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

YOLOv5: State-of-the-art object detection at 140 FPS

blog.roboflow.ai

Post reply on HN
Print view View original

61–70 of 136 posts

Re: YOLOv5: State-of-the-art object detection at 140 FPS

#61

Post by zb1plus »

sillysaurusx wrote: post #26
sillysaurusx wrote: post #18

We made a site that lets you collaboratively tag a bunch of images, called tagpls.com. For example, users decided to re-tag imagenet for fun: https://twitter.com/theshawwn/status/1262535747975868418 And the tags ended up being hilarious: https://pbs.twimg.com/media/EYXRzDAUwAMjXIG?format=jpg&name=... (I'm particularly fond of https://i.imgur.com/ZMz2yUc.png ) The data is freely available via API: https://www.tagpls.c…

Well, that didn't take long – our API endpoint keeled over. Luckily, you can fetch all the data directly from firebase: # fetch raw tag data $ curl -fsSL https://experiments-573d7.firebaseio.com/results/.json > tags.json $ du -hs tags.json 14M tags.json # fetch tag metadata (colors, remapping label names, possibly other stuff in the future) $ curl -fsSL https://experiments-573d7.firebaseio.com/user_meta/.json > tags_…

Perhaps you can mirror it to an s3 bucket or GH repo for people to CURL more easily?

Re: YOLOv5: State-of-the-art object detection at 140 FPS

#62

Post by syntaxing »

nharada wrote: post #58

I welcome forward progress in the field, but something about this doesn't sit right with me. The authors have an unpublished/unreviewed set of results and they're already co-opting the YOLO name (without the original author) for it and all of this to promote a company? I guess this was inevitable when there's so much money in ML but it definitely feels against the spirit of the academic research community that they'r…

Totally agreed, kinda seems dirty to call something "v5" when it this is a derivative work of the original.

Re: YOLOv5: State-of-the-art object detection at 140 FPS

#63

Post by bArray »

I'm just going to call this out as bullshit. This isn't YOLOv5. I doubt they even did a proper comparison between their model and YOLOv4.

Someone asked it to not be called YOLOv5 and their response was just awful [1]. They also blew off a request to publish a blog/paper detailing the network [2].

I filed a ticket to get to the bottom of this with the creators of YOLOv4: https://github.com/AlexeyAB/darknet/issues/5920

[1] https://github.com/ultralytics/yolov5/issues/2

[2] https://github.com/ultralytics/yolov5/issues/4

Re: YOLOv5: State-of-the-art object detection at 140 FPS

#65

Post by dang »

sillysaurusx wrote: post #18

We made a site that lets you collaboratively tag a bunch of images, called tagpls.com. For example, users decided to re-tag imagenet for fun: https://twitter.com/theshawwn/status/1262535747975868418 And the tags ended up being hilarious: https://pbs.twimg.com/media/EYXRzDAUwAMjXIG?format=jpg&name=... (I'm particularly fond of https://i.imgur.com/ZMz2yUc.png ) The data is freely available via API: https://www.tagpls.c…

You should post this as a Show HN!

Re: YOLOv5: State-of-the-art object detection at 140 FPS

#66

Post by ma2rten »

In February 2020, PJ Reddie noted he would discontinue research in computer vision.

He actually stopped working on it because of ethical concerns. I'm inspired that he made this principled choice despite being quite successful in this field.

https://syncedreview.com/2020/02/24/yolo-creator-says-he-sto...

Re: YOLOv5: State-of-the-art object detection at 140 FPS

#67

Post by rcpt »

bArray wrote: post #63

I'm just going to call this out as bullshit. This isn't YOLOv5. I doubt they even did a proper comparison between their model and YOLOv4. Someone asked it to not be called YOLOv5 and their response was just awful [1]. They also blew off a request to publish a blog/paper detailing the network [2]. I filed a ticket to get to the bottom of this with the creators of YOLOv4: https://github.com/AlexeyAB/darknet/issues/5920…

I love that the response to them is "you can you up,no can no bb"

Learned a new phrase today.

Re: YOLOv5: State-of-the-art object detection at 140 FPS

#68

Post by craftinator »

jcims wrote: post #48

Has anyone (beyond maybe self-driving software) tried using object tagging as a way to start introducing physics into a scene? E.g. human and bicycle have same motion vector, increases likelihood that human is riding bicycle. Bicycle and human have size and weight ranges that could be used to plot trajectory. Bicycles riding in a straight line and trees both provide some cues as to the gravity vector in the scene. Et…

I've been wondering these same thoughts for years. I don't do much work in the neural network subfield, but have done a lot with computer vision, and always found myself wanting more robust physical estimation techniques that didn't require external data.

Re: YOLOv5: State-of-the-art object detection at 140 FPS

#69

Post by catalogia »

rcpt wrote: post #67
bArray wrote: post #63

I'm just going to call this out as bullshit. This isn't YOLOv5. I doubt they even did a proper comparison between their model and YOLOv4. Someone asked it to not be called YOLOv5 and their response was just awful [1]. They also blew off a request to publish a blog/paper detailing the network [2]. I filed a ticket to get to the bottom of this with the creators of YOLOv4: https://github.com/AlexeyAB/darknet/issues/5920…

I love that the response to them is "you can you up,no can no bb" Learned a new phrase today.

Can you explain it? I can't figure out what that means.

Re: YOLOv5: State-of-the-art object detection at 140 FPS

#70

Post by FriendlyNormie »

catalogia wrote: post #69
rcpt wrote: post #67

Earlier quoted context omitted.

I love that the response to them is "you can you up,no can no bb" Learned a new phrase today.

Can you explain it? I can't figure out what that means.

No post body was provided.
Post reply on HN