering itself, is about finding useful generalizations.
Re:How a Japanese cucumber farmer is using deep learning and...
by justinsaccount on Wednesday August 31, 2016 @05:22PM
(#12401589)
"Even with this low-res image, the system can only classify a cucumber based on its shape, length and level of distortion. It can't recognize color, texture, scratches and prickles,” Makoto explained. Increasing image resolution by zooming into the cucumber would result in much higher accuracy, but would also increase the training time significantly.