Roadmap of MMYOLO

Question

Roadmap of MMYOLO

hhaAndroid opened this issue 2 years ago · 34 comments

We keep this issue open to collect feature requests from users and hear your voice. Our monthly release plan is also available here.

You can either:

Suggest a new feature by leaving a comment.
Vote for a feature request with +1 or be against with -1. (Remember that developers are busy and cannot respond to all feature requests, so vote for your most favorable one!)
Tell us that you would like to help implement one of the features in the list or review the PRs. (This is the greatest things to hear about!)

V0.5.0(2023.1)

code
- Support YOLOv8 instance seg (YOLOv8 支持实例分割)
- Added a script to verify whether the installation was successful (新增快速验证是否安装成功的脚本) #487

V0.2.0(2022.11)

Collected features

YOLO series supports input Any channel (YOLO 系列代码支持输入任意通道)
Adaptive batchsize function(支持自动 bs 计算功能) #141
Adaptive to anchor calculation(支持训练前自动anchor 聚类优化) #163

中文视频资源

汇总地址： https://github.com/open-mmlab/mmyolo/blob/dev/docs/zh_cn/article.md

工具类

	序号	内容	视频	课程中的代码/文档
✅	第1讲	特征图可视化		特征图可视化文档特征图可视化.ipynb
✅	第2讲	基于 sahi 的大图推理		10分钟轻松掌握大图推理.ipynb

基础类

	序号	内容	课程中的代码/文档
✅	第1讲	配置全解读	配置全解读文档
✅	第2讲	工程文件结构简析	工程文件结构简析文档
🟩	第x讲	模型是如何构建的 - cfg 模式和 Registry 机制详解
🟩	第x讲	MMEngine 必备知识点梳理

实用类

	序号	内容	课程中的代码/文档
✅	第1讲	源码阅读和调试「必备」技巧	源码阅读和调试「必备」技巧文档
✅	第2讲	10分钟换遍主干网络	10分钟换遍主干网络文档 10分钟换遍主干网络.ipynb
✅	第3讲	自定义数据集从标注到部署保姆级教程	自定义数据集从标注到部署保姆级教程
✅	第4讲	顶会第一步 · 模块自定义	顶会第一步·模块自定义.ipynb
🟩	第x讲	关于 MMDet/MMYOLO 中可视化的一切
🟩	第x讲	关于组件随意组合那件事
🟩	第x讲	OpenMMLab 跨库调用全知道
🟩	第x讲	YOLOv5 自定义插件

源码解读类

	序号	内容
🟩	第x讲	RTMDet 原理和实现全解析
🟩	第x讲	YOLOv5 原理和实现全解析
🟩	第x讲	YOLOv6 原理和实现全解析
🟩	第x讲	YOLOv7 原理和实现全解析
🟩	第x讲	YOLOv8 原理和实现全解析
🟩	第x讲	PPYOLOE 原理和实现全解析

Answer 1 · 2022-10-09T01:53:47.000Z

Support deployment based on MMDeploy

Answer 2 · 2022-10-09T01:55:03.000Z

Pick: Added a script to verify whether the installation was successful

Answer 3 · 2022-10-13T10:31:08.000Z

Add a script to support to convert yolo-style *.txt format to coco in PR#161

Answer 4 · 2022-10-16T03:01:46.000Z

Pick :

[基础类第 x 期] 如何优雅地使用 MMYOLO 训练自定义数据集

Answer 5 · 2022-11-02T02:16:21.000Z

Can you post a video tutorial on how to customize module embedding into the network? Take the Transformer module in the original yolov5 library for example, how to integrate the module designed by myself into the network. I want to do a series of experiments based on mmyolo, but don't konw how to modify the file clearly.

Answer 6 · 2022-11-02T14:18:40.000Z

Are you planning to support yolov5 1280 pretrained models, yolov6 m/l models and yolov7 training?

Answer 7 · 2022-11-02T14:23:29.000Z

Are you planning to support yolov5 1280 model, yolov6 m/l model and yolov7 training?

Hi @fcakyon
All you mention were already in progress, will release soon😄

Answer 8 · 2022-11-02T14:38:15.000Z

Are you planning to support yolov5 1280 model, yolov6 m/l model and yolov7 training?

