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

YOLO: Real-Time Object Detection

pjreddie.com

Post reply on HN
Print view View original

51–60 of 63 posts

Re: YOLO: Real-Time Object Detection

#51

Post by w-m »

natvert wrote: post #38

Interesting this is trending now. We have actually just recently released an improved version of YoloV3 (called G-Darknet) https://github.com/generalized-iou/g-darknet , using GIoU as a loss, which is described here: https://giou.stanford.edu Also notable in G-Darknet are some tools useful for training (called darkboard), see https://github.com/generalized-iou/g-darknet/tree/master/dar...

Heads up: the boxes are drawn in the wrong places using Firefox 66 on Ubuntu 18.04. https://imgur.com/a/4d51spv

A bit confusing as the drawn boxes don't match the text. Works with Chromium though.

Re: YOLO: Real-Time Object Detection

#52

Post by worldexplorer »

joshvm wrote: post #32
dacox wrote: post #8

Great project, but pretty old now.

Yolov3 is about a year old and is still state of the art for all meaningful purposes. It's fast and works well. You might get "better" results with a Faster RCNN variant, but it's slow and the difference will likely be imperceptible. Using map50 as pjreddie points out, isn't a great metric for object detection.

Interestingly in our production systems yolo object detection speed was much faster and accurate.

Re: YOLO: Real-Time Object Detection

#53

Post by elephantum »

natvert wrote: post #38

Interesting this is trending now. We have actually just recently released an improved version of YoloV3 (called G-Darknet) https://github.com/generalized-iou/g-darknet , using GIoU as a loss, which is described here: https://giou.stanford.edu Also notable in G-Darknet are some tools useful for training (called darkboard), see https://github.com/generalized-iou/g-darknet/tree/master/dar...

Interesting idea!

Though I have a question: in order to calculate C you need a way to attribute proposal and ground truth. It's trivial in case when there's only one instance of each class in the image.

But how does it work, when you're working with a set of same-class object? For example detecting each car in traffic.

Re: YOLO: Real-Time Object Detection

#55

Post by SimplyUnknown »

airstrike wrote: post #22
syntaxing wrote: post #18

Earlier quoted context omitted.

You should read his site, his IDGAF attitude is pretty funny. The FAQ section is the most entertaining.

Nothing beats this resume https://pjreddie.com/static/Redmon%20Resume.pdf

My new theory is that he is Bill Wurtz

Re: YOLO: Real-Time Object Detection

#56

Post by barrystaes »

https://pjreddie.com/media/files/papers/YOLOv3.pdf

Sounds to good to be true. Also reads like that. :) A gem from this paper:

But maybe a better question is: “What are we going todo with these detectors now that we have them?” A lot ofthe people doing this research are at Google and Facebook.I guess at least we know the technology is in good handsand definitely won’t be used to harvest your personal infor-mation and sell it to.... wait, you’re saying that’s exactlywhat it will be used for?? Oh.Well the other people heavily funding vision research arethe military and they’ve never done anything horrible likekilling lots of people with new technology oh wait..... 1

1 The author is funded by the Office of Naval Research and Google.

Re: YOLO: Real-Time Object Detection

#57

Post by natvert »

w-m wrote: post #51
natvert wrote: post #38

Interesting this is trending now. We have actually just recently released an improved version of YoloV3 (called G-Darknet) https://github.com/generalized-iou/g-darknet , using GIoU as a loss, which is described here: https://giou.stanford.edu Also notable in G-Darknet are some tools useful for training (called darkboard), see https://github.com/generalized-iou/g-darknet/tree/master/dar...

Heads up: the boxes are drawn in the wrong places using Firefox 66 on Ubuntu 18.04. https://imgur.com/a/4d51spv A bit confusing as the drawn boxes don't match the text. Works with Chromium though.

Thx, I'll check that

Re: YOLO: Real-Time Object Detection

#59

Post by natvert »

elephantum wrote: post #53
natvert wrote: post #38

Interesting this is trending now. We have actually just recently released an improved version of YoloV3 (called G-Darknet) https://github.com/generalized-iou/g-darknet , using GIoU as a loss, which is described here: https://giou.stanford.edu Also notable in G-Darknet are some tools useful for training (called darkboard), see https://github.com/generalized-iou/g-darknet/tree/master/dar...

Interesting idea! Though I have a question: in order to calculate C you need a way to attribute proposal and ground truth. It's trivial in case when there's only one instance of each class in the image. But how does it work, when you're working with a set of same-class object? For example detecting each car in traffic.

Good question, we use the same method as coco, described in https://arxiv.org/pdf/1405.0312.pdf and implemented in the coco evaluation scripts here: https://github.com/cocodataset/cocoapi/blob/master/PythonAPI... -- basically the best matching proposal, ground truth pair
Post reply on HN