You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
@@ -40,38 +40,31 @@ English | [简体中文](README_zh-CN.md)
40
40
41
41
</div>
42
42
43
-
## Introduction
43
+
## 📄 Table of Contents
44
44
45
-
MMYOLO is an open source toolbox for YOLO series algorithms based on PyTorch and [MMDetection](https://github.com/open-mmlab/mmdetection). It is a part of the [OpenMMLab](https://openmmlab.com/) project.
MMYOLO unifies the implementation of modules in various YOLO algorithms and provides a unified benchmark. Users can compare and analyze in a fair and convenient way.
56
-
57
-
-**Rich and detailed documentation**
58
-
59
-
MMYOLO provides rich documentation for getting started, model deployment, advanced usages, and algorithm analysis, making it easy for users at different levels to get started and make extensions quickly.
60
-
61
-
-**Modular Design**
62
-
63
-
MMYOLO decomposes the framework into different components where users can easily customize a model by combining different modules with various training and testing strategies.
45
+
-[🥳 🚀 What's New](#--whats-new-)
46
+
-[✨ Highlight](#-highlight-)
47
+
-[📖 Introduction](#-introduction-)
48
+
-[🛠️ Installation](#%EF%B8%8F-installation-)
49
+
-[👨🏫 Tutorial](#-tutorial-)
50
+
-[📊 Overview of Benchmark and Model Zoo](#-overview-of-benchmark-and-model-zoo-)
51
+
-[❓ FAQ](#-faq-)
52
+
-[🙌 Contributing](#-contributing-)
53
+
-[🤝 Acknowledgement](#-acknowledgement-)
54
+
-[🖊️ Citation](#️-citation-)
55
+
-[🎫 License](#-license-)
56
+
-[🏗️ Projects in OpenMMLab](#%EF%B8%8F-projects-in-openmmlab-)
The figure above is contributed by RangeKing@GitHub, thank you very much!
58
+
## 🥳 🚀 What's New [🔝](#-table-of-contents)
67
59
68
-
And the figure of P6 model is in [model_design.md](docs/en/algorithm_descriptions/model_design.md).
60
+
💎 **v0.4.0** was released on 18/1/2023:
69
61
70
-
</details>
62
+
1. Implemented [YOLOv8](https://github.com/open-mmlab/mmyolo/blob/dev/configs/yolov8/README.md) object detection model, and supports model deployment in [projects/easydeploy](https://github.com/open-mmlab/mmyolo/blob/dev/projects/easydeploy)
63
+
2. Added Chinese and English versions of [Algorithm principles and implementation with YOLOv8](https://github.com/open-mmlab/mmyolo/blob/dev/docs/en/algorithm_descriptions/yolov8_description.md)
71
64
72
-
## What's New
65
+
For release history and update details, please refer to [changelog](https://mmyolo.readthedocs.io/en/latest/notes/changelog.html).
73
66
74
-
### Highlight
67
+
### ✨ Highlight[🔝](#-table-of-contents)
75
68
76
69
We are excited to announce our latest work on real-time object recognition tasks, **RTMDet**, a family of fully convolutional single-stage detectors. RTMDet not only achieves the best parameter-accuracy trade-off on object detection from tiny to extra-large model sizes but also obtains new state-of-the-art performance on instance segmentation and rotated object detection tasks. Details can be found in the [technical report](https://arxiv.org/abs/2212.07784). Pre-trained models are [here](configs/rtmdet).
77
70
@@ -91,16 +84,36 @@ We are excited to announce our latest work on real-time object recognition tasks
91
84
92
85
MMYOLO currently only implements the object detection algorithm, but it has a significant training acceleration compared to the MMDeteciton version. The training speed is 2.6 times faster than the previous version.
93
86
94
-
💎 **v0.3.0** was released on 8/1/2023:
87
+
## 📖 Introduction [🔝](#-table-of-contents)
95
88
96
-
1. Implement fast version of [RTMDet](https://github.com/open-mmlab/mmyolo/blob/dev/configs/rtmdet/README.md). RTMDet-s 8xA100 training takes only 14 hours. The training speed is 2.6 times faster than the previous version.
97
-
2. Support [PPYOLOE](https://github.com/open-mmlab/mmyolo/blob/dev/configs/ppyoloe/README.md) training
98
-
3. Support `iscrowd` attribute training in [YOLOv5](https://github.com/open-mmlab/mmyolo/blob/dev/configs/yolov5/crowdhuman/yolov5_s-v61_8xb16-300e_ignore_crowdhuman.py)
99
-
4. Support [YOLOv5 assigner result visualization](https://github.com/open-mmlab/mmyolo/blob/dev/projects/assigner_visualization/README.md)
89
+
MMYOLO is an open source toolbox for YOLO series algorithms based on PyTorch and [MMDetection](https://github.com/open-mmlab/mmdetection). It is a part of the [OpenMMLab](https://openmmlab.com/) project.
100
90
101
-
For release history and update details, please refer to [changelog](https://mmyolo.readthedocs.io/en/latest/notes/changelog.html).
MMYOLO unifies the implementation of modules in various YOLO algorithms and provides a unified benchmark. Users can compare and analyze in a fair and convenient way.
100
+
101
+
- 📚 **Rich and detailed documentation**
102
+
103
+
MMYOLO provides rich documentation for getting started, model deployment, advanced usages, and algorithm analysis, making it easy for users at different levels to get started and make extensions quickly.
