Initial commit

.gitignore

+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+**/*.pyc
+
+# C extensions
+
+# Distribution / packaging
+
+.Python
+videos/
+build/
+runs/
+weights/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# pyenv
+.python-version
+
+# celery beat schedule file
+celerybeat-schedule
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# custom
+.DS_Store
+
+# Pytorch
+*.pth
+
+#vscode
+.vscode/*
+
+#user scripts
+*.sh
+
+# model files
+*.onnx
+*.pt
+*.engine

.pre-commit-config.yaml

+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.3.0
+    hooks:
+      - id: check-yaml
+      - id: end-of-file-fixer
+      - id: trailing-whitespace

README.md

+<p align="center">
+  <img src="assets/banner-YOLO.png" align="middle" width = "1000" />
+</p>
+
+English | [简体中文](README_cn.md)
+
+ <br>
+
+ <div>
+    </a>
+    <a href="[https://colab.research.google.com/github/meituan/YOLOv6/blob/main/turtorial.ipynb](https://colab.research.google.com/gist/HouSanDuo123/bdad4ad6706209d4e9275d2186d54289/tutorial.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a>
+     <a href="https://www.kaggle.com/code/housanduo/yolov6"><img src="https://kaggle.com/static/images/open-in-kaggle.svg" alt="Open In Kaggle"></a>
+  </div>
+ <br>
+
+## YOLOv6
+
+Implementation of paper:
+- [YOLOv6 v3.0: A Full-Scale Reloading](https://arxiv.org/abs/2301.05586) 🔥
+- [YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications](https://arxiv.org/abs/2209.02976)
+
+<p align="center">
+  <img src="assets/speed_comparision_v3.png" align="middle" width = "1000" />
+</p>
+
+
+## What's New
+
+- [2023.01.06] Release P6 models and enhance the performance of P5 models. ⭐️ [Benchmark](#Benchmark)
+    - Renew the neck of the detector with a BiC module and SimCSPSPPF Block.
+    - Propose an anchor-aided training (AAT) strategy.
+    - Involve a new self-distillation strategy for small models of YOLOv6.
+    - Expand YOLOv6 and hit a new
+SOTA performance on the COCO dataset.
+- [2022.11.04] Release [base models](configs/base/README.md) to simplify the training and deployment process.
+- [2022.09.06] Customized quantization methods. 🚀 [Quantization Tutorial](./tools/qat/README.md)
+- [2022.09.05] Release M/L models and update N/T/S models with enhanced performance. 
+- [2022.06.23] Release N/T/S models with excellent performance.
+
+## Benchmark
+| Model                                                        | Size | mAP<sup>val<br/>0.5:0.95 | Speed<sup>T4<br/>trt fp16 b1 <br/>(fps) | Speed<sup>T4<br/>trt fp16 b32 <br/>(fps) | Params<br/><sup> (M) | FLOPs<br/><sup> (G) |
+| :----------------------------------------------------------- | ---- | :----------------------- | --------------------------------------- | ---------------------------------------- | -------------------- | ------------------- |
+| [**YOLOv6-N**](https://github.com/meituan/YOLOv6/releases/download/0.3.0/yolov6n.pt) | 640  | 37.5                     | 779                                     | 1187                                     | 4.7                  | 11.4                |
+| [**YOLOv6-S**](https://github.com/meituan/YOLOv6/releases/download/0.3.0/yolov6s.pt) | 640  | 45.0                     | 339                                     | 484                                      | 18.5                 | 45.3                |
+| [**YOLOv6-M**](https://github.com/meituan/YOLOv6/releases/download/0.3.0/yolov6m.pt) | 640  | 50.0                     | 175                                     | 226                                      | 34.9                 | 85.8                |
+| [**YOLOv6-L**](https://github.com/meituan/YOLOv6/releases/download/0.3.0/yolov6l.pt) | 640  | 52.8                     | 98                                      | 116                                      | 59.6                 | 150.7               |
+|                              |                               |                                |                    |                        |
+| [**YOLOv6-N6**](https://github.com/meituan/YOLOv6/releases/download/0.3.0/yolov6n6.pt) | 1280 | 44.9                     | 228                                     | 281                                      | 10.4                 | 49.8                |
+| [**YOLOv6-S6**](https://github.com/meituan/YOLOv6/releases/download/0.3.0/yolov6s6.pt) | 1280 | 50.3                     | 98                                      | 108                                      | 41.4                 | 198.0               |
+| [**YOLOv6-M6**](https://github.com/meituan/YOLOv6/releases/download/0.3.0/yolov6m6.pt) | 1280 | 55.2                     | 47                                      | 55                                       | 79.6                 | 379.5               |
+| [**YOLOv6-L6**](https://github.com/meituan/YOLOv6/releases/download/0.3.0/yolov6l6.pt) | 1280 | 57.2                     | 26                                      | 29                                       | 140.4                | 673.4               |
+<details>
+<summary>Table Notes</summary>
+
+- All checkpoints are trained with self-distillation except for YOLOv6-N6/S6 models trained to 300 epochs without distillation.  
+- Results of the mAP and speed are evaluated on [COCO val2017](https://cocodataset.org/#download) dataset with the input resolution of 640×640 for P5 models and 1280x1280 for P6 models.
+- Speed is tested with TensorRT 7.2 on T4.
+- Refer to [Test speed](./docs/Test_speed.md) tutorial to reproduce the speed results of YOLOv6.
+- Params and FLOPs of YOLOv6 are estimated on deployed models.
+</details>
+
+<details>
+<summary>Legacy models</summary>
+
+| Model                                                        | Size | mAP<sup>val<br/>0.5:0.95              | Speed<sup>T4<br/>trt fp16 b1 <br/>(fps) | Speed<sup>T4<br/>trt fp16 b32 <br/>(fps) | Params<br/><sup> (M) | FLOPs<br/><sup> (G) |
+| :----------------------------------------------------------- | ---- | :------------------------------------ | --------------------------------------- | ---------------------------------------- | -------------------- | ------------------- |
+| [**YOLOv6-N**](https://github.com/meituan/YOLOv6/releases/download/0.2.0/yolov6n.pt) | 640  | 35.9<sup>300e</sup><br/>36.3<sup>400e | 802                                     | 1234                                     | 4.3                  | 11.1                |
+| [**YOLOv6-T**](https://github.com/meituan/YOLOv6/releases/download/0.2.0/yolov6t.pt) | 640  | 40.3<sup>300e</sup><br/>41.1<sup>400e | 449                                     | 659                                      | 15.0                 | 36.7                |
+| [**YOLOv6-S**](https://github.com/meituan/YOLOv6/releases/download/0.2.0/yolov6s.pt) | 640  | 43.5<sup>300e</sup><br/>43.8<sup>400e | 358                                     | 495                                      | 17.2                 | 44.2                |
+| [**YOLOv6-M**](https://github.com/meituan/YOLOv6/releases/download/0.2.0/yolov6m.pt) | 640  | 49.5                                  | 179                                     | 233                                      | 34.3                 | 82.2                |
+| [**YOLOv6-L-ReLU**](https://github.com/meituan/YOLOv6/releases/download/0.2.0/yolov6l_relu.pt) | 640  | 51.7                                  | 113                                     | 149                                      | 58.5                 | 144.0               |
+| [**YOLOv6-L**](https://github.com/meituan/YOLOv6/releases/download/0.2.0/yolov6l.pt) | 640  | 52.5                                  | 98                                      | 121                                      | 58.5                 | 144.0               |
+- Speed is tested with TensorRT 7.2 on T4.
+### Quantized model 🚀
+
+| Model                 | Size | Precision | mAP<sup>val<br/>0.5:0.95 | Speed<sup>T4<br/>trt b1 <br/>(fps) | Speed<sup>T4<br/>trt b32 <br/>(fps) |
+| :-------------------- | ---- | --------- | :----------------------- | ---------------------------------- | ----------------------------------- |
+| **YOLOv6-N RepOpt** | 640  | INT8      | 34.8                     | 1114                               | 1828                                |
+| **YOLOv6-N**        | 640  | FP16      | 35.9                     | 802                                | 1234                                |
+| **YOLOv6-T RepOpt** | 640  | INT8      | 39.8                     | 741                                | 1167                                |
+| **YOLOv6-T**        | 640  | FP16      | 40.3                     | 449                                | 659                                 |
+| **YOLOv6-S RepOpt** | 640  | INT8      | 43.3                     | 619                                | 924                                 |
+| **YOLOv6-S**        | 640  | FP16      | 43.5                     | 377                                | 541                                 |
+
+- Speed is tested with TensorRT 8.4 on T4.
+- Precision is figured on models for 300 epochs.
+
+</details>
+
+
+## Quick Start
+
+<details>
+<summary> Install</summary>
+
+
+```shell
+git clone https://github.com/meituan/YOLOv6
+cd YOLOv6
+pip install -r requirements.txt
+```
+</details>
+
+
+
+<details>
+<summary> Reproduce our results on COCO</summary>
+
+Please refer to [Train COCO Dataset](./docs/Train_coco_data.md).
+
+</details>
+
+<details open>
+<summary> Finetune on custom data</summary>
+
+Single GPU
+
+```shell
+# P5 models
+python tools/train.py --batch 32 --conf configs/yolov6s_finetune.py --data data/dataset.yaml --fuse_ab --device 0
+# P6 models
+python tools/train.py --batch 32 --conf configs/yolov6s6_finetune.py --data data/dataset.yaml --img 1280 --device 0
+```
+
+Multi GPUs (DDP mode recommended)
+
+```shell
+# P5 models
+python -m torch.distributed.launch --nproc_per_node 8 tools/train.py --batch 256 --conf configs/yolov6s_finetune.py --data data/dataset.yaml --fuse_ab --device 0,1,2,3,4,5,6,7
+# P6 models
+python -m torch.distributed.launch --nproc_per_node 8 tools/train.py --batch 128 --conf configs/yolov6s6_finetune.py --data data/dataset.yaml --img 1280 --device 0,1,2,3,4,5,6,7
+```
+- fuse_ab: add anchor-based auxiliary branch and use Anchor Aided Training Mode (Not supported on P6 models currently)
+- conf: select config file to specify network/optimizer/hyperparameters. We recommend to apply yolov6n/s/m/l_finetune.py when training on your custom dataset.
+- data: prepare dataset and specify dataset paths in data.yaml ( [COCO](http://cocodataset.org), [YOLO format coco labels](https://github.com/meituan/YOLOv6/releases/download/0.1.0/coco2017labels.zip) )
+- make sure your dataset structure as follows:
+```
+├── coco
+│   ├── annotations
+│   │   ├── instances_train2017.json
+│   │   └── instances_val2017.json
+│   ├── images
+│   │   ├── train2017
+│   │   └── val2017
+│   ├── labels
+│   │   ├── train2017
+│   │   ├── val2017
+│   ├── LICENSE
+│   ├── README.txt
+```
+
+</details>
+
+<details>
+<summary>Resume training</summary>
+
+If your training process is corrupted, you can resume training by
+```
+# single GPU training.
+python tools/train.py --resume
+
+# multi GPU training.
+python -m torch.distributed.launch --nproc_per_node 8 tools/train.py --resume
+```
+Above command will automatically find the latest checkpoint in YOLOv6 directory, then resume the training process. 
+
+Your can also specify a checkpoint path to `--resume` parameter by
+```
+# remember to replace /path/to/your/checkpoint/path to the checkpoint path which you want to resume training.
+--resume /path/to/your/checkpoint/path
+```
+This will resume from the specific checkpoint you provide.
+
+</details>
+
+<details open>
+<summary> Evaluation</summary>
+
+Reproduce mAP on COCO val2017 dataset with 640×640 or 1280x1280 resolution
+
+```shell
+# P5 models
+python tools/eval.py --data data/coco.yaml --batch 32 --weights yolov6s.pt --task val --reproduce_640_eval
+# P6 models
+python tools/eval.py --data data/coco.yaml --batch 32 --weights yolov6s6.pt --task val --reproduce_640_eval --img 1280
+```
+- verbose: set True to print mAP of each classes.
+- do_coco_metric: set True / False to enable / disable pycocotools evaluation method.
+- do_pr_metric: set True / False to print or not to print the precision and recall metrics.
+- config-file: specify a config file to define all the eval params, for example: [yolov6n_with_eval_params.py](configs/experiment/yolov6n_with_eval_params.py)
+</details>
+
+
+<details>
+<summary>Inference</summary>
+
+First, download a pretrained model from the YOLOv6 [release](https://github.com/meituan/YOLOv6/releases/tag/0.3.0) or use your trained model to do inference.
+
+Second, run inference with `tools/infer.py`
+
+```shell
+# P5 models
+python tools/infer.py --weights yolov6s.pt --source img.jpg / imgdir / video.mp4
+# P6 models
+python tools/infer.py --weights yolov6s6.pt --img 1280 1280 --source img.jpg / imgdir / video.mp4
+```
+If you want to inference on local camera or  web camera, you can run:
+```shell
+# P5 models
+python tools/infer.py --weights yolov6s.pt --webcam --webcam-addr 0
+# P6 models
+python tools/infer.py --weights yolov6s6.pt --img 1280 1280 --webcam --webcam-addr 0
+```
+`webcam-addr` can be local camera number id or rtsp address.
+</details>
+
+<details>
+<summary> Deployment</summary>
+
+*  [ONNX](./deploy/ONNX)
+*  [OpenCV Python/C++](./deploy/ONNX/OpenCV)
+*  [OpenVINO](./deploy/OpenVINO)
+*  [TensorRT](./deploy/TensorRT)
+</details>
+
+<details open>
+<summary> Tutorials</summary>
+
+*  [User Guide(zh_CN)](https://yolov6-docs.readthedocs.io/zh_CN/latest/) 
+*  [Train COCO Dataset](./docs/Train_coco_data.md)
+*  [Train custom data](./docs/Train_custom_data.md)
+*  [Test speed](./docs/Test_speed.md)
+*  [Tutorial of Quantization for YOLOv6](./docs/Tutorial%20of%20Quantization.md)
+</details>
+
+<details>
+<summary> Third-party resources</summary>
+
+ * YOLOv6 NCNN Android app demo: [ncnn-android-yolov6](https://github.com/FeiGeChuanShu/ncnn-android-yolov6) from [FeiGeChuanShu](https://github.com/FeiGeChuanShu)
+
+ * YOLOv6 ONNXRuntime/MNN/TNN C++: [YOLOv6-ORT](https://github.com/DefTruth/lite.ai.toolkit/blob/main/lite/ort/cv/yolov6.cpp), [YOLOv6-MNN](https://github.com/DefTruth/lite.ai.toolkit/blob/main/lite/mnn/cv/mnn_yolov6.cpp) and [YOLOv6-TNN](https://github.com/DefTruth/lite.ai.toolkit/blob/main/lite/tnn/cv/tnn_yolov6.cpp) from [DefTruth](https://github.com/DefTruth)
+
+ * YOLOv6 TensorRT Python: [yolov6-tensorrt-python](https://github.com/Linaom1214/TensorRT-For-YOLO-Series) from [Linaom1214](https://github.com/Linaom1214)
+
+ * YOLOv6 TensorRT Windows C++: [yolort](https://github.com/zhiqwang/yolov5-rt-stack/tree/main/deployment/tensorrt-yolov6) from [Wei Zeng](https://github.com/Wulingtian)
+
+ * [YOLOv6 web demo](https://huggingface.co/spaces/nateraw/yolov6) on [Huggingface Spaces](https://huggingface.co/spaces) with [Gradio](https://github.com/gradio-app/gradio). [![Hugging Face Spaces](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-blue)](https://huggingface.co/spaces/nateraw/yolov6)
+
+ * Tutorial: [How to train YOLOv6 on a custom dataset](https://blog.roboflow.com/how-to-train-yolov6-on-a-custom-dataset/) <a href="https://colab.research.google.com/drive/1YnbqOinBZV-c9I7fk_UL6acgnnmkXDMM"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a>
+
+ * YouTube Tutorial: [How to train YOLOv6 on a custom dataset](https://youtu.be/fFCWrMFH2UY)
+
+ * Demo of YOLOv6 inference on Google Colab [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/mahdilamb/YOLOv6/blob/main/inference.ipynb)
+
+ * Blog post: [YOLOv6 Object Detection – Paper Explanation and Inference](https://learnopencv.com/yolov6-object-detection/)
+
+   </details>
+
+### [FAQ（Continuously updated）](https://github.com/meituan/YOLOv6/wiki/FAQ%EF%BC%88Continuously-updated%EF%BC%89)
+
+If you have any questions, welcome to join our WeChat group to discuss and exchange.
+<p align="center">
+  <img src="assets/wechat_qrcode.png" align="middle" width = "1000" />
+</p>

