Building a Poor Man’s Deep Learning Camera in Python • Hacker News Board

Re: Building a Poor Man’s Deep Learning Camera in Python

#11

Post by RealityVoid » Tue, Dec 19, 2017, 11:16 AM UTC

njam wrote: post #7

This is an awesome family xmas project. I don't have an old pc around to run YOLO / YOLO Tiny constantly though; can anyone recommend a cheap, suitable server provider for this? AWS EC2?

AWS EC2 P2 instance is the one used in the fast.ai course and it seems like quite a good choice for these things.

Re: Building a Poor Man’s Deep Learning Camera in Python

#12

Post by aryamaan » Tue, Dec 19, 2017, 11:21 AM UTC

This is superb. Gonna try this sometime soon. I wanted to do this when Google announced Clips.

Re: Building a Poor Man’s Deep Learning Camera in Python

#13

Post by fiftyacorn » Tue, Dec 19, 2017, 11:27 AM UTC

txsh wrote: post #8

fiftyacorn wrote: post #6

This is the project I am planning to do with my son as he's getting interested in computers and loves nature. The rough aims are - > Rasp Pi + Camera/PIR to photograph birds > Connect to internet and post to wp, twitter and instagram The final aim is to add an AI component to see if we can detect birds and keep a count

Do you have hummingbirds in your area? You could setup a high fps camera pointed at hummingbird feeder. Hummingbirds aren't afraid to approach a feeder placed just outside the window of a house.

no - starlings and sea gulls mainly - nothing exciting

Re: Building a Poor Man’s Deep Learning Camera in Python

#14

Post by simonw » Tue, Dec 19, 2017, 11:50 AM UTC

This article inspired me to have a play around with Darknet and Darkflow - turns out they're pretty easy to get going on an OS X laptop with Python 3 (installed via Homebrew).

Here's how I got Darkflow working: https://gist.github.com/simonw/0f93bec220be9cf8250533b603bf6...

For Darknet, I just ran "make" as documented here: https://pjreddie.com/darknet/install/ and then followed the instructions on https://pjreddie.com/darknet/yolo/ and https://pjreddie.com/darknet/nightmare/ to try it out.

Re: Building a Poor Man’s Deep Learning Camera in Python

#15

Post by mrfusion » Tue, Dec 19, 2017, 11:58 AM UTC

So this can identify anything at all? That’s pretty amazing. Maybe we’re getting closer to a dish washing robot.

Re: Building a Poor Man’s Deep Learning Camera in Python

#16

Post by IshKebab » Tue, Dec 19, 2017, 12:03 PM UTC

Iv wrote: post #9

njam wrote: post #7

This is an awesome family xmas project. I don't have an old pc around to run YOLO / YOLO Tiny constantly though; can anyone recommend a cheap, suitable server provider for this? AWS EC2?

Don't you have a computer with a decent GPU? I have trained YOLOv2 on a GTX 1050. A night of training (and starting from pre-trained lower layers) yields good results depending on your application.

He meant for inference.

Re: Building a Poor Man’s Deep Learning Camera in Python

#17

Post by TuringNYC » Tue, Dec 19, 2017, 12:26 PM UTC

mrfusion wrote: post #15

So this can identify anything at all? That’s pretty amazing. Maybe we’re getting closer to a dish washing robot.

No, it will identify anything it is trained for. I havent read the article but these things are usually trained for common datasets with 10, 100, 1000 classes of common objects. The 1000 class dataset covers a giant portion of the distribution of objects you'd see, so sort of close to "anything."

Love the project.

Re: Building a Poor Man’s Deep Learning Camera in Python

#18

Post by lovelearning » Tue, Dec 19, 2017, 12:30 PM UTC

florianletsch wrote: post #10

sandGorgon wrote: post #5

how does this compare with https://aiyprojects.withgoogle.com/vision ? which one is the cheapest and the most funnest to work with ?

(EDIT due to wrongly stating that models run on the Raspberry Pi directly) The Google Vision Kit will run models on a custom neural processing chip connected to the Raspberry Pi Zero. With the DIY setup from the blog bost, the neural network runs on a "large pc" (potentially with GPU). Depending on the hardware you have at your disposal, you can run more complex (and therefore more powerful) neural networks. At the s…

Inference doesn't run on the RPi Zero. It runs on the VisionBonnet board which has a Movidius VPU tensor co-processor on it. RPi is just for handling the LEDs, buzzers and buttons. For training a model with custom datasets, you are correct - something bigger's needed.

Re: Building a Poor Man’s Deep Learning Camera in Python

#19

Post by txmx2017 » Tue, Dec 19, 2017, 12:31 PM UTC

fiftyacorn wrote: post #13

txsh wrote: post #8

Earlier quoted context omitted.

Do you have hummingbirds in your area? You could setup a high fps camera pointed at hummingbird feeder. Hummingbirds aren't afraid to approach a feeder placed just outside the window of a house.

no - starlings and sea gulls mainly - nothing exciting

Sea gulls then. They aggressively go after food with little regard for their safety. They’re like rats with wings.

Re: Building a Poor Man’s Deep Learning Camera in Python

#20

Post by IanCal » Tue, Dec 19, 2017, 1:29 PM UTC

simonw wrote: post #14

This article inspired me to have a play around with Darknet and Darkflow - turns out they're pretty easy to get going on an OS X laptop with Python 3 (installed via Homebrew). Here's how I got Darkflow working: https://gist.github.com/simonw/0f93bec220be9cf8250533b603bf6... For Darknet, I just ran "make" as documented here: https://pjreddie.com/darknet/install/ and then followed the instructions on https://pjreddie.c…

Well that was a remarkably fast installation & test for something like this. Very fun trying it out directly with my webcam, though rather slow on my laptop CPU, will have to get it installed on a better machine.