104
+
105
+
- 🧩 **Modular Design**
102
106
103
-
## Installation
107
+
MMYOLO decomposes the framework into different components where users can easily customize a model by combining different modules with various training and testing strategies.
The figure above is contributed by RangeKing@GitHub, thank you very much!
111
+
112
+
And the figure of P6 model is in [model_design.md](docs/en/algorithm_descriptions/model_design.md).
113
+
114
+
</details>
115
+
116
+
## 🛠️ Installation [🔝](#-table-of-contents)
104
117
105
118
MMYOLO relies on PyTorch, MMCV, MMEngine, and MMDetection. Below are quick steps for installation. Please refer to the [Install Guide](docs/en/get_started.md) for more detailed instructions.
MMYOLO is based on MMDetection and adopts the same code structure and design approach. To get better use of this, please read [MMDetection Overview](https://mmdetection.readthedocs.io/en/latest/get_started.html) for the first understanding of MMDetection.
125
138
@@ -144,6 +157,8 @@ For different parts from MMDetection, we have also prepared user guides and adva
-[Algorithm principles and implementation](https://mmyolo.readthedocs.io/en/latest/algorithm_descriptions/index.html#algorithm-principles-and-implementation)
146
159
-[Algorithm principles and implementation with YOLOv5](docs/en/algorithm_descriptions/yolov5_description.md)
160
+
-[Algorithm principles and implementation with RTMDet](docs/en/algorithm_descriptions/rtmdet_description.md)
161
+
-[Algorithm principles and implementation with YOLOv8](docs/en/algorithm_descriptions/yolov8_description.md)
147
162
148
163
- Deployment Guides
149
164
@@ -158,7 +173,7 @@ For different parts from MMDetection, we have also prepared user guides and adva
158
173
-[How to](docs/en/advanced_guides/how_to.md)
159
174
-[Plugins](docs/en/advanced_guides/plugins.md)
160
175
161
-
## Overview of Benchmark and Model Zoo
176
+
## 📊 Overview of Benchmark and Model Zoo[🔝](#-table-of-contents)
162
177
163
178
Results and models are available in the [model zoo](docs/en/model_zoo.md).
164
179
@@ -171,6 +186,7 @@ Results and models are available in the [model zoo](docs/en/model_zoo.md).
171
186
-[x][YOLOv6](configs/yolov6)
172
187
-[x][YOLOv7](configs/yolov7)
173
188
-[x][PPYOLOE](configs/ppyoloe)
189
+
-[x][YOLOv8](configs/yolov8)
174
190
175
191
</details>
176
192
@@ -198,16 +214,21 @@ Results and models are available in the [model zoo](docs/en/model_zoo.md).
198
214
<td>
199
215
<ul>
200
216
<li>YOLOv5CSPDarknet</li>
217
+
<li>YOLOv8CSPDarknet</li>
201
218
<li>YOLOXCSPDarknet</li>
202
219
<li>EfficientRep</li>
203
220
<li>CSPNeXt</li>
204
221
<li>YOLOv7Backbone</li>
205
222
<li>PPYOLOECSPResNet</li>
223
+
<li>mmdet backbone</li>
224
+
<li>mmcls backbone</li>
225
+
<li>timm</li>
206
226
</ul>
207
227
</td>
208
228
<td>
209
229
<ul>
210
230
<li>YOLOv5PAFPN</li>
231
+
<li>YOLOv8PAFPN</li>
211
232
<li>YOLOv6RepPAFPN</li>
212
233
<li>YOLOXPAFPN</li>
213
234
<li>CSPNeXtPAFPN</li>
@@ -218,6 +239,7 @@ Results and models are available in the [model zoo](docs/en/model_zoo.md).
218
239
<td>
219
240
<ul>
220
241
<li>IoULoss</li>
242
+
<li>mmdet loss</li>
221
243
</ul>
222
244
</td>
223
245
<td>
@@ -232,22 +254,26 @@ Results and models are available in the [model zoo](docs/en/model_zoo.md).
232
254
233
255
</details>
234
256
235
-
## FAQ
257
+
## ❓ FAQ[🔝](#-table-of-contents)
236
258
237
259
Please refer to the [FAQ](docs/en/notes/faq.md) for frequently asked questions.
238
260
239
-
## Contributing
261
+
## 🙌 Contributing[🔝](#-table-of-contents)
240
262
241
263
We appreciate all contributions to improving MMYOLO. Ongoing projects can be found in our [GitHub Projects](https://github.com/open-mmlab/mmyolo/projects). Welcome community users to participate in these projects. Please refer to [CONTRIBUTING.md](.github/CONTRIBUTING.md) for the contributing guideline.
242
264
243
-
## Acknowledgement
265
+
## 🤝 Acknowledgement[🔝](#-table-of-contents)
244
266
245
267
MMYOLO is an open source project that is contributed by researchers and engineers from various colleges and companies. We appreciate all the contributors who implement their methods or add new features, as well as users who give valuable feedback.
246
-
We wish that the toolbox and benchmark could serve the growing research community by providing a flexible toolkit to reimplement existing methods and develop their own new detectors.
268
+
We wish that the toolbox and benchmark could serve the growing research community by providing a flexible toolkit to re-implement existing methods and develop their own new detectors.
0 commit comments