README_cn.md

+<p align="center">
+  <img src="assets/banner-YOLO.png" align="middle" width = "1000" />
+</p>
+
+简体中文 | [English](README.md)
+
+## YOLOv6
+
+官方论文: 
+- [YOLOv6 v3.0: A Full-Scale Reloading](https://arxiv.org/abs/2301.05586) 🔥
+- [YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications](https://arxiv.org/abs/2209.02976)
+
+<p align="center">
+  <img src="assets/speed_comparision_v3.png" align="middle" width = "1000" />
+</p>
+
+
+## 更新日志
+- [2023.01.06] 发布大分辨率 P6 模型以及对 P5 模型做了全面的升级 ⭐️ [模型指标](#模型指标)
+    - 添加 BiC 模块 和 SimCSPSPPF 模块以增强检测网络颈部的表征能力。
+    - 提出一个锚点辅助训练 (AAT) 策略。
+    - 为 YOLOv6 小模型引入一个新的自蒸馏训练策略。
+    - 扩展 YOLOv6 并在 COCO 上取得了实时目标检测 SOTA 的精度和速度。
+- [2022.11.04] 发布 [基础版模型](configs/base/README_cn.md) 简化训练部署流程
+- [2022.09.06] 定制化的模型量化加速方法 🚀 [量化教程](./tools/qat/README.md)
+- [2022.09.05] 发布 M/L 模型，并且进一步提高了 N/T/S 模型的性能  
+- [2022.06.23] 发布 N/T/S v1.0 版本模型
+
+## 模型指标
+| 模型                                                       | 输入尺寸 | mAP<sup>val<br/>0.5:0.95              | 速度<sup>T4<br/>trt fp16 b1 <br/>(fps) | 速度<sup>T4<br/>trt fp16 b32 <br/>(fps) | Params<br/><sup> (M) | FLOPs<br/><sup> (G) |
+| :----------------------------------------------------------- | ---- | :------------------------------------ | --------------------------------------- | ---------------------------------------- | -------------------- | ------------------- |
+| [**YOLOv6-N**](https://github.com/meituan/YOLOv6/releases/download/0.3.0/yolov6n.pt) | 640  | 37.5                     | 779                                     | 1187                                     | 4.7                  | 11.4                |
+| [**YOLOv6-S**](https://github.com/meituan/YOLOv6/releases/download/0.3.0/yolov6s.pt) | 640  | 45.0                     | 339                                     | 484                                      | 18.5                 | 45.3                |
+| [**YOLOv6-M**](https://github.com/meituan/YOLOv6/releases/download/0.3.0/yolov6m.pt) | 640  | 50.0                     | 175                                     | 226                                      | 34.9                 | 85.8                |
+| [**YOLOv6-L**](https://github.com/meituan/YOLOv6/releases/download/0.3.0/yolov6l.pt) | 640  | 52.8                     | 98                                      | 116                                      | 59.6                 | 150.7               |
+|                              |                               |                                |                    |                        |
+| [**YOLOv6-N6**](https://github.com/meituan/YOLOv6/releases/download/0.3.0/yolov6n6.pt) | 1280 | 44.9                     | 228                                     | 281                                      | 10.4                 | 49.8                |
+| [**YOLOv6-S6**](https://github.com/meituan/YOLOv6/releases/download/0.3.0/yolov6s6.pt) | 1280 | 50.3                     | 98                                      | 108                                      | 41.4                 | 198.0               |
+| [**YOLOv6-M6**](https://github.com/meituan/YOLOv6/releases/download/0.3.0/yolov6m6.pt) | 1280 | 55.2                     | 47                                      | 55                                       | 79.6                 | 379.5               |
+| [**YOLOv6-L6**](https://github.com/meituan/YOLOv6/releases/download/0.3.0/yolov6l6.pt) | 1280 | 57.2                     | 26                                      | 29                                       | 140.4                | 673.4               |
+
+<details>
+<summary>表格笔记</summary>
+
+- 除了 YOLOv6-N6/S6 模型是训练了300轮的结果，其余模型均为自蒸馏训练之后的结果；  
+- mAP 和速度指标是在 [COCO val2017](https://cocodataset.org/#download)  数据集上评估的，P5模型输入分辨率为 640×640，P6模型输入分辨率为 1280×1280；
+- 速度是在 T4 上测试的，TensorRT 版本为 7.2；
+- 复现 YOLOv6 的速度指标，请查看 [速度测试](./docs/Test_speed.md) 教程；
+- YOLOv6 的参数和计算量是在推理模式下计算的；
+</details>
+
+<details>
+<summary>旧版模型</summary>
+
+| 模型                                                       | 输入尺寸 | mAP<sup>val<br/>0.5:0.95              | 速度<sup>T4<br/>trt fp16 b1 <br/>(fps) | 速度<sup>T4<br/>trt fp16 b32 <br/>(fps) | Params<br/><sup> (M) | FLOPs<br/><sup> (G) |
+| :----------------------------------------------------------- | ---- | :------------------------------------ | --------------------------------------- | ---------------------------------------- | -------------------- | ------------------- |
+| [**YOLOv6-N**](https://github.com/meituan/YOLOv6/releases/download/0.2.0/yolov6n.pt) | 640  | 35.9<sup>300e</sup><br/>36.3<sup>400e | 802                                     | 1234                                     | 4.3                  | 11.1                |
+| [**YOLOv6-T**](https://github.com/meituan/YOLOv6/releases/download/0.2.0/yolov6t.pt) | 640  | 40.3<sup>300e</sup><br/>41.1<sup>400e | 449                                     | 659                                      | 15.0                 | 36.7                |
+| [**YOLOv6-S**](https://github.com/meituan/YOLOv6/releases/download/0.2.0/yolov6s.pt) | 640  | 43.5<sup>300e</sup><br/>43.8<sup>400e | 358                                     | 495                                      | 17.2                 | 44.2                |
+| [**YOLOv6-M**](https://github.com/meituan/YOLOv6/releases/download/0.2.0/yolov6m.pt) | 640  | 49.5                                  | 179                                     | 233                                      | 34.3                 | 82.2                |
+| [**YOLOv6-L-ReLU**](https://github.com/meituan/YOLOv6/releases/download/0.2.0/yolov6l_relu.pt) | 640  | 51.7                                  | 113                                     | 149                                      | 58.5                 | 144.0               |
+| [**YOLOv6-L**](https://github.com/meituan/YOLOv6/releases/download/0.2.0/yolov6l.pt) | 640  | 52.5                                  | 98                                      | 121                                      | 58.5                 | 144.0               |
+- 速度是在 T4 上测试的，TensorRT 版本为 7.2；
+
+### 量化模型
+
+| 模型                 | 输入尺寸 | 精度 | mAP<sup>val<br/>0.5:0.95 | 速度<sup>T4<br/>trt b1 <br/>(fps) | 速度<sup>T4<br/>trt b32 <br/>(fps) |
+| :-------------------- | ---- | --------- | :----------------------- | ---------------------------------- | ----------------------------------- |
+| **YOLOv6-N RepOpt** | 640  | INT8      | 34.8                     | 1114                               | 1828                                |
+| **YOLOv6-N**        | 640  | FP16      | 35.9                     | 802                                | 1234                                |
+| **YOLOv6-T RepOpt** | 640  | INT8      | 39.8                     | 741                                | 1167                                |
+| **YOLOv6-T**        | 640  | FP16      | 40.3                     | 449                                | 659                                 |
+| **YOLOv6-S RepOpt** | 640  | INT8      | 43.3                     | 619                                | 924                                 |
+| **YOLOv6-S**        | 640  | FP16      | 43.5                     | 377                                | 541                                 |
+
+- 速度是在 T4 上测试的，TensorRT 版本为 8.4；
+- 精度是在训练 300 epoch 的模型上测试的；
+
+</details>
+
+
+## 快速开始
+
+<details>
+<summary> 安装</summary>
+
+
+```shell
+git clone https://github.com/meituan/YOLOv6
+cd YOLOv6
+pip install -r requirements.txt
+```
+</details>
+
+<details>
+<summary> 在 COCO 数据集上复现我们的结果</summary>
+
+请参考教程 [训练 COCO 数据集](./docs/Train_coco_data.md).
+
+</details>
+
+<details open>
+<summary> 在自定义数据集上微调模型 </summary>
+
+单卡
+
+```shell
+# P5 models
+python tools/train.py --batch 32 --conf configs/yolov6s_finetune.py --data data/dataset.yaml --fuse_ab --device 0
+# P6 models
+python tools/train.py --batch 32 --conf configs/yolov6s6_finetune.py --data data/dataset.yaml --img 1280 --device 0
+```
+
+多卡 （我们推荐使用 DDP 模式）
+
+```shell
+# P5 models
+python -m torch.distributed.launch --nproc_per_node 8 tools/train.py --batch 256 --conf configs/yolov6s_finetune.py --data data/dataset.yaml --fuse_ab --device 0,1,2,3,4,5,6,7
+# P6 models
+python -m torch.distributed.launch --nproc_per_node 8 tools/train.py --batch 128 --conf configs/yolov6s6_finetune.py --data data/dataset.yaml --img 1280 --device 0,1,2,3,4,5,6,7
+```
+- fuse_ab: 增加anchor-based预测分支并使用联合锚点训练模式 (P6模型暂不支持此功能)
+- conf: 配置文件路径，里面包含网络结构、优化器配置、超参数信息。如果您是在自己的数据集训练，我们推荐您使用yolov6n/s/m/l_finetune.py配置文件；
+- data: 数据集配置文件，以 COCO 数据集为例，您可以在 [COCO](http://cocodataset.org) 下载数据, 在这里下载 [YOLO 格式标签](https://github.com/meituan/YOLOv6/releases/download/0.1.0/coco2017labels.zip)；
+- 确保您的数据集按照下面这种格式来组织；
+```
+├── coco
+│   ├── annotations
+│   │   ├── instances_train2017.json
+│   │   └── instances_val2017.json
+│   ├── images
+│   │   ├── train2017
+│   │   └── val2017
+│   ├── labels
+│   │   ├── train2017
+│   │   ├── val2017
+```
+
+</details>
+
+<details>
+<summary>恢复训练</summary>
+
+
+如果您的训练进程中断了，您可以这样恢复先前的训练进程。
+```
+# 单卡训练
+python tools/train.py --resume
+
+# 多卡训练
+python -m torch.distributed.launch --nproc_per_node 8 tools/train.py --resume
+```
+上面的命令将自动在 YOLOv6 目录中找到最新保存的模型，然后恢复训练。
+
+您也可以通过 `--resume` 参数指定要恢复的模型路径
+```
+# 记得把 /path/to/your/checkpoint/path  替换为您要恢复训练的模型权重路径
+--resume /path/to/your/checkpoint/path
+```
+这将从您提供的模型路径恢复训练。
+
+</details>
+
+
+<details>
+<summary> 评估</summary>
+在 COCO val2017 数据集上复现我们的结果（输入分辨率 640x640 或 1280x1280）
+
+```shell
+# P5 models
+python tools/eval.py --data data/coco.yaml --batch 32 --weights yolov6s.pt --task val --reproduce_640_eval
+# P6 models
+python tools/eval.py --data data/coco.yaml --batch 32 --weights yolov6s6.pt --task val --reproduce_640_eval --img 1280
+```
+- verbose: 如果要打印每一类的精度信息，请设置为 True；
+- do_coco_metric: 设置 True / False 来打开或关闭 pycocotools 的评估；
+- do_pr_metric: 设置 True / False 来显示或不显示精度和召回的指标；
+- config-file: 指定一个包含所有评估参数的配置文件，例如 [yolov6n_with_eval_params.py](configs/experiment/yolov6n_with_eval_params.py)
+</details>
+
+
+<details>
+<summary>推理</summary>
+
+首先，从 [release页面](https://github.com/meituan/YOLOv6/releases/tag/0.3.0)  下载一个训练好的模型权重文件，或选择您自己训练的模型；
+
+然后，通过 `tools/infer.py`文件进行推理。
+
+```shell
+# P5 models
+python tools/infer.py --weights yolov6s.pt --source img.jpg / imgdir / video.mp4
+# P6 models
+python tools/infer.py --weights yolov6s6.pt --img 1280 1280 --source img.jpg / imgdir / video.mp4
+```
+如果您想使用本地摄像头或者网络摄像头，您可以运行:
+```shell
+# P5 models
+python tools/infer.py --weights yolov6s.pt --webcam --webcam-addr 0
+# P6 models
+python tools/infer.py --weights yolov6s6.pt --img 1280 1280 --webcam --webcam-addr 0
+```
+`webcam-addr` 可以是本地摄像头的 ID，或者是 RTSP 地址。
+</details>
+
+<details>
+<summary> 部署 </summary>
+
+*  [ONNX](./deploy/ONNX)
+*  [OpenCV Python/C++](./deploy/ONNX/OpenCV)
+*  [OpenVINO](./deploy/OpenVINO)
+*  [TensorRT](./deploy/TensorRT)
+</details>
+
+<details open>
+<summary> 教程 </summary>
+
+*  [用户手册（中文版）](https://yolov6-docs.readthedocs.io/zh_CN/latest/) 
+*  [训练 COCO 数据集](./docs/Train_coco_data.md)
+*  [训练自定义数据集](./docs/Train_custom_data.md)
+*  [测速](./docs/Test_speed.md)
+*  [ YOLOv6 量化教程](./docs/Tutorial%20of%20Quantization.md)
+</details>
+
+
+<details>
+<summary> 第三方资源 </summary>
+
+ * YOLOv6 NCNN Android app demo: [ncnn-android-yolov6](https://github.com/FeiGeChuanShu/ncnn-android-yolov6) from [FeiGeChuanShu](https://github.com/FeiGeChuanShu)
+ * YOLOv6 ONNXRuntime/MNN/TNN C++: [YOLOv6-ORT](https://github.com/DefTruth/lite.ai.toolkit/blob/main/lite/ort/cv/yolov6.cpp), [YOLOv6-MNN](https://github.com/DefTruth/lite.ai.toolkit/blob/main/lite/mnn/cv/mnn_yolov6.cpp) and [YOLOv6-TNN](https://github.com/DefTruth/lite.ai.toolkit/blob/main/lite/tnn/cv/tnn_yolov6.cpp) from [DefTruth](https://github.com/DefTruth)
+ * YOLOv6 TensorRT Python: [yolov6-tensorrt-python](https://github.com/Linaom1214/TensorRT-For-YOLO-Series) from [Linaom1214](https://github.com/Linaom1214)
+ * YOLOv6 TensorRT Windows C++: [yolort](https://github.com/zhiqwang/yolov5-rt-stack/tree/main/deployment/tensorrt-yolov6) from [Wei Zeng](https://github.com/Wulingtian)
+ * [YOLOv6 web demo](https://huggingface.co/spaces/nateraw/yolov6) on [Huggingface Spaces](https://huggingface.co/spaces) with [Gradio](https://github.com/gradio-app/gradio). [![Hugging Face Spaces](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-blue)](https://huggingface.co/spaces/nateraw/yolov6)
+ * 教程: [如何用 YOLOv6 训练自己的数据集](https://blog.roboflow.com/how-to-train-yolov6-on-a-custom-dataset/) <a href="https://colab.research.google.com/drive/1YnbqOinBZV-c9I7fk_UL6acgnnmkXDMM"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a>
+ * YOLOv6 在 Google Colab 上的推理 Demo [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/mahdilamb/YOLOv6/blob/main/inference.ipynb)
+</details>
+
+### [FAQ（持续更新）](https://github.com/meituan/YOLOv6/wiki/FAQ%EF%BC%88Continuously-updated%EF%BC%89)
+
+如果您有任何问题，欢迎加入我们的微信群一起讨论交流！
+<p align="center">
+  <img src="assets/wechat_qrcode.png" align="middle" width = "1000" />
+</p>
\ No newline at end of file