Hi @fcakyon All you mention were already in progress, will release soon😄

Great news! I am the maintainer of sahi, can wait to support mmyolo once these features are released 💯

Answer 9 · 2022-11-02T14:46:06.000Z

Are you planning to support yolov5 1280 model, yolov6 m/l model and yolov7 training?

Hi @fcakyon All you mention were already in progress, will release soon😄

Great news! I am the maintainer of sahi, can wait to support mmyolo once these features are released 💯

Hi @fcakyon
I am the one who want to support sahi in MMYOLO, What a coincidence ! We can keep in touch 😄

Answer 10 · 2022-11-02T15:00:05.000Z

Hi @fcakyon I am the one who want to support sahi in MMYOLO, What a coincidence ! We can keep in touch 😄

Wow, great coincidence 😮 Let's keep in touch 🚀

Answer 11 · 2022-11-03T08:39:04.000Z

Hi @fcakyon I am the one who want to support sahi in MMYOLO, What a coincidence ! We can keep in touch smile

Wow, great coincidence open_mouth Let's keep in touch rocket

Hi, We plan to integrate sahi in v0.1.3. The current plan is:

First make a draft in mmyolo to see the generality
If the generality is very strong, we can consider submitting PR directly to mmengine so that all openmmlab repo can be used directly

how do you feel? @fcakyon

Answer 12 · 2022-11-03T08:49:23.000Z

@hhaAndroid sounds great! What is your implementation plan? Do you want to include it as a tool or as a separate model? How can I help you with this?

Answer 13 · 2022-11-03T08:52:09.000Z

@hhaAndroid sounds great! What is your implementation plan? Do you want to include it as a tool or as a separate model? How can I help you with this?

Let's open an issue to discuss!

Answer 14 · 2022-11-16T06:57:23.000Z

Can you arrange an urgent arrangement for yolo-pose?

Answer 15 · 2022-11-16T13:05:18.000Z

Can you arrange an urgent arrangement for yolo-pose?

Hi~ For yolo-pose, are you referring the yolo-pose from the texas instruments or another version? If there is a specific version you would like MMYOLO to be integrated, can you add a comment in issue#233 ? Thx!!

Answer 16 · 2022-11-24T14:23:02.000Z

Add more result analysis functions. Refer to https://github.com/dbolya/tide.

Answer 17 · 2022-12-12T16:20:16.000Z

I want to use the model implemented by mmyolo in the config file that I have implemented through mmdetection. For example, I want to add one of mmyolo's backbones to the complete model defined by mmdetection. Is it possible? What should I do?

Answer 18 · 2022-12-28T09:40:46.000Z

I want to use the model implemented by mmyolo in the config file that I have implemented through mmdetection. For example, I want to add one of mmyolo's backbones to the complete model defined by mmdetection. Is it possible? What should I do?

Hi @chihuajiao, sorry for the late reply. You could refer to the tutorial to implemente it.

Answer 19 · 2023-02-11T11:53:50.000Z

Hi! I found that both MMYOLO and MMDetection contains implementations of YOLQX-s. What are the differences between the two. In our experiments, the AP-10K data set in MMPose, which also contains bounding boxes information like COCO are applied. But there is a big gap between the results of MMYOLO and MMetection. I would like to know the differences between the two implementations. Thanks a lot for your time!

Answer 20 · 2023-02-12T01:53:45.000Z

Hi! I found that both MMYOLO and MMDetection contains implementations of YOLQX-s. What are the differences between the two. In our experiments, the AP-10K data set in MMPose, which also contains bounding boxes information like COCO are applied. But there is a big gap between the results of MMYOLO and MMetection. I would like to know the differences between the two implementations. Thanks a lot for your time!

Hi, I could only say something about the MMPose bbox detection you mentioned. Most of the algorithms you could find in MMPose are two-stage heatmap detections, which require human bboxes detection in their first stage. That's why there is COCO bbox information used in the implementations.

Answer 21 · 2023-02-12T02:14:49.000Z

Hi! I found that both MMYOLO and MMDetection contains implementations of YOLQX-s. What are the differences between the two. In our experiments, the AP-10K data set in MMPose, which also contains bounding boxes information like COCO are applied. But there is a big gap between the results of MMYOLO and MMetection. I would like to know the differences between the two implementations. Thanks a lot for your time!

