Live data from Hacker News

Not Hotdog App

itunes.apple.com

91–100 of 148 posts

Re: Not Hotdog App

#93
post #87

Earlier quoted context omitted.

It was random, I was already working on the show as what Hollywood calls a (technical) “consultant”: advising on storylines, dialogue, background assets, etc. When this idea popped up, someone suggested we build the app for real. We took a try and ended up building the entire thing in-house with the crew, as opposed to hiring an external agency to do it for us.

How long did it take you to build the app? How many devs worked on it and who got to feed the training data set?

You can fetch a dataset of 1273 labeled hot-dog images and 123287 non-hot-dog images from mscoco training dataset:

search for "hot dog" or click on the hot dog icon:

http://mscoco.org/explore/

Re: Not Hotdog App

#94
This is related to a TV show.

Maybe this comment thread could use a link to a video clip of the show.

Maybe this comment thread could use a link to a video clip of the app in use, since it doesn't work on most devices.

Re: Not Hotdog App

#95
post #57

I always find it strange when apps like this are made unavailable in certain countries (in this case, the UK). Video, I understand. From a consumer perspective it's crappy, but I do understand that licensing agreements for video are generally geographically restricted. But an app that goes along with a TV show? I can't see Sky (the UK network broadcasting Silicon Valley and most other HBO shows right now) distributin…

My guess is they don't want to put in the lawyer work to figure out if they can. I imagine HBO has to heavily vet things like this, unlike small startups.

Re: Not Hotdog App

#97
post #14

Earlier quoted context omitted.

Only American ones it seems

Is that a joke, or does circumcision or its absence actually have an effect on the classifier? Or do you refer to some other characteristic? Offhand I can't really think of a more marked difference between American and non-American penises than the relatively high US circumcision rate, but I'm not so much a subject matter expert as just an interested amateur, and perhaps I overlook something here. (If anything, I'd e…

I'm pretty sure he means the app is only available in the US store and not commenting on the shape or size of american "hot-dogs".

Re: Not Hotdog App

#98
post #97

Earlier quoted context omitted.

Is that a joke, or does circumcision or its absence actually have an effect on the classifier? Or do you refer to some other characteristic? Offhand I can't really think of a more marked difference between American and non-American penises than the relatively high US circumcision rate, but I'm not so much a subject matter expert as just an interested amateur, and perhaps I overlook something here. (If anything, I'd e…

I'm pretty sure he means the app is only available in the US store and not commenting on the shape or size of american "hot-dogs".

Hey, the show did a whole scene about taking a dick joke too seriously, I figured a comment doing the same could work. I appear to have been wrong about that! Or, at the very least, I need to work on my delivery.

Re: Not Hotdog App

#99

Earlier quoted context omitted.

This looks great, haha! Shame I can't access it from the UK. It would be really interesting to read more about your thoughts on working with RN and C++ and perhaps how you did some of it. I'm currently doing the same (but with a C++ audio engine rather than image processing stuff) and I think it's an incredibly powerful combination - but I do feel like I'm making up some interop patterns as I go and there might be be…

Sounds like you're further ahead than I was with the React Native part! Not Hotdog is very simple so I just wrote a simple Native module around my TensorFlow code and let the chips fall where they may performance-wise. The snap/analyze/display sequence is slow enough that I don't need to worry about fps or anything like that. As much as I enjoyed using RN for this app, I would probably move to native code if I needed…

Can you explain to a noob how you wrote the Native module around TensorFlow? My main area of focus is in python, but I feel hindered when I think I'm ready to start developing for mobile apps. I'm looking into RN, but still not sure how that plays with TF and other python modules.
Post reply on HN