THthunderbong·Feb 4, 2026Submission
Detectron2: Platform for object detection and visual recognition tasks
1 points · Open discussionfacebookresearch
detectron2
Python2019–2026
facebookresearch / detectron2
detectron2
Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
12Distinct people
12Mentions
0Explicit recommenders
35KGitHub stars
What to know before exploring
What it is
Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
GitHub
Where it is used
No documented product use was verified in the last source check.
What people are saying
No recommendation phrase was found in the indexed comments.
No classified warning is attached to this page. Read the discussions before treating silence as approval.
Also in these discussions
No other repository is repeatedly linked in the same discussions.
This week on Hacker News
Nov 7–Nov 14 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/14/2026, 3:56:07 PM UTC.
No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.
Mentions over time
HN mentions by year12 dated mentions
Observed mentions: 2019-10-11 03:06:59 UTC to 2026-02-04 14:14:46 UTC.
* An incomplete calendar period is marked with an outlined bar. Its count is not directly comparable with a full period.
Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.
View mention counts and date ranges
| Period | Start (UTC) | End (exclusive, UTC) | Mentions | Submissions | Comments |
|---|---|---|---|---|---|
| 2019 | 2019-01-01 00:00:00 UTC | 2020-01-01 00:00:00 UTC | 3 | 1 | 2 |
| 2020 | 2020-01-01 00:00:00 UTC | 2021-01-01 00:00:00 UTC | 2 | 0 | 2 |
| 2021 | 2021-01-01 00:00:00 UTC | 2022-01-01 00:00:00 UTC | 2 | 0 | 2 |
| 2022 | 2022-01-01 00:00:00 UTC | 2023-01-01 00:00:00 UTC | 0 | 0 | 0 |
| 2023 | 2023-01-01 00:00:00 UTC | 2024-01-01 00:00:00 UTC | 1 | 0 | 1 |
| 2024 | 2024-01-01 00:00:00 UTC | 2025-01-01 00:00:00 UTC | 1 | 0 | 1 |
| 2025 | 2025-01-01 00:00:00 UTC | 2026-01-01 00:00:00 UTC | 2 | 0 | 2 |
| 2026 (partial) | 2026-01-01 00:00:00 UTC | 2027-01-01 00:00:00 UTC | 1 | 1 | 0 |
What Hacker News says
12 sourcesThere certainly are issues on Linux as well. The Detectron2 library alone has several hundred issues related to incorrect versions of something: https://github.com/facebookresearch/detectron2/issues
The mmdetection library (https://github.com/open-mmlab/mmdetection/issues) also has hundreds of version-related issues. Admittedly, that library has not seen any updates for over a year now, but it is sad that things just break and become basically unusable on modern Linux operating systems because NVIDIA can't stop breaking backwards and forwards compatibility for what is essentially just fancy matrix multiplication.
In PYX: The next step in Python packagingAutomation + human intervention, yes. In the setup I described, worst case scenario something gets blurred out that's benign, but it doesn't create a press/support nightmare for Meta.
Considering they've open sourced one of their image detection API [1], I'd imagine it's more a problem of accuracy and implementation at scale than a serious technical hurdle.
[1] https://github.com/facebookresearch/detectron2
In Facebook ban on discussing Linux?I don’t do AI professionally but as a hobby, so this may not be the best way. But the way you described, it seems the user maybe taking the picture a bit further away and there may be other objects in the frame. So you may want to look into some sort of segmentation or have bounding box. This could help the user make sure they are looking at documents for the correct machine.
I think something like detectron2 [1] could help. It is Apache2 license, so commercial friendly. That said the pre-trained weights may not be commercial friendly, so you’ll want to check on that.
Also fast.ai course [2] is a good starting point to understand the basics. If you are pressed for time, just go through Lesson 1.
[1] https://github.com/facebookresearch/detectron2
[2] https://course.fast.ai/
Edit: added fast.ai, grammar
In Ask HN: How to train an image recognition AII could fine-tune a Detectron2 model a few months ago using PyTorch and MPS backend [1]. I'd be interested if it's working yet.
https://github.com/facebookresearch/detectron2/issues/4342
In PyTorch 2.0https://github.com/facebookresearch/detectron2/issues/1602
^ probably not, since they use detectron2, but given the labeled images are really the core part of this, there’s no reason you can’t use them on a different mode that is compatible.
In Show HN: Object Detection in an HourIf you haven't already, take a look at the detectron2 models and tutorials, especially the colab they have. It is a great way to get started.
https://github.com/facebookresearch/detectron2
In Launch HN: Segments.ai (YC W21) – Build better datasets for image segmentation> and every outdoor photo on Facebook can now more easily be “placed in context”
When you factor in their ML prowess [i] it's not hard to imagine that every photo you submit w̶i̶l̶l̶ is getting automagically tagged with an astonishing amount of context: who, what, when, and where (why too since they have all of your chats/messages too).
[i] https://github.com/facebookresearch/detectron2
In Why did Facebook acquire Mapillary?I have one of these powering my open source four wheel drive robot. [1]
I've started doing machine learning experiments with it finally. (See [1] for details)
There's a few tricks to getting the best performance. You want to convert your neural network to run with NVIDIA's TensorRT library instead of just tensorflow or torch. TensorRT does all the optimized goodness that gets you the most out of the hardware. Not all possible network operations can run in TensorRT (though nvidia updates the framework regularly). This means some networks can't be easily converted to something fully optimized for this platform. Facebook's detectron2 for example uses some operations that don't readily convert. [2]
But then if you're new like me you've got to both find some code that will ultimately produce something you can convert to TensorRT, and you also
Read the rest
need something that you can easily train. I've learned that training using your own dataset is often non-obvious. A lot of example code shows how to use an existing dataset but they totally gloss over the specific label format those datasets use. That means you've got to do some digging to figure out how to make your own dataset load properly in to the training code.
After trying a few different things, I've gotten some good results training using Bonnet(al) [3]. I was able to make enough sense of its training code to use my own dataset, and it looks like it will readily convert to TensorRT. Then you load the converted network using NVIDIA's Deepstream library for maximum pipeline efficiency [4].
The performance numbers for the AGX Xavier are very good, and I am hopeful I will get my application fully operation soon enough.
[1] https://reboot.love/t/new-cameras-on-rover/
[2] https://github.com/facebookresearch/detectron2/issues/192
[3] https://github.com/PRBonn/bonnetal
[4] https://developer.nvidia.com/deepstream-sdk
Github link [1] for those of us who don't want to connect to facebook.com.
Looks quite interesting and quite scary considering who is making it, but I will play around a bit with it!
[1] https://github.com/facebookresearch/detectron2
In Detectron2: A PyTorch-based modular object detection libraryI work a lot with object detection at my current role.
Would be cool to add Detectron 2, seems that this library that has some of the state of the art(SOTA) models in object detection. https://github.com/facebookresearch/detectron2
Also the TF Object Detection API has a suite of pretrained SOTA object detection models https://github.com/tensorflow/models/tree/master/research/ob...
What makes object detection really valuable is being able to finetune a model to detect objects that are relevant to your problem. However collecting, labeling, takes a lot of time since the best way is to manually label. But 30-50 hrs of manual labeling can get you some great results when you are leveraging pretrained models. Building a tool to manage data labeling and training for finetuning object detection models would be very valuable.
In Show HN: OpenCV based multi-object-tracker with various object detection modelsDetectron2 – Next-gen platform for object detection and segmentation
1 points · Open discussion