configs/base/README.md

+## YOLOv6 base model
+
+English | [简体中文](./README_cn.md)
+
+### Features
+
+- Use only regular convolution and Relu activation functions.
+
+- Apply CSP (1/2 channel dim) blocks in the network structure, except for Nano base model.
+
+Advantage:
+- Adopt a unified network structure and configuration, and the accuracy loss of the PTQ 8-bit quantization model is negligible, about 0.4%.
+- Suitable for users who are just getting started or who need to apply, optimize and deploy an 8-bit quantization model quickly and frequently.
+
+Shortcoming:
+- The accuracy on COCO is slightly lower than the v2.0 released models.
+
+### Performance
+
+| Model                                                         | Size | mAP<sup>val<br/>0.5:0.95 | Speed<sup>T4<br/>trt fp16 b1 <br/>(fps) | Speed<sup>T4<br/>trt fp16 b32 <br/>(fps) | Params<br/><sup> (M) | FLOPs<br/><sup> (G) |
+| :----------------------------------------------------------- | -------- | :----------------------- | -------------------------------------- | --------------------------------------- | -------------------- | ------------------- |
+| [**YOLOv6-N-base**](https://github.com/meituan/YOLOv6/releases/download/0.2.1/yolov6n_base.pt) | 640      | 35.6<sup>400e            | 832                                    | 1249                                    | 4.3                  | 11.1                |
+| [**YOLOv6-S-base**](https://github.com/meituan/YOLOv6/releases/download/0.2.1/yolov6s_base.pt) | 640      | 43.8<sup>400e            | 373                                    | 531                                     | 11.5                 | 27.6                |
+| [**YOLOv6-M-base**](https://github.com/meituan/YOLOv6/releases/download/0.2.1/yolov6m_base.pt) | 640      | 48.8<sup>distill         | 179                                    | 246                                     | 27.7                 | 68.4                |
+| [**YOLOv6-L-base**](https://github.com/meituan/YOLOv6/releases/download/0.2.1/yolov6l_base.pt) | 640      | 51.0<sup>distill         | 115                                    | 153                                     | 58.5                 | 144.0               |
+
+- Speed is tested with TensorRT 7.2 on T4.
+- The processes of model training, evaluation, and inference are the same as the original ones. For details, please refer to [this README](https://github.com/meituan/YOLOv6#quick-start).
\ No newline at end of file

configs/base/README_cn.md

+## YOLOv6 基础版模型
+
+简体中文 | [English](./README.md)
+
+### 模型特点
+
+- 仅使用常规卷积和Relu激活函数
+
+- 网络结构均采用CSP (1/2通道) block，Nano网络除外。
+
+优势：
+- 采用统一的网络结构和配置，且 PTQ 8位量化模型精度损失(约0.4%)较小，适合刚入门或有快速迭代部署8位量化模型需求的用户。
+
+不足：
+- COCO上精度对比2.0版本发布模型稍低。
+
+### 模型指标
+
+| 模型                                                         | 输入尺寸 | mAP<sup>val<br/>0.5:0.95 | 速度<sup>T4<br/>trt fp16 b1 <br/>(fps) | 速度<sup>T4<br/>trt fp16 b32 <br/>(fps) | Params<br/><sup> (M) | FLOPs<br/><sup> (G) |
+| :----------------------------------------------------------- | -------- | :----------------------- | -------------------------------------- | --------------------------------------- | -------------------- | ------------------- |
+| [**YOLOv6-N-base**](https://github.com/meituan/YOLOv6/releases/download/0.2.1/yolov6n_base.pt) | 640      | 35.6<sup>400e            | 832                                    | 1249                                    | 4.3                  | 11.1                |
+| [**YOLOv6-S-base**](https://github.com/meituan/YOLOv6/releases/download/0.2.1/yolov6s_base.pt) | 640      | 43.8<sup>400e            | 373                                    | 531                                     | 11.5                 | 27.6                |
+| [**YOLOv6-M-base**](https://github.com/meituan/YOLOv6/releases/download/0.2.1/yolov6m_base.pt) | 640      | 48.8<sup>distill         | 179                                    | 246                                     | 27.7                 | 68.4                |
+| [**YOLOv6-L-base**](https://github.com/meituan/YOLOv6/releases/download/0.2.1/yolov6l_base.pt) | 640      | 51.0<sup>distill         | 115                                    | 153                                     | 58.5                 | 144.0               |
+
+- 速度是在 T4 上测试的，TensorRT 版本为 7.2；
+- 模型训练、评估、推理流程与原来保持一致，具体可参考 [首页 README 文档](https://github.com/meituan/YOLOv6/blob/main/README_cn.md#%E5%BF%AB%E9%80%9F%E5%BC%80%E5%A7%8B)。

configs/base/yolov6l_base.py

+# YOLOv6 large base model
+model = dict(
+    type='YOLOv6l_base',
+    depth_multiple=1.0,
+    width_multiple=1.0,
+    pretrained=None,
+    backbone=dict(
+        type='CSPBepBackbone',
+        num_repeats=[1, 6, 12, 18, 6],
+        out_channels=[64, 128, 256, 512, 1024],
+        csp_e=float(1)/2,
+        ),
+    neck=dict(
+        type='CSPRepPANNeck',
+        num_repeats=[12, 12, 12, 12],
+        out_channels=[256, 128, 128, 256, 256, 512],
+        csp_e=float(1)/2,
+        ),
+    head=dict(
+        type='EffiDeHead',
+        in_channels=[128, 256, 512],
+        num_layers=3,
+        begin_indices=24,
+        anchors=1,
+        out_indices=[17, 20, 23],
+        strides=[8, 16, 32],
+        iou_type='giou',
+        use_dfl=True,
+        reg_max=16, #if use_dfl is False, please set reg_max to 0
+        distill_weight={
+            'class': 2.0,
+            'dfl': 1.0,
+        },
+    )
+)
+
+solver=dict(
+    optim='SGD',
+    lr_scheduler='Cosine',
+    lr0=0.01,
+    lrf=0.01,
+    momentum=0.937,
+    weight_decay=0.0005,
+    warmup_epochs=3.0,
+    warmup_momentum=0.8,
+    warmup_bias_lr=0.1       
+)
+ 
+data_aug = dict(
+    hsv_h=0.015,  
+    hsv_s=0.7, 
+    hsv_v=0.4,
+    degrees=0.0,
+    translate=0.1,
+    scale=0.9,
+    shear=0.0,
+    flipud=0.0,
+    fliplr=0.5,
+    mosaic=1.0,
+    mixup=0.1,
+)
+training_mode = "conv_relu" 

configs/base/yolov6l_base_finetune.py

+# YOLOv6 large base model
+model = dict(
+    type='YOLOv6l_base',
+    depth_multiple=1.0,
+    width_multiple=1.0,
+    pretrained=None,
+    backbone=dict(
+        type='CSPBepBackbone',
+        num_repeats=[1, 6, 12, 18, 6],
+        out_channels=[64, 128, 256, 512, 1024],
+        csp_e=float(1)/2,
+        ),
+    neck=dict(
+        type='CSPRepPANNeck',
+        num_repeats=[12, 12, 12, 12],
+        out_channels=[256, 128, 128, 256, 256, 512],
+        csp_e=float(1)/2,
+        ),
+    head=dict(
+        type='EffiDeHead',
+        in_channels=[128, 256, 512],
+        num_layers=3,
+        begin_indices=24,
+        anchors=1,
+        out_indices=[17, 20, 23],
+        strides=[8, 16, 32],
+        iou_type='giou',
+        use_dfl=True,
+        reg_max=16, #if use_dfl is False, please set reg_max to 0
+        distill_weight={
+            'class': 2.0,
+            'dfl': 1.0,
+        },
+    )
+)
+
+solver = dict(
+    optim='SGD',
+    lr_scheduler='Cosine',
+    lr0=0.0032,
+    lrf=0.12,
+    momentum=0.843,
+    weight_decay=0.00036,
+    warmup_epochs=2.0,
+    warmup_momentum=0.5,
+    warmup_bias_lr=0.05
+)
+
+data_aug = dict(
+    hsv_h=0.0138,
+    hsv_s=0.664,
+    hsv_v=0.464,
+    degrees=0.373,
+    translate=0.245,
+    scale=0.898,
+    shear=0.602,
+    flipud=0.00856,
+    fliplr=0.5,
+    mosaic=1.0,
+    mixup=0.243,
+)
+training_mode = "conv_relu" 

configs/base/yolov6m_base.py

+# YOLOv6 medium/large base model
+model = dict(
+    type='YOLOv6m_base',
+    depth_multiple=0.80,
+    width_multiple=0.75,
+    pretrained=None,
+    backbone=dict(
+        type='CSPBepBackbone',
+        num_repeats=[1, 6, 12, 18, 6],
+        out_channels=[64, 128, 256, 512, 1024],
+        csp_e=float(1)/2,
+        ),
+    neck=dict(
+        type='CSPRepPANNeck',
+        num_repeats=[12, 12, 12, 12],
+        out_channels=[256, 128, 128, 256, 256, 512],
+        csp_e=float(1)/2,
+        ),
+    head=dict(
+        type='EffiDeHead',
+        in_channels=[128, 256, 512],
+        num_layers=3,
+        begin_indices=24,
+        anchors=1,
+        out_indices=[17, 20, 23],
+        strides=[8, 16, 32],
+        iou_type='giou',
+        use_dfl=True,
+        reg_max=16, #if use_dfl is False, please set reg_max to 0
+        distill_weight={
+            'class': 1.0,
+            'dfl': 1.0,
+        },
+    )
+)
+
+solver=dict(
+    optim='SGD',
+    lr_scheduler='Cosine',
+    lr0=0.01,
+    lrf=0.01,
+    momentum=0.937,
+    weight_decay=0.0005,
+    warmup_epochs=3.0,
+    warmup_momentum=0.8,
+    warmup_bias_lr=0.1       
+)
+ 
+data_aug = dict(
+    hsv_h=0.015,  
+    hsv_s=0.7, 
+    hsv_v=0.4,
+    degrees=0.0,
+    translate=0.1,
+    scale=0.9,
+    shear=0.0,
+    flipud=0.0,
+    fliplr=0.5,
+    mosaic=1.0,
+    mixup=0.1,
+)
+training_mode = "conv_relu" 

configs/base/yolov6m_base_finetune.py

+# YOLOv6 medium/large base model
+model = dict(
+    type='YOLOv6m_base',
+    depth_multiple=0.80,
+    width_multiple=0.75,
+    pretrained=None,
+    backbone=dict(
+        type='CSPBepBackbone',
+        num_repeats=[1, 6, 12, 18, 6],
+        out_channels=[64, 128, 256, 512, 1024],
+        csp_e=float(1)/2,
+        ),
+    neck=dict(
+        type='CSPRepPANNeck',
+        num_repeats=[12, 12, 12, 12],
+        out_channels=[256, 128, 128, 256, 256, 512],
+        csp_e=float(1)/2,
+        ),
+    head=dict(
+        type='EffiDeHead',
+        in_channels=[128, 256, 512],
+        num_layers=3,
+        begin_indices=24,
+        anchors=1,
+        out_indices=[17, 20, 23],
+        strides=[8, 16, 32],
+        iou_type='giou',
+        use_dfl=True,
+        reg_max=16, #if use_dfl is False, please set reg_max to 0
+        distill_weight={
+            'class': 1.0,
+            'dfl': 1.0,
+        },
+    )
+)
+
+solver = dict(
+    optim='SGD',
+    lr_scheduler='Cosine',
+    lr0=0.0032,
+    lrf=0.12,
+    momentum=0.843,
+    weight_decay=0.00036,
+    warmup_epochs=2.0,
+    warmup_momentum=0.5,
+    warmup_bias_lr=0.05
+)
+
+data_aug = dict(
+    hsv_h=0.0138,
+    hsv_s=0.664,
+    hsv_v=0.464,
+    degrees=0.373,
+    translate=0.245,
+    scale=0.898,
+    shear=0.602,
+    flipud=0.00856,
+    fliplr=0.5,
+    mosaic=1.0,
+    mixup=0.243,
+)
+training_mode = "conv_relu" 

configs/base/yolov6n_base.py

+# YOLOv6 nano base model
+model = dict(
+    type='YOLOv6n_base',
+    depth_multiple=0.33,
+    width_multiple=0.25,
+    pretrained=None,
+    backbone=dict(
+        type='EfficientRep',
+        num_repeats=[1, 6, 12, 18, 6],
+        out_channels=[64, 128, 256, 512, 1024],
+        ),
+    neck=dict(
+        type='RepPANNeck',
+        num_repeats=[12, 12, 12, 12],
+        out_channels=[256, 128, 128, 256, 256, 512],
+        ),
+    head=dict(
+        type='EffiDeHead',
+        in_channels=[128, 256, 512],
+        num_layers=3,
+        begin_indices=24,
+        anchors=1,
+        out_indices=[17, 20, 23],
+        strides=[8, 16, 32],
+        iou_type='giou',
+        use_dfl=False,
+        reg_max=0 #if use_dfl is False, please set reg_max to 0
+    )
+)
+
+solver=dict(
+    optim='SGD',
+    lr_scheduler='Cosine',
+    lr0=0.01,
+    lrf=0.01,
+    momentum=0.937,
+    weight_decay=0.0005,
+    warmup_epochs=3.0,
+    warmup_momentum=0.8,
+    warmup_bias_lr=0.1       
+)
+ 
+data_aug = dict(
+    hsv_h=0.015,  
+    hsv_s=0.7, 
+    hsv_v=0.4,
+    degrees=0.0,
+    translate=0.1,
+    scale=0.5,
+    shear=0.0,
+    flipud=0.0,
+    fliplr=0.5,
+    mosaic=1.0,
+    mixup=0.0,
+)
+training_mode = "conv_relu" 

configs/base/yolov6n_base_finetune.py

+# YOLOv6 nano base model
+model = dict(
+    type='YOLOv6n_base',
+    depth_multiple=0.33,
+    width_multiple=0.25,
+    pretrained=None,
+    backbone=dict(
+        type='EfficientRep',
+        num_repeats=[1, 6, 12, 18, 6],
+        out_channels=[64, 128, 256, 512, 1024],
+        ),
+    neck=dict(
+        type='RepPANNeck',
+        num_repeats=[12, 12, 12, 12],
+        out_channels=[256, 128, 128, 256, 256, 512],
+        ),
+    head=dict(
+        type='EffiDeHead',
+        in_channels=[128, 256, 512],
+        num_layers=3,
+        begin_indices=24,
+        anchors=1,
+        out_indices=[17, 20, 23],
+        strides=[8, 16, 32],
+        iou_type='giou',
+        use_dfl=False,
+        reg_max=0 #if use_dfl is False, please set reg_max to 0
+    )
+)
+
+solver = dict(
+    optim='SGD',
+    lr_scheduler='Cosine',
+    lr0=0.0032,
+    lrf=0.12,
+    momentum=0.843,
+    weight_decay=0.00036,
+    warmup_epochs=2.0,
+    warmup_momentum=0.5,
+    warmup_bias_lr=0.05
+)
+
+data_aug = dict(
+    hsv_h=0.0138,
+    hsv_s=0.664,
+    hsv_v=0.464,
+    degrees=0.373,
+    translate=0.245,
+    scale=0.898,
+    shear=0.602,
+    flipud=0.00856,
+    fliplr=0.5,
+    mosaic=1.0,
+    mixup=0.243
+)
+training_mode = "conv_relu" 

configs/base/yolov6s_base.py

+# YOLOv6 small base model
+model = dict(
+    type='YOLOv6s_base',
+    depth_multiple=0.70,
+    width_multiple=0.50,
+    pretrained=None,
+    backbone=dict(
+        type='CSPBepBackbone',
+        num_repeats=[1, 6, 12, 18, 6],
+        out_channels=[64, 128, 256, 512, 1024],
+        csp_e=float(1)/2,
+        ),
+    neck=dict(
+        type='CSPRepPANNeck',
+        num_repeats=[12, 12, 12, 12],
+        out_channels=[256, 128, 128, 256, 256, 512],
+        csp_e=float(1)/2,
+        ),
+    head=dict(
+        type='EffiDeHead',
+        in_channels=[128, 256, 512],
+        num_layers=3,
+        begin_indices=24,
+        anchors=1,
+        out_indices=[17, 20, 23],
+        strides=[8, 16, 32],
+        iou_type='giou',
+        use_dfl=False,
+        reg_max=0 #if use_dfl is False, please set reg_max to 0
+    )
+)
+
+solver=dict(
+    optim='SGD',
+    lr_scheduler='Cosine',
+    lr0=0.01,
+    lrf=0.01,
+    momentum=0.937,
+    weight_decay=0.0005,
+    warmup_epochs=3.0,
+    warmup_momentum=0.8,
+    warmup_bias_lr=0.1       
+)
+ 
+data_aug = dict(
+    hsv_h=0.015,  
+    hsv_s=0.7, 
+    hsv_v=0.4,
+    degrees=0.0,
+    translate=0.1,
+    scale=0.5,
+    shear=0.0,
+    flipud=0.0,
+    fliplr=0.5,
+    mosaic=1.0,
+    mixup=0.0,
+)
+training_mode = "conv_relu" 

