Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

How HBO’s Silicon Valley Built “Not Hotdog” with TensorFlow, Keras and React Native

medium.com

Post reply on HN
Print view View original

31–40 of 123 posts

Re: How HBO’s Silicon Valley Built “Not Hotdog” with TensorFlow, Keras and React Native

#31

Post by timanglade »

nganig wrote: post #28

Pretty fascinating and encouraging to see how much was accomplished with a laptop and consumer GPU. Gave me some great ideas. Also happy to see Chicago dogs properly identified.

Ha you have no idea how hard chicago hotdogs made my life! There was a joke in the show about Dinesh having to stare at a lot of “adult” imagery for days on end to tune his AI, but my waterloo was chicago hotdogs — the stupid pickles end up hiding the sausage more times than not, which makes it hard to differentiate them from say, a sandwich.

For those of you like me that never knew they existed, here is what they look like: http://img.food.com/img/recipes/25/97/2/large/picMKCD0m.jpg

Re: How HBO’s Silicon Valley Built “Not Hotdog” with TensorFlow, Keras and React Native

#33

Post by ethbro »

timanglade wrote: post #31
nganig wrote: post #28

Pretty fascinating and encouraging to see how much was accomplished with a laptop and consumer GPU. Gave me some great ideas. Also happy to see Chicago dogs properly identified.

Ha you have no idea how hard chicago hotdogs made my life! There was a joke in the show about Dinesh having to stare at a lot of “adult” imagery for days on end to tune his AI, but my waterloo was chicago hotdogs — the stupid pickles end up hiding the sausage more times than not, which makes it hard to differentiate them from say, a sandwich. For those of you like me that never knew they existed, here is what they lo…

I feel your pain. I once watched a single episode of Jeopardy 50+ times in pursuit of timings for a prototype app demo.

I could have a good half-hour conversion about the nuances of Alex Trebek's vocal inflections... shudders

Re: How HBO’s Silicon Valley Built “Not Hotdog” with TensorFlow, Keras and React Native

#34

Post by lightbyte »

timanglade wrote: post #26
lightbyte wrote: post #23

Earlier quoted context omitted.

I have a quick question on this. The blog post mentions that you guys went with CONV-BATCHNORM-ACTIVATION (still unsure on whether this is the better order), but in the model code that is posted the batchnorm and activations are the other way around. Which ordering did you end up using?

Ooops, good catch — I had posted the wrong definition. Corrected now! It was convolution, batch norm, then elu activation.

Quick followup, what type of optimizer did you guys end up using?

Re: How HBO’s Silicon Valley Built “Not Hotdog” with TensorFlow, Keras and React Native

#35

Post by rattray »

timanglade wrote: post #11
richardkeller wrote: post #10

What an ingenious way to covertly distribute the Pied Piper decentralized storage app.

Boy I sure hope no one does a static analysis of the binary…

I really hope you've hidden an Easter egg in there

Re: How HBO’s Silicon Valley Built “Not Hotdog” with TensorFlow, Keras and React Native

#36

Post by timanglade »

lightbyte wrote: post #34
timanglade wrote: post #26

Earlier quoted context omitted.

Ooops, good catch — I had posted the wrong definition. Corrected now! It was convolution, batch norm, then elu activation.

Quick followup, what type of optimizer did you guys end up using?

SGD with Cyclical Learning Rates [0]. Honestly, it’s the closest to a Machine Learning silver bullet I’ve found to date! That paper is awesome.

[0]: https://arxiv.org/abs/1506.01186

Re: How HBO’s Silicon Valley Built “Not Hotdog” with TensorFlow, Keras and React Native

#37

Post by metakermit »

timanglade wrote: post #7
tebica wrote: post #6

Love the post! This explains how mobile TensorFlow can be a actually used on daily life.

One of my primary motivators behind building this blogpost was to show how exactly one can use TensorFlow to ship a production mobile application. There’s certainly a lot of material out there, but a lot of it is either light on details, or only fit for prototypes/demos. There was quite a bit of work involved in making TensorFlow work well on a variety of devices, and I’m proud we managed to get it down to just 50MB…

yeah, that's my main pain with the TF docs – great if you just want to try one of the MNIST tutorial variations, but there's a lot more you need to figure out when you get beyond of these "hello world" examples…

Re: How HBO’s Silicon Valley Built “Not Hotdog” with TensorFlow, Keras and React Native

#39

Post by timanglade »

ethbro wrote: post #33
timanglade wrote: post #31

Earlier quoted context omitted.

Ha you have no idea how hard chicago hotdogs made my life! There was a joke in the show about Dinesh having to stare at a lot of “adult” imagery for days on end to tune his AI, but my waterloo was chicago hotdogs — the stupid pickles end up hiding the sausage more times than not, which makes it hard to differentiate them from say, a sandwich. For those of you like me that never knew they existed, here is what they lo…

I feel your pain. I once watched a single episode of Jeopardy 50+ times in pursuit of timings for a prototype app demo. I could have a good half-hour conversion about the nuances of Alex Trebek's vocal inflections... shudders

Ha, I’d love to hear more. What was the app for? I can’t imagine why you’d have to pick up on Trebek’s elocution??

Re: How HBO’s Silicon Valley Built “Not Hotdog” with TensorFlow, Keras and React Native

#40

Post by mamon »

timanglade wrote: post #8

Just wanted to say thanks for the warm welcome from HN when the app was released last month — I hope this blogpost answers the questions that were raised back then. I’d be happy to answer anything else you’d like to know! Original thread: https://news.ycombinator.com/item?id=14347211 Demo of the app (in the show): https://www.youtube.com/watch?v=ACmydtFDTGs App for iOS: https://itunes.apple.com/app/not-hotdog/id12124…

Slightly offtopic, but I wonder how hard it was to attach eGPU to MacBook Pro? Is there some official support, or was it just a dirty hack?
Post reply on HN