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

Lobe – Deep Learning Made Simple

lobe.ai

Post reply on HN
Print view View original

11–20 of 74 posts

Re: Lobe – Deep Learning Made Simple

#11

Post by mbeissinger »

RankingMember wrote: post #7

This looks awesome. I liked the demonstration of real-world applications with the water tank. From a deep-learning novice: Can you give a rough idea of the processing cost of doing something like setting up your water tank level recognition?

Thanks! We used the water tank as the first end-to-end test using the product, and made a website that calls the API every minute to monitor the water level in a dashboard.

The architecture implemented using Lobes for object detection is called Yolo v2 (https://pjreddie.com/darknet/yolo/). It is fairly state-of-the-art for that type of problem and has ~70 million parameters that are being learned (matrices that get multiplied and added together). With a webcam and a GPU over the network, we typically see ~1-5 fps with a lot of network overhead sending output images - looking to make that faster for API deployment. The paper site above shows it having 62.94 Bn FLOPS

Re: Lobe – Deep Learning Made Simple

#12

Post by mbeissinger »

k1ns wrote: post #9

This is really cool. What will the pricing model be down the road? For instance, if I were to use these models and the cloud API to service a main feature of my application, what ballpark are you thinking of in terms of monthly cost?

Our initial thoughts for pricing model are to be based on compute and keep as low as possible - we want this to be accessible to as many people as possible and do things like enable local training with Tensorflow.js for free. For cloud API deployment, we will price around the backend compute cost on AWS/GCP for gpu instances plus some margin for us maintaining the distributed setup and scaling of serving a machine learning model.

Re: Lobe – Deep Learning Made Simple

#15

Post by ozgooen »

ozgooen wrote: post #14
mbeissinger wrote: post #2

Hey everyone! One of the cofounders of Lobe here - let us know if you have any questions.

Is Lobe only for image data? Would it work for inputs that are text files or similar?

I guess another question here is what are heuristics for how many images are necessary for different levels of functionality. The demos look pretty impressive, but I'm not sure how much went into them.

Re: Lobe – Deep Learning Made Simple

#18

Post by milesokeefe »

Pretty excited about this, I've been on the edge of my seat waiting to hear back from Google after applying for the AutoML alpha but this looks even better, especially because it allows exporting the model which AutoML has not promised yet.

Also AFAIK AutoML alpha initially only supports vision tasks while this allows nearly any input type.

Re: Lobe – Deep Learning Made Simple

#19

Post by milesokeefe »

ozgooen wrote: post #14
mbeissinger wrote: post #2

Hey everyone! One of the cofounders of Lobe here - let us know if you have any questions.

Is Lobe only for image data? Would it work for inputs that are text files or similar?

They support more than image input, their examples have inputs such as 3d models, accelerometer data, sound, 3d depth maps, and numeric data.

It goes the other way as well and supports generation.

Re: Lobe – Deep Learning Made Simple

#20

Post by adammenges »

ozgooen wrote: post #14
mbeissinger wrote: post #2

Hey everyone! One of the cofounders of Lobe here - let us know if you have any questions.

Is Lobe only for image data? Would it work for inputs that are text files or similar?

Yeah! You can mainly work with images and arbitrary vectors (that's what the bounding box examples we show are using, for instance) currently, and have plans to include native support for text, video, etc. as time progresses.
Post reply on HN