configs/base/yolov6s_base_finetune.py

+# YOLOv6 small base model
+model = dict(
+    type='YOLOv6s_base',
+    depth_multiple=0.70,
+    width_multiple=0.50,
+    pretrained=None,
+    backbone=dict(
+        type='CSPBepBackbone',
+        num_repeats=[1, 6, 12, 18, 6],
+        out_channels=[64, 128, 256, 512, 1024],
+        csp_e=float(1)/2,
+        ),
+    neck=dict(
+        type='CSPRepPANNeck',
+        num_repeats=[12, 12, 12, 12],
+        out_channels=[256, 128, 128, 256, 256, 512],
+        csp_e=float(1)/2,
+        ),
+    head=dict(
+        type='EffiDeHead',
+        in_channels=[128, 256, 512],
+        num_layers=3,
+        begin_indices=24,
+        anchors=1,
+        out_indices=[17, 20, 23],
+        strides=[8, 16, 32],
+        iou_type='giou',
+        use_dfl=False,
+        reg_max=0 #if use_dfl is False, please set reg_max to 0
+    )
+)
+
+solver = dict(
+    optim='SGD',
+    lr_scheduler='Cosine',
+    lr0=0.0032,
+    lrf=0.12,
+    momentum=0.843,
+    weight_decay=0.00036,
+    warmup_epochs=2.0,
+    warmup_momentum=0.5,
+    warmup_bias_lr=0.05
+)
+
+data_aug = dict(
+    hsv_h=0.0138,
+    hsv_s=0.664,
+    hsv_v=0.464,
+    degrees=0.373,
+    translate=0.245,
+    scale=0.898,
+    shear=0.602,
+    flipud=0.00856,
+    fliplr=0.5,
+    mosaic=1.0,
+    mixup=0.243
+)
+training_mode = "conv_relu" 

configs/experiment/eval_640_repro.py

+# eval param for different scale
+
+eval_params = dict(
+    default = dict(
+        img_size=640,
+        test_load_size=638,
+        letterbox_return_int=True,
+        scale_exact=True,
+        force_no_pad=True,
+        not_infer_on_rect=True,
+    ),
+    yolov6n = dict(
+        img_size=640,
+        test_load_size=636,
+        letterbox_return_int=True,
+        scale_exact=True,
+        force_no_pad=True,
+        not_infer_on_rect=True,
+    ),
+    yolov6t = dict(
+        img_size=640,
+        test_load_size=634,
+        letterbox_return_int=True,
+        scale_exact=True,
+        force_no_pad=True,
+        not_infer_on_rect=True,
+    ),
+    yolov6s = dict(
+        img_size=640,
+        test_load_size=634,
+        letterbox_return_int=True,
+        scale_exact=True,
+        force_no_pad=True,
+        not_infer_on_rect=True,
+    ),
+    yolov6m = dict(
+        img_size=640,
+        test_load_size=636,
+        letterbox_return_int=True,
+        scale_exact=True,
+        force_no_pad=True,
+        not_infer_on_rect=True,
+    ),
+    yolov6l = dict(
+        img_size=640,
+        test_load_size=636,
+        letterbox_return_int=True,
+        scale_exact=True,
+        force_no_pad=True,
+        not_infer_on_rect=True,
+    ),
+    yolov6l_relu = dict(
+        img_size=640,
+        test_load_size=638,
+        letterbox_return_int=True,
+        scale_exact=True,
+        force_no_pad=True,
+        not_infer_on_rect=True,
+    ),
+    yolov6n6 = dict(
+        img_size=1280,
+        test_load_size=1263,
+        letterbox_return_int=True,
+        scale_exact=True,
+        force_no_pad=True,
+        not_infer_on_rect=True,
+    ),
+    yolov6s6 = dict(
+        img_size=1280,
+        test_load_size=1272,
+        letterbox_return_int=True,
+        scale_exact=True,
+        force_no_pad=True,
+        not_infer_on_rect=True,
+    ),
+    yolov6m6 = dict(
+        img_size=1280,
+        test_load_size=1216,
+        letterbox_return_int=True,
+        scale_exact=True,
+        force_no_pad=True,
+        not_infer_on_rect=True,
+    ),
+    yolov6l6 = dict(
+        img_size=1280,
+        test_load_size=1239,
+        letterbox_return_int=True,
+        scale_exact=True,
+        force_no_pad=True,
+        not_infer_on_rect=True,
+    )
+)

configs/experiment/yolov6n_with_eval_params.py

+# YOLOv6n model with eval param(when traing)
+model = dict(
+    type='YOLOv6n',
+    pretrained=None,
+    depth_multiple=0.33,
+    width_multiple=0.25,
+    backbone=dict(
+        type='EfficientRep',
+        num_repeats=[1, 6, 12, 18, 6],
+        out_channels=[64, 128, 256, 512, 1024],
+        ),
+    neck=dict(
+        type='RepPANNeck',
+        num_repeats=[12, 12, 12, 12],
+        out_channels=[256, 128, 128, 256, 256, 512],
+        ),
+    head=dict(
+        type='EffiDeHead',
+        in_channels=[128, 256, 512],
+        num_layers=3,
+        begin_indices=24,
+        anchors=1,
+        out_indices=[17, 20, 23],
+        strides=[8, 16, 32],
+        iou_type='siou',
+        use_dfl=False,
+        reg_max=0 #if use_dfl is False, please set reg_max to 0
+    )
+)
+
+solver = dict(
+    optim='SGD',
+    lr_scheduler='Cosine',
+    lr0=0.02, #0.01 # 0.02
+    lrf=0.01,
+    momentum=0.937,
+    weight_decay=0.0005,
+    warmup_epochs=3.0,
+    warmup_momentum=0.8,
+    warmup_bias_lr=0.1
+)
+
+data_aug = dict(
+    hsv_h=0.015,
+    hsv_s=0.7,
+    hsv_v=0.4,
+    degrees=0.0,
+    translate=0.1,
+    scale=0.5,
+    shear=0.0,
+    flipud=0.0,
+    fliplr=0.5,
+    mosaic=1.0,
+    mixup=0.0,
+)
+
+# Eval params when eval model.
+# If eval_params item is list, eg conf_thres=[0.03, 0.03],
+# first will be used in train.py and second will be used in eval.py.
+eval_params = dict(
+    batch_size=None,  #None mean will be the same as batch on one device * 2
+    img_size=None,  #None mean will be the same as train image size
+    conf_thres=0.03,
+    iou_thres=0.65,
+
+    #pading and scale coord
+    test_load_size=None, #None mean will be the same as test image size
+    letterbox_return_int=False,
+    force_no_pad=False,
+    not_infer_on_rect=False,
+    scale_exact=False,
+
+    #metric
+    verbose=False,
+    do_coco_metric=True,
+    do_pr_metric=False,
+    plot_curve=False,
+    plot_confusion_matrix=False
+)

configs/experiment/yolov6s_csp_scaled.py

+# YOLOv6m model
+model = dict(
+    type='YOLOv6s_csp',
+    pretrained=None,
+    depth_multiple=0.70,
+    width_multiple=0.50,
+    backbone=dict(
+        type='CSPBepBackbone',
+        num_repeats=[1, 6, 12, 18, 6],
+        out_channels=[64, 128, 256, 512, 1024],
+        csp_e=float(1)/2,
+        ),
+    neck=dict(
+        type='CSPRepPANNeck',
+        num_repeats=[12, 12, 12, 12],
+        out_channels=[256, 128, 128, 256, 256, 512],
+        csp_e=float(1)/2,
+        ),
+    head=dict(
+        type='EffiDeHead',
+        in_channels=[128, 256, 512],
+        num_layers=3,
+        begin_indices=24,
+        anchors=1,
+        out_indices=[17, 20, 23],
+        strides=[8, 16, 32],
+        iou_type='giou',
+        use_dfl=False,
+        reg_max=0 #if use_dfl is False, please set reg_max to 0
+    )
+)
+
+solver=dict(
+    optim='SGD',
+    lr_scheduler='Cosine',
+    lr0=0.01,
+    lrf=0.01,
+    momentum=0.937,
+    weight_decay=0.0005,
+    warmup_epochs=3.0,
+    warmup_momentum=0.8,
+    warmup_bias_lr=0.1
+)
+
+data_aug = dict(
+    hsv_h=0.015,
+    hsv_s=0.7,
+    hsv_v=0.4,
+    degrees=0.0,
+    translate=0.1,
+    scale=0.9,
+    shear=0.0,
+    flipud=0.0,
+    fliplr=0.5,
+    mosaic=1.0,
+    mixup=0.1,
+)

configs/experiment/yolov6t.py

+# YOLOv6t model
+model = dict(
+    type='YOLOv6t',
+    pretrained=None,
+    depth_multiple=0.33,
+    width_multiple=0.375,
+    backbone=dict(
+        type='EfficientRep',
+        num_repeats=[1, 6, 12, 18, 6],
+        out_channels=[64, 128, 256, 512, 1024],
+        ),
+    neck=dict(
+        type='RepPANNeck',
+        num_repeats=[12, 12, 12, 12],
+        out_channels=[256, 128, 128, 256, 256, 512],
+        ),
+    head=dict(
+        type='EffiDeHead',
+        in_channels=[128, 256, 512],
+        num_layers=3,
+        begin_indices=24,
+        anchors=1,
+        out_indices=[17, 20, 23],
+        strides=[8, 16, 32],
+        iou_type='siou',
+        use_dfl=False,
+        reg_max=0 #if use_dfl is False, please set reg_max to 0
+    )
+)
+
+solver = dict(
+    optim='SGD',
+    lr_scheduler='Cosine',
+    lr0=0.01,
+    lrf=0.01,
+    momentum=0.937,
+    weight_decay=0.0005,
+    warmup_epochs=3.0,
+    warmup_momentum=0.8,
+    warmup_bias_lr=0.1
+)
+
+data_aug = dict(
+    hsv_h=0.015,
+    hsv_s=0.7,
+    hsv_v=0.4,
+    degrees=0.0,
+    translate=0.1,
+    scale=0.5,
+    shear=0.0,
+    flipud=0.0,
+    fliplr=0.5,
+    mosaic=1.0,
+    mixup=0.0,
+)

configs/experiment/yolov6t_csp_scaled.py

+# YOLOv6n model
+model = dict(
+    type='YOLOv6n_csp',
+    pretrained=None,
+    depth_multiple=0.60,
+    width_multiple=0.50,
+    backbone=dict(
+        type='CSPBepBackbone',
+        num_repeats=[1, 6, 12, 18, 6],
+        out_channels=[64, 128, 256, 512, 1024],
+        csp_e=float(1)/2,
+        ),
+    neck=dict(
+        type='CSPRepPANNeck',
+        num_repeats=[12, 12, 12, 12],
+        out_channels=[256, 128, 128, 256, 256, 512],
+        csp_e=float(1)/2,
+        ),
+    head=dict(
+        type='EffiDeHead',
+        in_channels=[128, 256, 512],
+        num_layers=3,
+        begin_indices=24,
+        anchors=1,
+        out_indices=[17, 20, 23],
+        strides=[8, 16, 32],
+        iou_type='giou',
+        use_dfl=False,
+        reg_max=0 #if use_dfl is False, please set reg_max to 0
+    )
+)
+
+solver=dict(
+    optim='SGD',
+    lr_scheduler='Cosine',
+    lr0=0.01,
+    lrf=0.01,
+    momentum=0.937,
+    weight_decay=0.0005,
+    warmup_epochs=3.0,
+    warmup_momentum=0.8,
+    warmup_bias_lr=0.1
+)
+
+data_aug = dict(
+    hsv_h=0.015,
+    hsv_s=0.7,
+    hsv_v=0.4,
+    degrees=0.0,
+    translate=0.1,
+    scale=0.9,
+    shear=0.0,
+    flipud=0.0,
+    fliplr=0.5,
+    mosaic=1.0,
+    mixup=0.1,
+)

configs/experiment/yolov6t_finetune.py

+# YOLOv6t model
+model = dict(
+    type='YOLOv6t',
+    pretrained='weights/yolov6t.pt',
+    depth_multiple=0.33,
+    width_multiple=0.375,
+    backbone=dict(
+        type='EfficientRep',
+        num_repeats=[1, 6, 12, 18, 6],
+        out_channels=[64, 128, 256, 512, 1024],
+        ),
+    neck=dict(
+        type='RepPANNeck',
+        num_repeats=[12, 12, 12, 12],
+        out_channels=[256, 128, 128, 256, 256, 512],
+        ),
+    head=dict(
+        type='EffiDeHead',
+        in_channels=[128, 256, 512],
+        num_layers=3,
+        begin_indices=24,
+        anchors=1,
+        out_indices=[17, 20, 23],
+        strides=[8, 16, 32],
+        iou_type='siou',
+        use_dfl=False,
+        reg_max=0 #if use_dfl is False, please set reg_max to 0
+    )
+)
+
+solver = dict(
+    optim='SGD',
+    lr_scheduler='Cosine',
+    lr0=0.0032,
+    lrf=0.12,
+    momentum=0.843,
+    weight_decay=0.00036,
+    warmup_epochs=2.0,
+    warmup_momentum=0.5,
+    warmup_bias_lr=0.05
+)
+
+data_aug = dict(
+    hsv_h=0.0138,
+    hsv_s=0.664,
+    hsv_v=0.464,
+    degrees=0.373,
+    translate=0.245,
+    scale=0.898,
+    shear=0.602,
+    flipud=0.00856,
+    fliplr=0.5,
+    mosaic=1.0,
+    mixup=0.243,
+)

configs/repopt/yolov6_tiny_hs.py

+# YOLOv6t model
+model = dict(
+    type='YOLOv6t',
+    pretrained=None,
+    depth_multiple=0.33,
+    width_multiple=0.375,
+    backbone=dict(
+        type='EfficientRep',
+        num_repeats=[1, 6, 12, 18, 6],
+        out_channels=[64, 128, 256, 512, 1024],
+        ),
+    neck=dict(
+        type='RepPANNeck',
+        num_repeats=[12, 12, 12, 12],
+        out_channels=[256, 128, 128, 256, 256, 512],
+        ),
+    head=dict(
+        type='EffiDeHead',
+        in_channels=[128, 256, 512],
+        num_layers=3,
+        begin_indices=24,
+        anchors=1,
+        out_indices=[17, 20, 23],
+        strides=[8, 16, 32],
+        atss_warmup_epoch=0,
+        iou_type='siou',
+        use_dfl=False,
+        reg_max=0 #if use_dfl is False, please set reg_max to 0
+    )
+)
+
+solver = dict(
+    optim='SGD',
+    lr_scheduler='Cosine',
+    lr0=0.01,
+    lrf=0.01,
+    momentum=0.937,
+    weight_decay=0.0005,
+    warmup_epochs=3.0,
+    warmup_momentum=0.8,
+    warmup_bias_lr=0.1
+)
+
+data_aug = dict(
+    hsv_h=0.015,
+    hsv_s=0.7,
+    hsv_v=0.4,
+    degrees=0.0,
+    translate=0.1,
+    scale=0.5,
+    shear=0.0,
+    flipud=0.0,
+    fliplr=0.5,
+    mosaic=1.0,
+    mixup=0.0,
+)
+
+# Choose Rep-block by the training Mode, choices=["repvgg", "hyper-search", "repopt"]
+training_mode='hyper_search'

configs/repopt/yolov6_tiny_opt.py

+# YOLOv6t model
+model = dict(
+    type='YOLOv6t',
+    pretrained=None,
+    scales='../yolov6_assert/v6t_v2_scale_last.pt',
+    depth_multiple=0.33,
+    width_multiple=0.375,
+    backbone=dict(
+        type='EfficientRep',
+        num_repeats=[1, 6, 12, 18, 6],
+        out_channels=[64, 128, 256, 512, 1024],
+        ),
+    neck=dict(
+        type='RepPANNeck',
+        num_repeats=[12, 12, 12, 12],
+        out_channels=[256, 128, 128, 256, 256, 512],
+        ),
+    head=dict(
+        type='EffiDeHead',
+        in_channels=[128, 256, 512],
+        num_layers=3,
+        begin_indices=24,
+        anchors=1,
+        out_indices=[17, 20, 23],
+        strides=[8, 16, 32],
+        atss_warmup_epoch=0,
+        iou_type='siou',
+        use_dfl=False,
+        reg_max=0 #if use_dfl is False, please set reg_max to 0
+    )
+)
+
+solver = dict(
+    optim='SGD',
+    lr_scheduler='Cosine',
+    lr0=0.01,
+    lrf=0.01,
+    momentum=0.937,
+    weight_decay=0.0005,
+    warmup_epochs=3.0,
+    warmup_momentum=0.8,
+    warmup_bias_lr=0.1
+)
+
+data_aug = dict(
+    hsv_h=0.015,
+    hsv_s=0.7,
+    hsv_v=0.4,
+    degrees=0.0,
+    translate=0.1,
+    scale=0.5,
+    shear=0.0,
+    flipud=0.0,
+    fliplr=0.5,
+    mosaic=1.0,
+    mixup=0.0,
+)
+# Choose Rep-block by the training Mode, choices=["repvgg", "hyper-search", "repopt"]
+training_mode='repopt'

