Placeholder Image

字幕表 動画を再生する

  • Hi, everybody.

  • And welcome to the Tensorflow Cafe at the TENSORFLOW Developers Summit.

  • I'm Laurence Maroney, and I'm chatting with Patrick Brand from the Coca Cola Company on Patrick.

  • You had a talk here at the summit.

  • Seems to be really interesting.

  • Yeah, about it.

  • Sure.

  • So I shared how tensorflow supporting one of our largest, most popular digital marketing programs here in the United States.

  • Okay, so it's like it's scanning codes from bottle caps.

  • That's right.

  • That's right.

  • So we've, uh, underneath a lot of the bottle caps in fridge packs, the products we sell.

  • We've got unique codes that are consumers can then use to intern to promotions and earn and win things.

  • Okay?

  • Yeah.

  • So why tensorflow?

  • Um Well, the we started, actually, early on on, I could recognize about last year, actually, and I could recognize that tensorflow had a very I call it approachable interface.

  • Right.

  • So thank you.

  • You know, it presents what would be otherwise very complex constructions in idioms that I think I would say every day program is gonna understand.

  • So you've got modules, got objects, you got classes.

  • You can compose these things to create, like a deep learning graph.

  • So it was that it was the entire, you know, platform.

  • Really?

  • The documentation, everything it was it seemed like something that was Ah, you know, a good move for us.

  • So now you did this.

  • So you trained it to classify basically the digits that are printed on his bottle tops.

  • And now I've seen these bottle tops, and sometimes I'm sure that dot matrix printer printing on these things, it's like, sometimes their skin, and sometimes they're obfuscated.

  • That's right.

  • How did you do all this?

  • Yeah.

  • So that was one issue we had had with our caps on other codes.

  • Is that normal?

  • Called like OCR solutions, right.

  • They couldn't handle the fidelity of the caps.

  • So what we did is we created a training set, both synthetic and real world, because we can generate these things these caps and fridge packs ourselves and really just, you know, through to tensorflow.

  • And, uh, we adjusted our model several times for development, but we eventually got something that performs extremely well for us and very well at scale.

  • Okay, so would you say it scaled so pretty quick?

  • Yeah, it's very fast, you know, it's ah, we're about one second.

  • It was our performance.

  • Quiet one second average processing time from a user experience perspective is great.

  • You know, it's it's not ruining anyones expectation when they engage with our platform.

  • Now you went to a tense floats.

  • Do this cause an ML base platform?

  • What would it have been like?

  • What's the difference if he had done this more and more traditional programming, Right?

  • So if we didn't say applied Amore heuristic model right, trying to use rules to interpret these codes so I could imagine a situation right, like where we create our model and it works really well for Let's zero degree rotation on the cap.

  • Users are holding this thing perfectly and holding their phone perfectly the second they twist that thing two degrees in the direction that heuristic model would fall apart.

  • So you find yourself having to in code all these different variations heuristics, And that sounds arduous, definitely, because the cap circular you don't really have a frame of reference.

  • I know that it's been yeah, I mean, just simple.

  • Something simple is a slight twist from the access and then rotation, which is very natural for someone holding a cap in their hand to do so.

  • You know, with a machine learning approach, Um, we're able Thio accommodate that translation appearance with convolution of neural net.

  • Sure, I think when the things I found that, like just to my eye that when I look at these digits on the bottle caps, it's sometimes hard to tell.

  • I have to tell the six from a five or a NATO that kind of thing.

  • So did you have a pretty good success with?

  • Absolutely, Um I can say anecdotally that Ah, that the machine I, uh, if you want, think about that way is actually often works better than the human eye just for the reasons you were saying that to him and I a lot of the, um, visual artifacts that are on these caps.

  • What's Q and pixel drift can start to complicate things, but our model is trained to look through that.

  • Okay, So how did you get training data, by the way?

  • Uh, where we started with synthetic data set.

  • And then that that got us a baseline.

  • We actually got I would say about 50% accuracy just on synthetic data alone.

  • Okay?

  • And that was used for transfer learning.

  • Actually, so we created a, well, a real world data set, just printing stuff way dialed up our printing facilities and we said, Hey, give us a bunch.

  • And then, um, I just want the whole bunch of just a whole bunch of caps for giving.

  • And then we treated this.

  • The multiple suppliers, and we drive them with some custom built tools that we created toe.

  • Make it easy for them to take a picture and label it.

  • We started moving into a much more similar line approach.

  • One team would take images, and the other team to make a portal would verify the image entering the code.

  • Make sure the quality of the image itself was good.

  • But we were able to very quickly, within a matter of weeks, generate enough data for us to train the model.

  • That's so cool.

  • Now, you mentioned that there are a number of initiatives you're working on, not just this one.

  • That's right.

  • Can you share any of the others?

  • I can, um, so in particular with computer vision on marketing, this code scanning initiative was the beginning of our kind of our computer vision platform.

  • We this year have launched a new digital icon visual icon that we're starting to put on the exterior of our packaging.

  • And it's a delightful looking, very beautiful image, and it fits in well with all of our other branded elements, which is critical, but it encodes information for that product.

  • So it's Q R code, but not a cure code.

  • It is not a cure, but it is principle.

  • It's in principle.

  • That same idea.

  • I would think of it more as like a bespoke Q R code, something that is appealing from a visual.

  • Interesting.

  • So instead of just lots of black and white squares, it's yes, it's three concentric rings with a little Coke bottle in.

  • The men have to take a look.

  • I have to check it out.

  • Cool.

  • So go back to the bottle.

  • Classify that you have.

  • I'd like to have a play.

  • How would I get started?

  • Step one is by one of our products.

  • Not all of our brands have these caps primitive, but but most of the Newman, certainly our core brands.

  • You know any Coca Cola product, our aid, et cetera.

  • Well, as well.

  • Um, but you byproduct twist off cap, and you now have everything you need.

  • Thio, enter into our promotions.

  • You know, you would create a count coke dot com slash rewards are on the new app that we launched two days ago.

  • The whole U S.

  • A.

  • Up, Um, And the hope is that, you know, it becomes an experience that's rewarding enough to continue engaging with our consumers.

  • Sounds good.

  • I'll have to give it a shot.

  • Thanks so much, Patrick.

  • You're welcome, Lawrence.

  • So thanks everybody for watching this episode.

  • If you've got any questions for me or any questions for Patrick, please just leave him in.

  • The comments below on any of the links that we discussed will put them in the description for this video.

  • Whatever you do, don't forget to hit that subscribe button.

  • Thank you.

  • Okay.

Hi, everybody.

字幕と単語

ワンタップで英和辞典検索 単語をクリックすると、意味が表示されます

B1 中級

デジタルマーケティングキャンペーンにTensorFlowを活用したコカ・コーラ社(TensorFlow Meets (The Coca-Cola Company using TensorFlow for digital marketing campaigns (TensorFlow Meets))

  • 2 0
    林宜悉 に公開 2021 年 01 月 14 日
動画の中の単語