Hi, I could only say something about the MMPose bbox detection you mentioned. Most of the algorithms you could find in MMPose are two-stage heatmap detections, which require human bboxes detection in their first stage. That's why there is COCO bbox information used in the implementations.

Thanks for your reply ! I may not explain my question clearly. I actually know that two main paradigms of pose estimation. I would like to use MMYolo or MMDetection to finish the animal object detection task. I just use the AP-10K data set supplied in MMPose that support the same format like COCO. I used YoloX-s to finish the object detection by MMDetection and MMYolo respectively. The results of the two frame work should be very close but in fact there is a big gap between the two results, about 10 AP. I guess that there are some differences in implementations of YoloX-s between the two object detection frame work.

Answer 22 · 2023-02-12T09:32:30.000Z

Hi! I found that both MMYOLO and MMDetection contains implementations of YOLQX-s. What are the differences between the two. In our experiments, the AP-10K data set in MMPose, which also contains bounding boxes information like COCO are applied. But there is a big gap between the results of MMYOLO and MMetection. I would like to know the differences between the two implementations. Thanks a lot for your time!

Hi, I could only say something about the MMPose bbox detection you mentioned. Most of the algorithms you could find in MMPose are two-stage heatmap detections, which require human bboxes detection in their first stage. That's why there is COCO bbox information used in the implementations.

Thanks for your reply ! I may not explain my question clearly. I actually know that two main paradigms of pose estimation. I would like to use MMYolo or MMDetection to finish the animal object detection task. I just use the AP-10K data set supplied in MMPose that support the same format like COCO. I used YoloX-s to finish the object detection by MMDetection and MMYolo respectively. The results of the two frame work should be very close but in fact there is a big gap between the two results, about 10 AP. I guess that there are some differences in implementations of YoloX-s between the two object detection frame work.

Well, I still can't tell why there is such a difference on your results. For the YOLOX implementations in MMDet and MMYOLO, the only difference is on the mosaic part, which you could check here and here. If you still have questions on the implementation and final performance, you are welcomed to open a new issue with your benchmark table so that the maintainers may be able to find out more details.

Answer 23 · 2023-02-24T11:42:51.000Z

I implemented yolox-pose based on mmyolo here, https://github.com/Bovey0809/mmyolo-pose

Answer 24 · 2023-02-24T12:05:00.000Z

I implemented yolox-pose based on mmyolo here, https://github.com/Bovey0809/mmyolo-pose

That is a pretty good job !

Answer 25 · 2023-03-07T02:26:30.000Z

Hi !
Does mmyolo support for mmselfsup ?
I wanna use moco to self_supervise train a pretrained model .
And then use the pretrained model on yolov5 . Does this shit can be realized ？

Answer 26 · 2023-03-07T08:31:34.000Z

Hi !
Does mmyolo support for mmselfsup ?
I wanna use moco to self_supervise train a pretrained model .
And then use the pretrained model on yolov5 . Does this shit can be realized ？

Hi，@arkerman
Of course, MMYOLO supports for MMSelfsup. Here's the example, https://mmyolo.readthedocs.io/en/latest/recommended_topics/replace_backbone.html#use-backbone-network-implemented-in-mmselfsup.

Answer 27 · 2023-03-17T08:18:25.000Z

Add distillation example in yolo serial

Answer 28 · 2023-03-18T03:47:27.000Z

Add distillation example in yolo serial

Hi @www516717402, here's a distillation example of RTMDet,
https://github.com/open-mmlab/mmyolo/tree/main/configs/rtmdet/distillation.

Answer 29 · 2023-06-02T02:49:53.000Z

V0.5.0(2023.1)

code

Support YOLOv8 instance seg (YOLOv8 支持实例分割)

Added a script to verify whether the installation was successful (新增快速验证是否安装成功的脚本) [Feature] Add a script to verify whether the installation was successful #487

Hi, does mmyolo support YOLOv8 ins-seg now? When will it support if not yet? I just saw a commit and failed to train YOLOv8 ins-seg model following the code in this commit. 😭

Answer 30 · 2023-12-12T09:25:29.000Z

What is the current state of yolov8 ins-seg support? Is it in progress or the plans for support of yolov8 were abandoned?