configs/repopt/yolov6_tiny_opt_qat.py

+# YOLOv6t model
+model = dict(
+    type='YOLOv6t',
+    pretrained='./assets/v6s_t.pt',
+    scales='./assets/v6t_v2_scale_last.pt',
+    depth_multiple=0.33,
+    width_multiple=0.375,
+    backbone=dict(
+        type='EfficientRep',
+        num_repeats=[1, 6, 12, 18, 6],
+        out_channels=[64, 128, 256, 512, 1024],
+        ),
+    neck=dict(
+        type='RepPANNeck',
+        num_repeats=[12, 12, 12, 12],
+        out_channels=[256, 128, 128, 256, 256, 512],
+        ),
+    head=dict(
+        type='EffiDeHead',
+        in_channels=[128, 256, 512],
+        num_layers=3,
+        begin_indices=24,
+        anchors=1,
+        out_indices=[17, 20, 23],
+        strides=[8, 16, 32],
+        atss_warmup_epoch=0,
+        iou_type='siou',
+        use_dfl=False,
+        reg_max=0, #if use_dfl is False, please set reg_max to 0
+        distill_weight={
+            'class': 1.0,
+            'dfl': 1.0,
+        },
+    )
+)
+
+solver = dict(
+    optim='SGD',
+    lr_scheduler='Cosine',
+    lr0=0.00001,
+    lrf=0.001,
+    momentum=0.937,
+    weight_decay=0.00005,
+    warmup_epochs=3.0,
+    warmup_momentum=0.8,
+    warmup_bias_lr=0.1
+)
+
+data_aug = dict(
+    hsv_h=0.015,
+    hsv_s=0.7,
+    hsv_v=0.4,
+    degrees=0.0,
+    translate=0.1,
+    scale=0.5,
+    shear=0.0,
+    flipud=0.0,
+    fliplr=0.5,
+    mosaic=1.0,
+    mixup=0.0,
+)
+
+ptq = dict(
+    num_bits = 8,
+    calib_batches = 4,
+    # 'max', 'histogram'
+    calib_method = 'max',
+    # 'entropy', 'percentile', 'mse'
+    histogram_amax_method='entropy',
+    histogram_amax_percentile=99.99,
+    calib_output_path='./',
+    sensitive_layers_skip=False,
+    sensitive_layers_list=[],
+)
+
+qat = dict(
+    calib_pt = './assets/v6s_t_calib_max.pt',
+    sensitive_layers_skip = False,
+    sensitive_layers_list=[],
+)
+
+# Choose Rep-block by the training Mode, choices=["repvgg", "hyper-search", "repopt"]
+training_mode='repopt'

configs/repopt/yolov6n_hs.py

+# YOLOv6n model
+model = dict(
+    type='YOLOv6n',
+    pretrained=None,
+    depth_multiple=0.33,
+    width_multiple=0.25,
+    backbone=dict(
+        type='EfficientRep',
+        num_repeats=[1, 6, 12, 18, 6],
+        out_channels=[64, 128, 256, 512, 1024],
+        ),
+    neck=dict(
+        type='RepPANNeck',
+        num_repeats=[12, 12, 12, 12],
+        out_channels=[256, 128, 128, 256, 256, 512],
+        ),
+    head=dict(
+        type='EffiDeHead',
+        in_channels=[128, 256, 512],
+        num_layers=3,
+        begin_indices=24,
+        anchors=1,
+        out_indices=[17, 20, 23],
+        strides=[8, 16, 32],
+        atss_warmup_epoch=0,
+        iou_type='siou',
+        use_dfl=False,
+        reg_max=0 #if use_dfl is False, please set reg_max to 0
+    )
+)
+
+solver = dict(
+    optim='SGD',
+    lr_scheduler='Cosine',
+    lr0=0.02, #0.01 # 0.02
+    lrf=0.01,
+    momentum=0.937,
+    weight_decay=0.0005,
+    warmup_epochs=3.0,
+    warmup_momentum=0.8,
+    warmup_bias_lr=0.1
+)
+
+data_aug = dict(
+    hsv_h=0.015,
+    hsv_s=0.7,
+    hsv_v=0.4,
+    degrees=0.0,
+    translate=0.1,
+    scale=0.5,
+    shear=0.0,
+    flipud=0.0,
+    fliplr=0.5,
+    mosaic=1.0,
+    mixup=0.0,
+)
+
+# Choose Rep-block by the training Mode, choices=["repvgg", "hyper-search", "repopt"]
+training_mode='hyper_search'

configs/repopt/yolov6n_opt.py

+# YOLOv6n model
+model = dict(
+    type='YOLOv6n',
+    pretrained=None,
+    scales='../yolov6_assert/v6n_v2_scale_last.pt',
+    depth_multiple=0.33,
+    width_multiple=0.25,
+    backbone=dict(
+        type='EfficientRep',
+        num_repeats=[1, 6, 12, 18, 6],
+        out_channels=[64, 128, 256, 512, 1024],
+        ),
+    neck=dict(
+        type='RepPANNeck',
+        num_repeats=[12, 12, 12, 12],
+        out_channels=[256, 128, 128, 256, 256, 512],
+        ),
+    head=dict(
+        type='EffiDeHead',
+        in_channels=[128, 256, 512],
+        num_layers=3,
+        begin_indices=24,
+        anchors=1,
+        out_indices=[17, 20, 23],
+        strides=[8, 16, 32],
+        atss_warmup_epoch=0,
+        iou_type='siou',
+        use_dfl=False,
+        reg_max=0 #if use_dfl is False, please set reg_max to 0
+    )
+)
+
+solver = dict(
+    optim='SGD',
+    lr_scheduler='Cosine',
+    lr0=0.02, #0.01 # 0.02
+    lrf=0.01,
+    momentum=0.937,
+    weight_decay=0.0005,
+    warmup_epochs=3.0,
+    warmup_momentum=0.8,
+    warmup_bias_lr=0.1
+)
+
+data_aug = dict(
+    hsv_h=0.015,
+    hsv_s=0.7,
+    hsv_v=0.4,
+    degrees=0.0,
+    translate=0.1,
+    scale=0.5,
+    shear=0.0,
+    flipud=0.0,
+    fliplr=0.5,
+    mosaic=1.0,
+    mixup=0.0,
+)
+# Choose Rep-block by the training Mode, choices=["repvgg", "hyper-search", "repopt"]
+training_mode='repopt'

configs/repopt/yolov6n_opt_qat.py

+# YOLOv6n model
+model = dict(
+    type='YOLOv6n',
+    pretrained='./assets/v6s_n.pt',
+    scales='./assets/v6n_v2_scale_last.pt',
+    depth_multiple=0.33,
+    width_multiple=0.25,
+    backbone=dict(
+        type='EfficientRep',
+        num_repeats=[1, 6, 12, 18, 6],
+        out_channels=[64, 128, 256, 512, 1024],
+        ),
+    neck=dict(
+        type='RepPANNeck',
+        num_repeats=[12, 12, 12, 12],
+        out_channels=[256, 128, 128, 256, 256, 512],
+        ),
+    head=dict(
+        type='EffiDeHead',
+        in_channels=[128, 256, 512],
+        num_layers=3,
+        begin_indices=24,
+        anchors=1,
+        out_indices=[17, 20, 23],
+        strides=[8, 16, 32],
+        atss_warmup_epoch=0,
+        iou_type='siou',
+        use_dfl=False,
+        reg_max=0, #if use_dfl is False, please set reg_max to 0
+        distill_weight={
+            'class': 1.0,
+            'dfl': 1.0,
+        },
+    )
+)
+
+solver = dict(
+    optim='SGD',
+    lr_scheduler='Cosine',
+    lr0=0.00001, #0.01 # 0.02
+    lrf=0.001,
+    momentum=0.937,
+    weight_decay=0.00005,
+    warmup_epochs=3.0,
+    warmup_momentum=0.8,
+    warmup_bias_lr=0.1
+)
+
+data_aug = dict(
+    hsv_h=0.015,
+    hsv_s=0.7,
+    hsv_v=0.4,
+    degrees=0.0,
+    translate=0.1,
+    scale=0.5,
+    shear=0.0,
+    flipud=0.0,
+    fliplr=0.5,
+    mosaic=1.0,
+    mixup=0.0,
+)
+
+ptq = dict(
+    num_bits = 8,
+    calib_batches = 4,
+    # 'max', 'histogram'
+    calib_method = 'max',
+    # 'entropy', 'percentile', 'mse'
+    histogram_amax_method='entropy',
+    histogram_amax_percentile=99.99,
+    calib_output_path='./',
+    sensitive_layers_skip=False,
+    sensitive_layers_list=[],
+)
+
+qat = dict(
+    calib_pt = './assets/v6s_n_calib_max.pt',
+    sensitive_layers_skip = False,
+    sensitive_layers_list=[],
+)
+# Choose Rep-block by the training Mode, choices=["repvgg", "hyper-search", "repopt"]
+training_mode='repopt'

configs/repopt/yolov6s_hs.py

+# YOLOv6s model
+model = dict(
+    type='YOLOv6s',
+    pretrained=None,
+    depth_multiple=0.33,
+    width_multiple=0.50,
+    backbone=dict(
+        type='EfficientRep',
+        num_repeats=[1, 6, 12, 18, 6],
+        out_channels=[64, 128, 256, 512, 1024],
+        ),
+    neck=dict(
+        type='RepPANNeck',
+        num_repeats=[12, 12, 12, 12],
+        out_channels=[256, 128, 128, 256, 256, 512],
+        ),
+    head=dict(
+        type='EffiDeHead',
+        in_channels=[128, 256, 512],
+        num_layers=3,
+        begin_indices=24,
+        anchors=1,
+        out_indices=[17, 20, 23],
+        strides=[8, 16, 32],
+        atss_warmup_epoch=0,
+        iou_type='giou',
+        use_dfl=False,
+        reg_max=0
+    )
+)
+
+solver = dict(
+    optim='SGD',
+    lr_scheduler='Cosine',
+    lr0=0.01,
+    lrf=0.01,
+    momentum=0.937,
+    weight_decay=0.0005,
+    warmup_epochs=3.0,
+    warmup_momentum=0.8,
+    warmup_bias_lr=0.1
+)
+
+data_aug = dict(
+    hsv_h=0.015,
+    hsv_s=0.7,
+    hsv_v=0.4,
+    degrees=0.0,
+    translate=0.1,
+    scale=0.5,
+    shear=0.0,
+    flipud=0.0,
+    fliplr=0.5,
+    mosaic=1.0,
+    mixup=0.0,
+)
+
+# Choose Rep-block by the training Mode, choices=["repvgg", "hyper-search", "repopt"]
+training_mode='hyper_search'

configs/repopt/yolov6s_opt.py

+# YOLOv6s model
+model = dict(
+    type='YOLOv6s',
+    pretrained=None,
+    scales='../yolov6_assert/v6s_v2_scale.pt',
+    depth_multiple=0.33,
+    width_multiple=0.50,
+    backbone=dict(
+        type='EfficientRep',
+        num_repeats=[1, 6, 12, 18, 6],
+        out_channels=[64, 128, 256, 512, 1024],
+        ),
+    neck=dict(
+        type='RepPANNeck',
+        num_repeats=[12, 12, 12, 12],
+        out_channels=[256, 128, 128, 256, 256, 512],
+        ),
+    head=dict(
+        type='EffiDeHead',
+        in_channels=[128, 256, 512],
+        num_layers=3,
+        begin_indices=24,
+        anchors=1,
+        out_indices=[17, 20, 23],
+        strides=[8, 16, 32],
+        atss_warmup_epoch=0,
+        iou_type='giou',
+        use_dfl=False,
+        reg_max=0
+    )
+)
+
+solver = dict(
+    optim='SGD',
+    lr_scheduler='Cosine',
+    lr0=0.01,
+    lrf=0.01,
+    momentum=0.937,
+    weight_decay=0.0005,
+    warmup_epochs=3.0,
+    warmup_momentum=0.8,
+    warmup_bias_lr=0.1
+)
+
+data_aug = dict(
+    hsv_h=0.015,
+    hsv_s=0.7,
+    hsv_v=0.4,
+    degrees=0.0,
+    translate=0.1,
+    scale=0.5,
+    shear=0.0,
+    flipud=0.0,
+    fliplr=0.5,
+    mosaic=1.0,
+    mixup=0.0,
+)
+
+# Choose Rep-block by the training Mode, choices=["repvgg", "hyper-search", "repopt"]
+training_mode='repopt'

configs/repopt/yolov6s_opt_qat.py

+# YOLOv6s model
+model = dict(
+    type='YOLOv6s',
+    pretrained='./assets/yolov6s_v2_reopt_43.1.pt',
+    scales='./assets/yolov6s_v2_scale.pt',
+    depth_multiple=0.33,
+    width_multiple=0.50,
+    backbone=dict(
+        type='EfficientRep',
+        num_repeats=[1, 6, 12, 18, 6],
+        out_channels=[64, 128, 256, 512, 1024],
+        ),
+    neck=dict(
+        type='RepPANNeck',
+        num_repeats=[12, 12, 12, 12],
+        out_channels=[256, 128, 128, 256, 256, 512],
+        ),
+    head=dict(
+        type='EffiDeHead',
+        in_channels=[128, 256, 512],
+        num_layers=3,
+        begin_indices=24,
+        anchors=1,
+        out_indices=[17, 20, 23],
+        strides=[8, 16, 32],
+        atss_warmup_epoch=0,
+        iou_type = 'giou',
+        use_dfl = False,
+        reg_max = 0,  # if use_dfl is False, please set reg_max to 0
+        distill_weight={
+            'class': 1.0,
+            'dfl': 1.0,
+        },
+    )
+)
+
+solver = dict(
+    optim='SGD',
+    lr_scheduler='Cosine',
+    lr0=0.00001,
+    lrf=0.001,
+    momentum=0.937,
+    weight_decay=0.00005,
+    warmup_epochs=3,
+    warmup_momentum=0.8,
+    warmup_bias_lr=0.1
+)
+
+data_aug = dict(
+    hsv_h=0.015,
+    hsv_s=0.7,
+    hsv_v=0.4,
+    degrees=0.0,
+    translate=0.1,
+    scale=0.5,
+    shear=0.0,
+    flipud=0.0,
+    fliplr=0.5,
+    mosaic=1.0,
+    mixup=0.0,
+)
+
+ptq = dict(
+    num_bits = 8,
+    calib_batches = 4,
+    # 'max', 'histogram'
+    calib_method = 'histogram',
+    # 'entropy', 'percentile', 'mse'
+    histogram_amax_method='entropy',
+    histogram_amax_percentile=99.99,
+    calib_output_path='./',
+    sensitive_layers_skip=False,
+    sensitive_layers_list=['detect.stems.0.conv',
+                           'detect.stems.1.conv',
+                           'detect.stems.2.conv',
+                           'detect.cls_convs.0.conv',
+                           'detect.cls_convs.1.conv',
+                           'detect.cls_convs.2.conv',
+                           'detect.reg_convs.0.conv',
+                           'detect.reg_convs.1.conv',
+                           'detect.reg_convs.2.conv',
+                           'detect.cls_preds.0',
+                           'detect.cls_preds.1',
+                           'detect.cls_preds.2',
+                           'detect.reg_preds.0',
+                           'detect.reg_preds.1',
+                           'detect.reg_preds.2',
+                           ],
+)
+
+qat = dict(
+    calib_pt = './assets/yolov6s_v2_reopt_43.1_calib_histogram.pt',
+    sensitive_layers_skip = False,
+    sensitive_layers_list=['detect.stems.0.conv',
+                           'detect.stems.1.conv',
+                           'detect.stems.2.conv',
+                           'detect.cls_convs.0.conv',
+                           'detect.cls_convs.1.conv',
+                           'detect.cls_convs.2.conv',
+                           'detect.reg_convs.0.conv',
+                           'detect.reg_convs.1.conv',
+                           'detect.reg_convs.2.conv',
+                           'detect.cls_preds.0',
+                           'detect.cls_preds.1',
+                           'detect.cls_preds.2',
+                           'detect.reg_preds.0',
+                           'detect.reg_preds.1',
+                           'detect.reg_preds.2',
+                           ],
+)
+
+# Choose Rep-block by the training Mode, choices=["repvgg", "hyper-search", "repopt"]
+training_mode='repopt'

configs/yolov6l.py

+# YOLOv6l model
+model = dict(
+    type='YOLOv6l',
+    pretrained=None,
+    depth_multiple=1.0,  
+    width_multiple=1.0,
+    backbone=dict(
+        type='CSPBepBackbone',
+        num_repeats=[1, 6, 12, 18, 6],
+        out_channels=[64, 128, 256, 512, 1024],
+        csp_e=float(1)/2,
+        fuse_P2=True,
+        ),
+    neck=dict(
+        type='CSPRepBiFPANNeck',
+        num_repeats=[12, 12, 12, 12],
+        out_channels=[256, 128, 128, 256, 256, 512],
+        csp_e=float(1)/2,
+        ),
+    head=dict(
+        type='EffiDeHead',
+        in_channels=[128, 256, 512],
+        num_layers=3,
+        begin_indices=24,
+        anchors=3,
+        anchors_init=[[10,13, 19,19, 33,23], 
+                      [30,61, 59,59, 59,119], 
+                      [116,90, 185,185, 373,326]],
+        out_indices=[17, 20, 23],
+        strides=[8, 16, 32],
+        atss_warmup_epoch=0,
+        iou_type='giou',
+        use_dfl=True,
+        reg_max=16, #if use_dfl is False, please set reg_max to 0
+        distill_weight={
+            'class': 2.0,
+            'dfl': 1.0,
+        },
+    )
+)
+
+solver=dict(
+    optim='SGD',
+    lr_scheduler='Cosine',
+    lr0=0.01,
+    lrf=0.01,
+    momentum=0.937,
+    weight_decay=0.0005,
+    warmup_epochs=3.0,
+    warmup_momentum=0.8,
+    warmup_bias_lr=0.1       
+)
+ 
+data_aug = dict(
+    hsv_h=0.015,  
+    hsv_s=0.7, 
+    hsv_v=0.4,
+    degrees=0.0,
+    translate=0.1,
+    scale=0.9,
+    shear=0.0,
+    flipud=0.0,
+    fliplr=0.5,
+    mosaic=1.0,
+    mixup=0.1,
+)
+training_mode = "conv_silu" 
+# use normal conv to speed up training and further improve accuracy.

