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/id1212457521

App for Android (just released yesterday): https://play.google.com/store/apps/details?id=com.seefoodtec...

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

I don't relish saying this but the, "Not Hotdog" app does not cut the mustard in even the most rudimentary of tests:

https://twitter.com/iotmpls/status/879381125541613568/photo/...

Probably only 20% of the world's hot dogs are just a basic hot dog with mustard on it. Once you move past one or two condiments, the domain of hot dogs identification along with fixings gets confusing from a computer vision standpoint.

Pinterest's similar images function is able to identify hotdogs with single condiments fairly well:

https://www.pinterest.com/pin/268175352794006376/visual-sear...

They appear to be using deep CNN's.

https://labs.pinterest.com/assets/paper/visual_search_at_pin...

Having embedded tensorflow for on-site identification is all well and good for immediacy and cost, but if I can't really properly identify whether something is a hotdog vs. a long skinny thing with a mustard squiggle, what good does that do me? What would be the next step up in your mind?

I ask this as someone who is sincerely interested in building low cost, fun, projects.

While we’re here and chatting about this, I should say most of the credit for this app should really go towards the following people:

Mike Judge, Alec Berg, Clay Tarver, and all the awesome writers that actually came up with the concept: Meghan Pleticha (who wrote the episode), Adam Countee, Carrie Kemper, Dan O’Keefe (of Festivus fame), Chris Provenzano (who wrote the amazing “Hooli-con” episode this season), Graham Wagner, Shawn Boxee, Rachele Lynn & Andrew Law…

Todd Silverstein, Jonathan Dotan, Amy Solomon, Jim Klever-Weis and our awesome Transmedia Producer Lisa Schomas for shepherding it through and making it real!

Our kick-ass production designers Dorothy Street & Rich Toyon.

Meaghan, Dana, David, Jay, Jonathan and the entire crew at HBO that worked hard to get the app published (yay! we did it!)

OK, but where are the eight octopus recipes?

I am glad I am not the only one with questions about the external GPU, I had considered trying that, but came to the conclusion that the data transfer between CPU to GPU would be too slow for ML tasks. So, what is your opinion on this ? if you had to do it again would you use the eGPU or just use AWS or another GPU cloud service .

It's interesting how amenable image classification neural networks are to the "take working model, peel off last layer or two, retrain for a new application" approach. I've seen this suggested as working pretty well in a few instances.

I guess the interpretation is that the first few normalize->convolution->pool->dropout layers are basically achieving something broadly analogous to the initial feature extraction steps that used to be the mainstay in this area (PCA/ICA, HOG, SIFT/SURF, etc.), and are reasonably problem-independent.

Interesting. What is the external GPU (eGPU) enclosure you used for the Nvidia GTX 980 Ti card? Is it this one? https://bizon-tech.com/us/bizonbox2s-egpu.html/

This should be standard 'hello world' tutorial for Pragmatic ML.

Nice write up that should become the go-to tutorial for TF and local training. Helped me a lot w/ the mobile part, it was a bit strange to thing about transfer the training when I read at first but it became clear in the second reading.

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.

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

This is the Twitter bot I built a few days after the show (similar to Tim's original prototype with Google Cloud): https://hackernoon.com/building-silicon-valleys-hot-dog-app-...

This is amazing - impressed by your persistence to source the training data yourself, that must have been tedious!

Did you try quantizing the parameters to shrink the model size some more? If so, how did it affect the results? It also runs slightly faster on mobile from my experience.

At MongoDB World this past week they did a demo of stitch where they actually built something similar with no back end code required and used the Clarifai API and an angular front end. It took like less than 80 minutes and could like run on prod of I wanted.

Wow, great writeup. This is an area that I know nothing about but have wanted to learn - seems like this post is a good starting point.

Any chance the full source will ever be opened up? Would be an excellent companion to the article.

Just want to say, awesome post. Its amazing how quickly you created this.

Finally for Android! Cool to see a cross-platform implementation of this, and how much can be done by one person and some reasonable gear.

Love this architecture. I think Im going to adopt some of it for HungryBot, my nonprofits diet tracking research arm. I think on-phone predictions solves a lot of my affordability issues.

https://www.infino.me/hungrybot

Great work!

Very informative write up. Thanks!

How did you source and categorize the initial 150K of hotdogs & not hotdogs?

As someone who maintains a popular android camera library; what is this app using to take photos on both iOS and Android? Android can be a bit tricky with device-specific differences and Camera 1 vs. Camera 2 API changes.

What kind of accuracy did you get with the transfer learning attempts?

What’s your biggest regret with this app? What are you most proud of?

The iOS app is not available in the Finnish App Store, only US :-( We have hotdogs here, too! (And not hotdogs.)

Okay, who is going to test this on you-know-what to see if Jian-Yang's pivot would have worked?

Tim: Any tips/online resources for someone starting out with ML? How did you learn?

great app! any plan to open source it?

LOL, I love that part. So funny.