configs/yolov6l6.py

+# YOLOv6l6 model
+model = dict(
+    type='YOLOv6l6',
+    pretrained=None,
+    depth_multiple=1.0,
+    width_multiple=1.0,
+    backbone=dict(
+        type='CSPBepBackbone_P6',
+        num_repeats=[1, 6, 12, 18, 6, 6],
+        out_channels=[64, 128, 256, 512, 768, 1024],
+        csp_e=float(1)/2,
+        fuse_P2=True,
+        ),
+    neck=dict(
+        type='CSPRepBiFPANNeck_P6',
+        num_repeats=[12, 12, 12, 12, 12, 12],
+        out_channels=[512, 256, 128, 256, 512, 1024],
+        csp_e=float(1)/2,
+        ),
+    head=dict(
+        type='EffiDeHead',
+        in_channels=[128, 256, 512, 1024],
+        num_layers=4,
+        anchors=1,
+        strides=[8, 16, 32, 64],
+        atss_warmup_epoch=4,
+        iou_type='giou',
+        use_dfl=True,
+        reg_max=16, #if use_dfl is False, please set reg_max to 0
+        distill_weight={
+            'class': 1.0,
+            'dfl': 1.0,
+        },
+    )
+)
+
+solver = dict(
+    optim='SGD',
+    lr_scheduler='Cosine',
+    lr0=0.01,
+    lrf=0.01,
+    momentum=0.937,
+    weight_decay=0.0005,
+    warmup_epochs=3.0,
+    warmup_momentum=0.8,
+    warmup_bias_lr=0.1
+)
+
+data_aug = dict(
+    hsv_h=0.015,
+    hsv_s=0.7,
+    hsv_v=0.4,
+    degrees=0.0,
+    translate=0.1,
+    scale=0.9,
+    shear=0.0,
+    flipud=0.0,
+    fliplr=0.5,
+    mosaic=1.0,
+    mixup=0.2,
+)
+training_mode = "conv_silu" 
\ No newline at end of file

configs/yolov6l6_finetune.py

+# YOLOv6l6 model
+model = dict(
+    type='YOLOv6l6',
+    pretrained='weights/yolov6l6.pt',
+    depth_multiple=1.0,
+    width_multiple=1.0,
+    backbone=dict(
+        type='CSPBepBackbone_P6',
+        num_repeats=[1, 6, 12, 18, 6, 6],
+        out_channels=[64, 128, 256, 512, 768, 1024],
+        csp_e=float(1)/2,
+        fuse_P2=True,
+        ),
+    neck=dict(
+        type='CSPRepBiFPANNeck_P6',
+        num_repeats=[12, 12, 12, 12, 12, 12],
+        out_channels=[512, 256, 128, 256, 512, 1024],
+        csp_e=float(1)/2,
+        ),
+    head=dict(
+        type='EffiDeHead',
+        in_channels=[128, 256, 512, 1024],
+        num_layers=4,
+        anchors=1,
+        strides=[8, 16, 32, 64],
+        atss_warmup_epoch=4,
+        iou_type='giou',
+        use_dfl=True,
+        reg_max=16, #if use_dfl is False, please set reg_max to 0
+        distill_weight={
+            'class': 1.0,
+            'dfl': 1.0,
+        },
+    )
+)
+
+solver = dict(
+    optim='SGD',
+    lr_scheduler='Cosine',
+    lr0=0.0032,
+    lrf=0.12,
+    momentum=0.843,
+    weight_decay=0.00036,
+    warmup_epochs=2.0,
+    warmup_momentum=0.5,
+    warmup_bias_lr=0.05
+)
+
+data_aug = dict(
+    hsv_h=0.0138,
+    hsv_s=0.664,
+    hsv_v=0.464,
+    degrees=0.373,
+    translate=0.245,
+    scale=0.898,
+    shear=0.602,
+    flipud=0.00856,
+    fliplr=0.5,
+    mosaic=1.0,
+    mixup=0.243,
+)
+training_mode = "conv_silu" 
\ No newline at end of file

configs/yolov6l_finetune.py

+# YOLOv6l model
+model = dict(
+    type='YOLOv6l',
+    pretrained='weights/yolov6l.pt',
+    depth_multiple=1.0,  
+    width_multiple=1.0,
+    backbone=dict(
+        type='CSPBepBackbone',
+        num_repeats=[1, 6, 12, 18, 6],
+        out_channels=[64, 128, 256, 512, 1024],
+        csp_e=float(1)/2,
+        fuse_P2=True,
+        ),
+    neck=dict(
+        type='CSPRepBiFPANNeck',
+        num_repeats=[12, 12, 12, 12],
+        out_channels=[256, 128, 128, 256, 256, 512],
+        csp_e=float(1)/2,
+        ),
+    head=dict(
+        type='EffiDeHead',
+        in_channels=[128, 256, 512],
+        num_layers=3,
+        begin_indices=24,
+        anchors=3,
+        anchors_init=[[10,13, 19,19, 33,23], 
+                      [30,61, 59,59, 59,119], 
+                      [116,90, 185,185, 373,326]],
+        out_indices=[17, 20, 23],
+        strides=[8, 16, 32],
+        atss_warmup_epoch=0,
+        iou_type='giou',
+        use_dfl=True,
+        reg_max=16, #if use_dfl is False, please set reg_max to 0
+        distill_weight={
+            'class': 2.0,
+            'dfl': 1.0,
+        },
+    )
+)
+
+solver = dict(
+    optim='SGD',
+    lr_scheduler='Cosine',
+    lr0=0.0032,
+    lrf=0.12,
+    momentum=0.843,
+    weight_decay=0.00036,
+    warmup_epochs=2.0,
+    warmup_momentum=0.5,
+    warmup_bias_lr=0.05
+)
+
+data_aug = dict(
+    hsv_h=0.0138,
+    hsv_s=0.664,
+    hsv_v=0.464,
+    degrees=0.373,
+    translate=0.245,
+    scale=0.898,
+    shear=0.602,
+    flipud=0.00856,
+    fliplr=0.5,
+    mosaic=1.0,
+    mixup=0.243,
+)
+training_mode = "conv_silu" 
+# use normal conv to speed up training and further improve accuracy.

configs/yolov6m.py

+# YOLOv6m model
+model = dict(
+    type='YOLOv6m',
+    pretrained=None,
+    depth_multiple=0.60,  
+    width_multiple=0.75,
+    backbone=dict(
+        type='CSPBepBackbone',
+        num_repeats=[1, 6, 12, 18, 6],
+        out_channels=[64, 128, 256, 512, 1024],
+        csp_e=float(2)/3,
+        fuse_P2=True,
+        ),
+    neck=dict(
+        type='CSPRepBiFPANNeck',
+        num_repeats=[12, 12, 12, 12],
+        out_channels=[256, 128, 128, 256, 256, 512],
+        csp_e=float(2)/3,
+        ),
+    head=dict(
+        type='EffiDeHead',
+        in_channels=[128, 256, 512],
+        num_layers=3,
+        begin_indices=24,
+        anchors=3,
+        anchors_init=[[10,13, 19,19, 33,23], 
+                      [30,61, 59,59, 59,119], 
+                      [116,90, 185,185, 373,326]],
+        out_indices=[17, 20, 23],
+        strides=[8, 16, 32],
+        atss_warmup_epoch=0,
+        iou_type='giou',
+        use_dfl=True,
+        reg_max=16, #if use_dfl is False, please set reg_max to 0
+        distill_weight={
+            'class': 0.8,
+            'dfl': 1.0,
+        },
+    )
+)
+
+solver=dict(
+    optim='SGD',
+    lr_scheduler='Cosine',
+    lr0=0.01,
+    lrf=0.01,
+    momentum=0.937,
+    weight_decay=0.0005,
+    warmup_epochs=3.0,
+    warmup_momentum=0.8,
+    warmup_bias_lr=0.1       
+)
+ 
+data_aug = dict(
+    hsv_h=0.015,  
+    hsv_s=0.7, 
+    hsv_v=0.4,
+    degrees=0.0,
+    translate=0.1,
+    scale=0.9,
+    shear=0.0,
+    flipud=0.0,
+    fliplr=0.5,
+    mosaic=1.0,
+    mixup=0.1,
+)

configs/yolov6m6.py

+# YOLOv6m6 model
+model = dict(
+    type='YOLOv6m6',
+    pretrained=None,
+    depth_multiple=0.60,
+    width_multiple=0.75,
+    backbone=dict(
+        type='CSPBepBackbone_P6',
+        num_repeats=[1, 6, 12, 18, 6, 6],
+        out_channels=[64, 128, 256, 512, 768, 1024],
+        csp_e=float(2)/3,
+        fuse_P2=True,
+        ),
+    neck=dict(
+        type='CSPRepBiFPANNeck_P6',
+        num_repeats=[12, 12, 12, 12, 12, 12],
+        out_channels=[512, 256, 128, 256, 512, 1024],
+        csp_e=float(2)/3,
+        ),
+    head=dict(
+        type='EffiDeHead',
+        in_channels=[128, 256, 512, 1024],
+        num_layers=4,
+        anchors=1,
+        strides=[8, 16, 32, 64],
+        atss_warmup_epoch=4,
+        iou_type='giou',
+        use_dfl=True,
+        reg_max=16, #if use_dfl is False, please set reg_max to 0
+        distill_weight={
+            'class': 1.0,
+            'dfl': 1.0,
+        },
+    )
+)
+
+solver = dict(
+    optim='SGD',
+    lr_scheduler='Cosine',
+    lr0=0.01,
+    lrf=0.01,
+    momentum=0.937,
+    weight_decay=0.0005,
+    warmup_epochs=3.0,
+    warmup_momentum=0.8,
+    warmup_bias_lr=0.1
+)
+
+data_aug = dict(
+    hsv_h=0.015,
+    hsv_s=0.7,
+    hsv_v=0.4,
+    degrees=0.0,
+    translate=0.1,
+    scale=0.9,
+    shear=0.0,
+    flipud=0.0,
+    fliplr=0.5,
+    mosaic=1.0,
+    mixup=0.1,
+)
\ No newline at end of file

configs/yolov6m6_finetune.py

+# YOLOv6m6 model
+model = dict(
+    type='YOLOv6m6',
+    pretrained='weights/yolov6m6.pt',
+    depth_multiple=0.60,
+    width_multiple=0.75,
+    backbone=dict(
+        type='CSPBepBackbone_P6',
+        num_repeats=[1, 6, 12, 18, 6, 6],
+        out_channels=[64, 128, 256, 512, 768, 1024],
+        csp_e=float(2)/3,
+        fuse_P2=True,
+        ),
+    neck=dict(
+        type='CSPRepBiFPANNeck_P6',
+        num_repeats=[12, 12, 12, 12, 12, 12],
+        out_channels=[512, 256, 128, 256, 512, 1024],
+        csp_e=float(2)/3,
+        ),
+    head=dict(
+        type='EffiDeHead',
+        in_channels=[128, 256, 512, 1024],
+        num_layers=4,
+        anchors=1,
+        strides=[8, 16, 32, 64],
+        atss_warmup_epoch=4,
+        iou_type='giou',
+        use_dfl=True,
+        reg_max=16, #if use_dfl is False, please set reg_max to 0
+        distill_weight={
+            'class': 1.0,
+            'dfl': 1.0,
+        },
+    )
+)
+
+solver = dict(
+    optim='SGD',
+    lr_scheduler='Cosine',
+    lr0=0.0032,
+    lrf=0.12,
+    momentum=0.843,
+    weight_decay=0.00036,
+    warmup_epochs=2.0,
+    warmup_momentum=0.5,
+    warmup_bias_lr=0.05
+)
+
+data_aug = dict(
+    hsv_h=0.0138,
+    hsv_s=0.664,
+    hsv_v=0.464,
+    degrees=0.373,
+    translate=0.245,
+    scale=0.898,
+    shear=0.602,
+    flipud=0.00856,
+    fliplr=0.5,
+    mosaic=1.0,
+    mixup=0.243,
+)
\ No newline at end of file

configs/yolov6m_finetune.py

+# YOLOv6m model
+model = dict(
+    type='YOLOv6m',
+    pretrained='weights/yolov6m.pt',
+    depth_multiple=0.60,  
+    width_multiple=0.75,
+    backbone=dict(
+        type='CSPBepBackbone',
+        num_repeats=[1, 6, 12, 18, 6],
+        out_channels=[64, 128, 256, 512, 1024],
+        csp_e=float(2)/3,
+        fuse_P2=True,
+        ),
+    neck=dict(
+        type='CSPRepBiFPANNeck',
+        num_repeats=[12, 12, 12, 12],
+        out_channels=[256, 128, 128, 256, 256, 512],
+        csp_e=float(2)/3,
+        ),
+    head=dict(
+        type='EffiDeHead',
+        in_channels=[128, 256, 512],
+        num_layers=3,
+        begin_indices=24,
+        anchors=3,
+        anchors_init=[[10,13, 19,19, 33,23], 
+                      [30,61, 59,59, 59,119], 
+                      [116,90, 185,185, 373,326]],
+        out_indices=[17, 20, 23],
+        strides=[8, 16, 32],
+        atss_warmup_epoch=0,
+        iou_type='giou',
+        use_dfl=True,
+        reg_max=16, #if use_dfl is False, please set reg_max to 0
+        distill_weight={
+            'class': 0.8,
+            'dfl': 1.0,
+        },
+    )
+)
+
+solver = dict(
+    optim='SGD',
+    lr_scheduler='Cosine',
+    lr0=0.0032,
+    lrf=0.12,
+    momentum=0.843,
+    weight_decay=0.00036,
+    warmup_epochs=2.0,
+    warmup_momentum=0.5,
+    warmup_bias_lr=0.05
+)
+
+data_aug = dict(
+    hsv_h=0.0138,
+    hsv_s=0.664,
+    hsv_v=0.464,
+    degrees=0.373,
+    translate=0.245,
+    scale=0.898,
+    shear=0.602,
+    flipud=0.00856,
+    fliplr=0.5,
+    mosaic=1.0,
+    mixup=0.243,
+)

configs/yolov6n.py

+# YOLOv6n model
+model = dict(
+    type='YOLOv6n',
+    pretrained=None,
+    depth_multiple=0.33,
+    width_multiple=0.25,
+    backbone=dict(
+        type='EfficientRep',
+        num_repeats=[1, 6, 12, 18, 6],
+        out_channels=[64, 128, 256, 512, 1024],
+        fuse_P2=True,
+        cspsppf=True,
+        ),
+    neck=dict(
+        type='RepBiFPANNeck',
+        num_repeats=[12, 12, 12, 12],
+        out_channels=[256, 128, 128, 256, 256, 512],
+        ),
+    head=dict(
+        type='EffiDeHead',
+        in_channels=[128, 256, 512],
+        num_layers=3,
+        begin_indices=24,
+        anchors=3, 
+        anchors_init=[[10,13, 19,19, 33,23], 
+                      [30,61, 59,59, 59,119], 
+                      [116,90, 185,185, 373,326]],
+        out_indices=[17, 20, 23],
+        strides=[8, 16, 32],
+        atss_warmup_epoch=0,
+        iou_type='siou',
+        use_dfl=False, # set to True if you want to further train with distillation 
+        reg_max=0, # set to 16 if you want to further train with distillation
+        distill_weight={
+            'class': 1.0,
+            'dfl': 1.0,
+        },
+    )
+)
+
+solver = dict(
+    optim='SGD',
+    lr_scheduler='Cosine',
+    lr0=0.02,
+    lrf=0.01,
+    momentum=0.937,
+    weight_decay=0.0005,
+    warmup_epochs=3.0,
+    warmup_momentum=0.8,
+    warmup_bias_lr=0.1
+)
+
+data_aug = dict(
+    hsv_h=0.015,
+    hsv_s=0.7,
+    hsv_v=0.4,
+    degrees=0.0,
+    translate=0.1,
+    scale=0.5,
+    shear=0.0,
+    flipud=0.0,
+    fliplr=0.5,
+    mosaic=1.0,
+    mixup=0.0,
+)

configs/yolov6n6.py

+# YOLOv6n model
+model = dict(
+    type='YOLOv6n6',
+    pretrained=None,
+    depth_multiple=0.33,
+    width_multiple=0.25,
+    backbone=dict(
+        type='EfficientRep6',
+        num_repeats=[1, 6, 12, 18, 6, 6],
+        out_channels=[64, 128, 256, 512, 768, 1024],
+        fuse_P2=True, # if use RepBiFPANNeck6, please set fuse_P2 to True.
+        cspsppf=True,
+        ),
+    neck=dict(
+        type='RepBiFPANNeck6',
+        num_repeats=[12, 12, 12, 12, 12, 12],
+        out_channels=[512, 256, 128, 256, 512, 1024],
+        ),
+    head=dict(
+        type='EffiDeHead',
+        in_channels=[128, 256, 512, 1024],
+        num_layers=4,
+        anchors=1,
+        strides=[8, 16, 32, 64],
+        atss_warmup_epoch=4,
+        iou_type='siou',
+        use_dfl=False,
+        reg_max=0 #if use_dfl is False, please set reg_max to 0
+    )
+)
+
+solver = dict(
+    optim='SGD',
+    lr_scheduler='Cosine',
+    lr0=0.02,
+    lrf=0.01,
+    momentum=0.937,
+    weight_decay=0.0005,
+    warmup_epochs=3.0,
+    warmup_momentum=0.8,
+    warmup_bias_lr=0.1
+)
+
+data_aug = dict(
+    hsv_h=0.015,
+    hsv_s=0.7,
+    hsv_v=0.4,
+    degrees=0.0,
+    translate=0.1,
+    scale=0.5,
+    shear=0.0,
+    flipud=0.0,
+    fliplr=0.5,
+    mosaic=1.0,
+    mixup=0.0,
+)

configs/yolov6n6_finetune.py

+# YOLOv6n model
+model = dict(
+    type='YOLOv6n6',
+    pretrained='weights/yolov6n6.pt',
+    depth_multiple=0.33,
+    width_multiple=0.25,
+    backbone=dict(
+        type='EfficientRep6',
+        num_repeats=[1, 6, 12, 18, 6, 6],
+        out_channels=[64, 128, 256, 512, 768, 1024],
+        fuse_P2=True, # if use RepBiFPANNeck6, please set fuse_P2 to True.
+        cspsppf=True,
+        ),
+    neck=dict(
+        type='RepBiFPANNeck6',
+        num_repeats=[12, 12, 12, 12, 12, 12],
+        out_channels=[512, 256, 128, 256, 512, 1024],
+        ),
+    head=dict(
+        type='EffiDeHead',
+        in_channels=[128, 256, 512, 1024],
+        num_layers=4,
+        anchors=1,
+        strides=[8, 16, 32, 64],
+        atss_warmup_epoch=4,
+        iou_type='siou',
+        use_dfl=False,
+        reg_max=0 #if use_dfl is False, please set reg_max to 0
+    )
+)
+
+solver = dict(
+    optim='SGD',
+    lr_scheduler='Cosine',
+    lr0=0.0032,
+    lrf=0.12,
+    momentum=0.843,
+    weight_decay=0.00036,
+    warmup_epochs=2.0,
+    warmup_momentum=0.5,
+    warmup_bias_lr=0.05
+)
+
+data_aug = dict(
+    hsv_h=0.0138,
+    hsv_s=0.664,
+    hsv_v=0.464,
+    degrees=0.373,
+    translate=0.245,
+    scale=0.898,
+    shear=0.602,
+    flipud=0.00856,
+    fliplr=0.5,
+    mosaic=1.0,
+    mixup=0.243,
+)

configs/yolov6n_finetune.py

+# YOLOv6s model
+model = dict(
+    type='YOLOv6n',
+    pretrained='weights/yolov6n.pt',
+    depth_multiple=0.33,
+    width_multiple=0.25,
+    backbone=dict(
+        type='EfficientRep',
+        num_repeats=[1, 6, 12, 18, 6],
+        out_channels=[64, 128, 256, 512, 1024],
+        fuse_P2=True,
+        cspsppf=True,
+        ),
+    neck=dict(
+        type='RepBiFPANNeck',
+        num_repeats=[12, 12, 12, 12],
+        out_channels=[256, 128, 128, 256, 256, 512],
+        ),
+    head=dict(
+        type='EffiDeHead',
+        in_channels=[128, 256, 512],
+        num_layers=3,
+        begin_indices=24,
+        anchors=3, 
+        anchors_init=[[10,13, 19,19, 33,23], 
+                      [30,61, 59,59, 59,119], 
+                      [116,90, 185,185, 373,326]],
+        out_indices=[17, 20, 23],
+        strides=[8, 16, 32],
+        atss_warmup_epoch=0,
+        iou_type='siou',
+        use_dfl=False, # set to True if you want to further train with distillation 
+        reg_max=0, # set to 16 if you want to further train with distillation
+        distill_weight={
+            'class': 1.0,
+            'dfl': 1.0,
+        },
+    )
+)
+
+solver = dict(
+    optim='SGD',
+    lr_scheduler='Cosine',
+    lr0=0.0032,
+    lrf=0.12,
+    momentum=0.843,
+    weight_decay=0.00036,
+    warmup_epochs=2.0,
+    warmup_momentum=0.5,
+    warmup_bias_lr=0.05
+)
+
+data_aug = dict(
+    hsv_h=0.0138,
+    hsv_s=0.664,
+    hsv_v=0.464,
+    degrees=0.373,
+    translate=0.245,
+    scale=0.898,
+    shear=0.602,
+    flipud=0.00856,
+    fliplr=0.5,
+    mosaic=1.0,
+    mixup=0.243,
+)

configs/yolov6s.py

+# YOLOv6s model
+model = dict(
+    type='YOLOv6s',
+    pretrained=None,
+    depth_multiple=0.33,
+    width_multiple=0.50,
+    backbone=dict(
+        type='EfficientRep',
+        num_repeats=[1, 6, 12, 18, 6],
+        out_channels=[64, 128, 256, 512, 1024],
+        fuse_P2=True,
+        cspsppf=True,
+        ),
+    neck=dict(
+        type='RepBiFPANNeck',
+        num_repeats=[12, 12, 12, 12],
+        out_channels=[256, 128, 128, 256, 256, 512],
+        ),
+    head=dict(
+        type='EffiDeHead',
+        in_channels=[128, 256, 512],
+        num_layers=3,
+        begin_indices=24,
+        anchors=3,
+        anchors_init=[[10,13, 19,19, 33,23], 
+                      [30,61, 59,59, 59,119], 
+                      [116,90, 185,185, 373,326]],
+        out_indices=[17, 20, 23],
+        strides=[8, 16, 32],
+        atss_warmup_epoch=0,
+        iou_type='giou',
+        use_dfl=False, # set to True if you want to further train with distillation 
+        reg_max=0, # set to 16 if you want to further train with distillation
+        distill_weight={
+            'class': 1.0,
+            'dfl': 1.0,
+        },
+    )
+)
+
+solver = dict(
+    optim='SGD',
+    lr_scheduler='Cosine',
+    lr0=0.01,
+    lrf=0.01,
+    momentum=0.937,
+    weight_decay=0.0005,
+    warmup_epochs=3.0,
+    warmup_momentum=0.8,
+    warmup_bias_lr=0.1
+)
+
+data_aug = dict(
+    hsv_h=0.015,
+    hsv_s=0.7,
+    hsv_v=0.4,
+    degrees=0.0,
+    translate=0.1,
+    scale=0.5,
+    shear=0.0,
+    flipud=0.0,
+    fliplr=0.5,
+    mosaic=1.0,
+    mixup=0.0,
+)
+

configs/yolov6s6.py

+# YOLOv6n model
+model = dict(
+    type='YOLOv6s6',
+    pretrained=None,
+    depth_multiple=0.33,
+    width_multiple=0.50,
+    backbone=dict(
+        type='EfficientRep6',
+        num_repeats=[1, 6, 12, 18, 6, 6],
+        out_channels=[64, 128, 256, 512, 768, 1024],
+        fuse_P2=True, # if use RepBiFPANNeck6, please set fuse_P2 to True.
+        cspsppf=True,
+        ),
+    neck=dict(
+        type='RepBiFPANNeck6',
+        num_repeats=[12, 12, 12, 12, 12, 12],
+        out_channels=[512, 256, 128, 256, 512, 1024],
+        ),
+    head=dict(
+        type='EffiDeHead',
+        in_channels=[128, 256, 512, 1024],
+        num_layers=4,
+        anchors=1,
+        strides=[8, 16, 32, 64],
+        atss_warmup_epoch=4,
+        iou_type='giou',
+        use_dfl=False,
+        reg_max=0 #if use_dfl is False, please set reg_max to 0
+    )
+)
+
+solver = dict(
+    optim='SGD',
+    lr_scheduler='Cosine',
+    lr0=0.01,
+    lrf=0.01,
+    momentum=0.937,
+    weight_decay=0.0005,
+    warmup_epochs=3.0,
+    warmup_momentum=0.8,
+    warmup_bias_lr=0.1
+)
+
+data_aug = dict(
+    hsv_h=0.015,
+    hsv_s=0.7,
+    hsv_v=0.4,
+    degrees=0.0,
+    translate=0.1,
+    scale=0.5,
+    shear=0.0,
+    flipud=0.0,
+    fliplr=0.5,
+    mosaic=1.0,
+    mixup=0.0,
+)

configs/yolov6s6_finetune.py

+# YOLOv6n model
+model = dict(
+    type='YOLOv6s6',
+    pretrained='weights/yolov6s6.pt',
+    depth_multiple=0.33,
+    width_multiple=0.50,
+    backbone=dict(
+        type='EfficientRep6',
+        num_repeats=[1, 6, 12, 18, 6, 6],
+        out_channels=[64, 128, 256, 512, 768, 1024],
+        fuse_P2=True, # if use RepBiFPANNeck6, please set fuse_P2 to True.
+        cspsppf=True,
+        ),
+    neck=dict(
+        type='RepBiFPANNeck6',
+        num_repeats=[12, 12, 12, 12, 12, 12],
+        out_channels=[512, 256, 128, 256, 512, 1024],
+        ),
+    head=dict(
+        type='EffiDeHead',
+        in_channels=[128, 256, 512, 1024],
+        num_layers=4,
+        anchors=1,
+        strides=[8, 16, 32, 64],
+        atss_warmup_epoch=4,
+        iou_type='giou',
+        use_dfl=False,
+        reg_max=0 #if use_dfl is False, please set reg_max to 0
+    )
+)
+
+solver = dict(
+    optim='SGD',
+    lr_scheduler='Cosine',
+    lr0=0.0032,
+    lrf=0.12,
+    momentum=0.843,
+    weight_decay=0.00036,
+    warmup_epochs=2.0,
+    warmup_momentum=0.5,
+    warmup_bias_lr=0.05
+)
+
+data_aug = dict(
+    hsv_h=0.0138,
+    hsv_s=0.664,
+    hsv_v=0.464,
+    degrees=0.373,
+    translate=0.245,
+    scale=0.898,
+    shear=0.602,
+    flipud=0.00856,
+    fliplr=0.5,
+    mosaic=1.0,
+    mixup=0.243,
+)
\ No newline at end of file

configs/yolov6s_finetune.py

+# YOLOv6s model
+model = dict(
+    type='YOLOv6s',
+    pretrained='weights/yolov6s.pt',
+    depth_multiple=0.33,
+    width_multiple=0.50,
+    backbone=dict(
+        type='EfficientRep',
+        num_repeats=[1, 6, 12, 18, 6],
+        out_channels=[64, 128, 256, 512, 1024],
+        fuse_P2=True,
+        cspsppf=True,
+        ),
+    neck=dict(
+        type='RepBiFPANNeck',
+        num_repeats=[12, 12, 12, 12],
+        out_channels=[256, 128, 128, 256, 256, 512],
+        ),
+    head=dict(
+        type='EffiDeHead',
+        in_channels=[128, 256, 512],
+        num_layers=3,
+        begin_indices=24,
+        anchors=3,
+        anchors_init=[[10,13, 19,19, 33,23], 
+                      [30,61, 59,59, 59,119], 
+                      [116,90, 185,185, 373,326]],
+        out_indices=[17, 20, 23],
+        strides=[8, 16, 32],
+        atss_warmup_epoch=0,
+        iou_type='giou',
+        use_dfl=False, # set to True if you want to further train with distillation 
+        reg_max=0, # set to 16 if you want to further train with distillation
+        distill_weight={
+            'class': 1.0,
+            'dfl': 1.0,
+        },
+    )
+)
+
+solver = dict(
+    optim='SGD',
+    lr_scheduler='Cosine',
+    lr0=0.0032,
+    lrf=0.12,
+    momentum=0.843,
+    weight_decay=0.00036,
+    warmup_epochs=2.0,
+    warmup_momentum=0.5,
+    warmup_bias_lr=0.05
+)
+
+data_aug = dict(
+    hsv_h=0.0138,
+    hsv_s=0.664,
+    hsv_v=0.464,
+    degrees=0.373,
+    translate=0.245,
+    scale=0.898,
+    shear=0.602,
+    flipud=0.00856,
+    fliplr=0.5,
+    mosaic=1.0,
+    mixup=0.243,
+)
\ No newline at end of file

data/coco.yaml

+# COCO 2017 dataset http://cocodataset.org
+train: ../coco/images/train2017 # 118287 images
+val: ../coco/images/val2017  # 5000 images
+test: ../coco/images/test2017
+anno_path: ../coco/annotations/instances_val2017.json
+
+# number of classes
+nc: 80
+# whether it is coco dataset, only coco dataset should be set to True.
+is_coco: True
+
+# class names
+names: [ 'person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train', 'truck', 'boat', 'traffic light',
+         'fire hydrant', 'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow',
+         'elephant', 'bear', 'zebra', 'giraffe', 'backpack', 'umbrella', 'handbag', 'tie', 'suitcase', 'frisbee',
+         'skis', 'snowboard', 'sports ball', 'kite', 'baseball bat', 'baseball glove', 'skateboard', 'surfboard',
+         'tennis racket', 'bottle', 'wine glass', 'cup', 'fork', 'knife', 'spoon', 'bowl', 'banana', 'apple',
+         'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza', 'donut', 'cake', 'chair', 'couch',
+         'potted plant', 'bed', 'dining table', 'toilet', 'tv', 'laptop', 'mouse', 'remote', 'keyboard', 'cell phone',
+         'microwave', 'oven', 'toaster', 'sink', 'refrigerator', 'book', 'clock', 'vase', 'scissors', 'teddy bear',
+         'hair drier', 'toothbrush' ]

data/dataset.yaml

+# Please insure that your custom_dataset are put in same parent dir with YOLOv6_DIR
+train: ../custom_dataset/images/train # train images
+val: ../custom_dataset/images/val # val images
+test: ../custom_dataset/images/test # test images (optional)
+
+# whether it is coco dataset, only coco dataset should be set to True.
+is_coco: False
+# Classes
+nc: 20  # number of classes
+names: ['aeroplane', 'bicycle', 'bird', 'boat', 'bottle', 'bus', 'car', 'cat', 'chair', 'cow', 'diningtable', 'dog',
+        'horse', 'motorbike', 'person', 'pottedplant', 'sheep', 'sofa', 'train', 'tvmonitor']  # class names

data/test1.yaml

+# mytrain
+train: ./data/test1/images/train
+val: ./data/test1/images/val
+test: ./data/test1/images/test
+#anno_path: ../coco/annotations/instances_val2017.json
+
+# number of classes
+nc: 8
+# whether it is coco dataset, only coco dataset should be set to True.
+is_coco: False
+
+# class names
+names: ['person', 'face','hand','garb','larwas','conwas','foowas','recyc']

data/test1/annotations/instances_val.json

+{"categories": [{"id": 0, "name": "person", "supercategory": ""}, {"id": 1, "name": "face", "supercategory": ""}, {"id": 2, "name": "hand", "supercategory": ""}, {"id": 3, "name": "garb", "supercategory": ""}, {"id": 4, "name": "larwas", "supercategory": ""}, {"id": 5, "name": "conwas", "supercategory": ""}, {"id": 6, "name": "foowas", "supercategory": ""}, {"id": 7, "name": "recyc", "supercategory": ""}], "annotations": [{"area": 44604.00207138064, "bbox": [381.00001335144043, 66.00000143051147, 126.00000381469727, 354.0000057220459], "category_id": 0, "id": 0, "image_id": "garb01_145", "iscrowd": 0, "segmentation": []}, {"area": 45745.99769973756, "bbox": [485.0000190734863, 92.00000524520874, 177.99999237060547, 256.99999809265137], "category_id": 0, "id": 1, "image_id": "garb01_145", "iscrowd": 0, "segmentation": []}, {"area": 5900.0003767013595, "bbox": [490.0000071525574, 0.9999972581863403, 59.000000953674316, 100.00000476837158], "category_id": 0, "id": 2, "image_id": "garb01_145", "iscrowd": 0, "segmentation": []}, {"area": 3408.0000610351535, "bbox": [478.0000066757202, 248.00000935792923, 48.00000190734863, 70.99999845027924], "category_id": 3, "id": 3, "image_id": "garb01_145", "iscrowd": 0, "segmentation": []}, {"area": 1944.0000257492045, "bbox": [394.9999928474426, 287.0000070333481, 35.999999046325684, 54.00000214576721], "category_id": 3, "id": 4, "image_id": "garb01_145", "iscrowd": 0, "segmentation": []}, {"area": 43839.99971628188, "bbox": [793.0000019073486, 560.0000041723251, 273.99999618530273, 160.0000011920929], "category_id": 7, "id": 5, "image_id": "garb01_145", "iscrowd": 0, "segmentation": []}, {"area": 30044.00137519838, "bbox": [521.0000133514404, 47.99999713897705, 116.00000381469727, 259.0000033378601], "category_id": 0, "id": 6, "image_id": "garb01_146", "iscrowd": 0, "segmentation": []}, {"area": 43647.99871635437, "bbox": [373.00000190734863, 67.99999594688416, 123.99999618530273, 352.00000047683716], "category_id": 0, "id": 7, "image_id": "garb01_146", "iscrowd": 0, "segmentation": []}, {"area": 2771.9999341964694, "bbox": [506.00000858306885, 199.9999988079071, 41.99999809265137, 66.00000143051147], "category_id": 3, "id": 8, "image_id": "garb01_146", "iscrowd": 0, "segmentation": []}, {"area": 2072.000101685525, "bbox": [394.99998450279236, 284.000001847744, 37.00000047683716, 56.00000202655792], "category_id": 3, "id": 9, "image_id": "garb01_146", "iscrowd": 0, "segmentation": []}, {"area": 43923.99766778949, "bbox": [789.0000343322754, 562.0000201463699, 277.99999237060547, 157.99999594688416], "category_id": 7, "id": 10, "image_id": "garb01_146", "iscrowd": 0, "segmentation": []}, {"area": 110160.00308990479, "bbox": [293.0000114440918, 103.99999380111694, 272.00000762939453, 405.0], "category_id": 0, "id": 11, "image_id": "garb01_147", "iscrowd": 0, "segmentation": []}, {"area": 12861.999757766716, "bbox": [558.0000066757202, 368.00002098083496, 118.00000190734863, 108.99999618530273], "category_id": 3, "id": 12, "image_id": "garb01_147", "iscrowd": 0, "segmentation": []}, {"area": 19840.000480413437, "bbox": [585.9999847412109, 272.999991774559, 155.0, 128.00000309944153], "category_id": 4, "id": 13, "image_id": "garb01_147", "iscrowd": 0, "segmentation": []}, {"area": 6350.000023841858, "bbox": [535.9999847412109, 384.9999797344208, 50.0, 127.00000047683716], "category_id": 7, "id": 14, "image_id": "garb01_147", "iscrowd": 0, "segmentation": []}, {"area": 3960.000060796736, "bbox": [517.0000004768372, 276.0000076889992, 65.99999904632568, 60.00000178813934], "category_id": 3, "id": 15, "image_id": "garb01_147", "iscrowd": 0, "segmentation": []}, {"area": 7525.999831199647, "bbox": [534.9999928474426, 275.9999942779541, 70.99999904632568, 105.99999904632568], "category_id": 7, "id": 16, "image_id": "garb01_147", "iscrowd": 0, "segmentation": []}, {"area": 72089.99691009521, "bbox": [393.0000114440918, 105.00000715255737, 177.99999237060547, 405.0], "category_id": 0, "id": 17, "image_id": "garb01_148", "iscrowd": 0, "segmentation": []}, {"area": 13684.999703168865, "bbox": [565.9999942779541, 365.9999889135361, 118.99999618530273, 115.0000011920929], "category_id": 3, "id": 18, "image_id": "garb01_148", "iscrowd": 0, "segmentation": []}, {"area": 2322.0001952648204, "bbox": [396.9999837875366, 240.00000178813934, 43.00000190734863, 54.00000214576721], "category_id": 3, "id": 19, "image_id": "garb01_148", "iscrowd": 0, "segmentation": []}, {"area": 20033.999178171165, "bbox": [584.9999713897705, 273.9999943971634, 158.99999618530273, 125.99999785423279], "category_id": 4, "id": 20, "image_id": "garb01_148", "iscrowd": 0, "segmentation": []}, {"area": 2345.9999349117284, "bbox": [544.0000081062317, 285.00000447034836, 45.999999046325684, 50.99999964237213], "category_id": 3, "id": 21, "image_id": "garb01_148", "iscrowd": 0, "segmentation": []}, {"area": 2789.9999141693115, "bbox": [554.9999928474426, 419.99998569488525, 30.999999046325684, 90.0], "category_id": 7, "id": 22, "image_id": "garb01_148", "iscrowd": 0, "segmentation": []}, {"area": 1350.0, "bbox": [559.0000152587891, 327.0000100135803, 30.0, 45.0], "category_id": 7, "id": 23, "image_id": "garb01_148", "iscrowd": 0, "segmentation": []}, {"area": 1350.0000402331352, "bbox": [544.0000152587891, 271.99999049305916, 45.0, 30.00000089406967], "category_id": 7, "id": 24, "image_id": "garb01_148", "iscrowd": 0, "segmentation": []}, {"area": 123074.00310134872, "bbox": [268.0000114440918, 101.9999885559082, 297.99999237060547, 413.00002098083496], "category_id": 0, "id": 25, "image_id": "garb01_149", "iscrowd": 0, "segmentation": []}, {"area": 17685.00051498413, "bbox": [206.99999809265137, 51.00000500679016, 131.00000381469727, 135.0], "category_id": 3, "id": 26, "image_id": "garb01_149", "iscrowd": 0, "segmentation": []}, {"area": 14145.00036597252, "bbox": [560.0000143051147, 365.9999889135361, 123.00000190734863, 115.0000011920929], "category_id": 3, "id": 27, "image_id": "garb01_149", "iscrowd": 0, "segmentation": []}, {"area": 20033.999178171165, "bbox": [583.0000019073486, 273.0000025033951, 158.99999618530273, 125.99999785423279], "category_id": 4, "id": 28, "image_id": "garb01_149", "iscrowd": 0, "segmentation": []}, {"area": 4088.0002547502554, "bbox": [515.0000143051147, 281.99999660253525, 73.00000190734863, 56.00000202655792], "category_id": 3, "id": 29, "image_id": "garb01_149", "iscrowd": 0, "segmentation": []}, {"area": 2576.0001029968234, "bbox": [532.9999852180481, 336.0000067949295, 55.999999046325684, 46.00000262260437], "category_id": 7, "id": 30, "image_id": "garb01_149", "iscrowd": 0, "segmentation": []}, {"area": 6551.999648094181, "bbox": [534.9999856948853, 385.9999877214432, 51.99999809265137, 125.99999785423279], "category_id": 7, "id": 31, "image_id": "garb01_149", "iscrowd": 0, "segmentation": []}, {"area": 1431.0001083612462, "bbox": [533.9999914169312, 273.0000051856041, 53.00000190734863, 27.000001072883606], "category_id": 7, "id": 32, "image_id": "garb01_149", "iscrowd": 0, "segmentation": []}, {"area": 104940.0037765503, "bbox": [347.00000762939453, 29.000000953674316, 220.0, 477.0000171661377], "category_id": 0, "id": 33, "image_id": "garb01_150", "iscrowd": 0, "segmentation": []}, {"area": 13090.000534057617, "bbox": [327.00000762939453, 33.99999260902405, 70.0, 187.00000762939453], "category_id": 3, "id": 34, "image_id": "garb01_150", "iscrowd": 0, "segmentation": []}, {"area": 15575.999554634098, "bbox": [551.9999933242798, 363.99998366832733, 131.99999809265137, 117.99999833106995], "category_id": 3, "id": 35, "image_id": "garb01_150", "iscrowd": 0, "segmentation": []}, {"area": 19812.00055885315, "bbox": [585.0000286102295, 271.9999945163727, 156.00000381469727, 127.00000047683716], "category_id": 4, "id": 36, "image_id": "garb01_150", "iscrowd": 0, "segmentation": []}, {"area": 5535.000032186508, "bbox": [534.0000152587891, 386.0000091791153, 45.0, 123.00000071525574], "category_id": 7, "id": 37, "image_id": "garb01_150", "iscrowd": 0, "segmentation": []}, {"area": 2819.9999928474426, "bbox": [530.0, 334.0000095963478, 60.0, 46.99999988079071], "category_id": 7, "id": 38, "image_id": "garb01_150", "iscrowd": 0, "segmentation": []}, {"area": 3976.000090479849, "bbox": [517.0000004768372, 281.99999660253525, 70.99999904632568, 56.00000202655792], "category_id": 3, "id": 39, "image_id": "garb01_150", "iscrowd": 0, "segmentation": []}, {"area": 1507.9999942779523, "bbox": [534.9999856948853, 272.99999713897705, 51.99999809265137, 29.000000953674316], "category_id": 7, "id": 40, "image_id": "garb01_150", "iscrowd": 0, "segmentation": []}], "images": [{"file_name": "garb01_145.jpg", "id": "garb01_145", "width": 1280, "height": 720}, {"file_name": "garb01_146.jpg", "id": "garb01_146", "width": 1280, "height": 720}, {"file_name": "garb01_147.jpg", "id": "garb01_147", "width": 1280, "height": 720}, {"file_name": "garb01_148.jpg", "id": "garb01_148", "width": 1280, "height": 720}, {"file_name": "garb01_149.jpg", "id": "garb01_149", "width": 1280, "height": 720}, {"file_name": "garb01_150.jpg", "id": "garb01_150", "width": 1280, "height": 720}]}
\ No newline at end of file

data/test1/images/.val.json

+{"information": {"./data/test1/images/val\\garb01_145.jpg": {"shape": [1280, 720], "labels": [[0.0, 0.34687501192092896, 0.3375000059604645, 0.09843750298023224, 0.49166667461395264], [0.0, 0.44843751192092896, 0.3062500059604645, 0.13906249403953552, 0.3569444417953491], [0.0, 0.4058593809604645, 0.07083333283662796, 0.04609375074505806, 0.1388888955116272], [3.0, 0.3921875059604645, 0.39375001192092896, 0.03750000149011612, 0.09861110895872116], [3.0, 0.3226562440395355, 0.43611112236976624, 0.02812499925494194, 0.07500000298023224], [7.0, 0.7265625, 0.8888888955116272, 0.21406249701976776, 0.2222222238779068]]}, "./data/test1/images/val\\garb01_146.jpg": {"shape": [1280, 720], "labels": [[0.0, 0.45234376192092896, 0.2465277761220932, 0.09062500298023224, 0.35972222685813904], [0.0, 0.33984375, 0.33888888359069824, 0.09687499701976776, 0.4888888895511627], [3.0, 0.4117187559604645, 0.3236111104488373, 0.03281249850988388, 0.09166666865348816], [3.0, 0.32304686307907104, 0.4333333373069763, 0.02890625037252903, 0.07777778059244156], [7.0, 0.7250000238418579, 0.8902778029441833, 0.21718749403953552, 0.21944443881511688]]}, "./data/test1/images/val\\garb01_147.jpg": {"shape": [1280, 720], "labels": [[0.0, 0.33515626192092896, 0.42569443583488464, 0.21250000596046448, 0.5625], [3.0, 0.4820312559604645, 0.5868055820465088, 0.09218750149011612, 0.15138888359069824], [4.0, 0.518359363079071, 0.4680555462837219, 0.12109375, 0.17777778208255768], [7.0, 0.43828123807907104, 0.6229166388511658, 0.0390625, 0.17638888955116272], [3.0, 0.4296875, 0.42500001192092896, 0.05156249925494194, 0.0833333358168602], [7.0, 0.4457031190395355, 0.45694443583488464, 0.05546874925494194, 0.14722222089767456]]}, "./data/test1/images/val\\garb01_148.jpg": {"shape": [1280, 720], "labels": [[0.0, 0.3765625059604645, 0.4270833432674408, 0.13906249403953552, 0.5625], [3.0, 0.4886718690395355, 0.5881944298744202, 0.09296874701976776, 0.1597222238779068], [3.0, 0.32695311307907104, 0.3708333373069763, 0.03359375149011612, 0.07500000298023224], [4.0, 0.5191406011581421, 0.4680555462837219, 0.12421874701976776, 0.17499999701976776], [3.0, 0.4429687559604645, 0.4312500059604645, 0.03593749925494194, 0.07083333283662796], [7.0, 0.4457031190395355, 0.6458333134651184, 0.02421874925494194, 0.125], [7.0, 0.44843751192092896, 0.4854166805744171, 0.0234375, 0.0625], [7.0, 0.44257813692092896, 0.3986110985279083, 0.03515625, 0.0416666679084301]]}, "./data/test1/images/val\\garb01_149.jpg": {"shape": [1280, 720], "labels": [[0.0, 0.3257812559604645, 0.42847222089767456, 0.23281249403953552, 0.5736111402511597], [3.0, 0.212890625, 0.16458334028720856, 0.10234375298023224, 0.1875], [3.0, 0.48554688692092896, 0.5881944298744202, 0.09609375149011612, 0.1597222238779068], [4.0, 0.517578125, 0.46666666865348816, 0.12421874701976776, 0.17499999701976776], [3.0, 0.43085938692092896, 0.4305555522441864, 0.05703125149011612, 0.07777778059244156], [7.0, 0.43828123807907104, 0.49861112236976624, 0.04374999925494194, 0.06388889253139496], [7.0, 0.43828123807907104, 0.6236110925674438, 0.04062499850988388, 0.17499999701976776], [7.0, 0.4378906190395355, 0.39791667461395264, 0.04140625149011612, 0.03750000149011612]]}, "./data/test1/images/val\\garb01_150.jpg": {"shape": [1280, 720], "labels": [[0.0, 0.3570312559604645, 0.3715277910232544, 0.171875, 0.6625000238418579], [3.0, 0.2828125059604645, 0.1770833283662796, 0.0546875, 0.2597222328186035], [3.0, 0.4828124940395355, 0.5874999761581421, 0.10312499850988388, 0.16388888657093048], [4.0, 0.5179687738418579, 0.4659722149372101, 0.12187500298023224, 0.17638888955116272], [7.0, 0.43476563692092896, 0.6215277910232544, 0.03515625, 0.17083333432674408], [7.0, 0.4375, 0.4965277910232544, 0.046875, 0.06527777761220932], [3.0, 0.431640625, 0.4305555522441864, 0.05546874925494194, 0.07777778059244156], [7.0, 0.43828123807907104, 0.3993055522441864, 0.04062499850988388, 0.04027777910232544]]}}, "image_hash": "3c5f665e49f188f90f996e6af6c415c3", "label_hash": "514ebd89a2c94eb602e4d74973bf577a"}
\ No newline at end of file