From 5225a0932e01c56864066a7cd0ff9b6e403a597f Mon Sep 17 00:00:00 2001 From: Chilicyy Date: Fri, 15 Sep 2023 15:35:02 +0800 Subject: [PATCH] update readme --- README.md | 35 ++++++++++++++++------------------- README_cn.md | 38 ++++++++++++++++---------------------- 2 files changed, 32 insertions(+), 41 deletions(-) diff --git a/README.md b/README.md index b2f85d6f..7d0d1848 100644 --- a/README.md +++ b/README.md @@ -9,26 +9,21 @@ English | [简体中文](README_cn.md) Implementation of Instance Segmentation based on [YOLOv6 v4.0 code](https://github.com/meituan/YOLOv6/tree/main). -New Feature -- Designe two types of segment heads referring to YOLACT and SOLO +

+ +
+

## Performance on MSCOCO -| Model | Size | mAPbox
50-95 | mAPmask
50-95 | SpeedT4
trt fp16 b1
(fps) | -| :----------------------------------------------------------- | ---- | :-------------------- | ---------------------- | --------------------------------------- | -| [**YOLOv6-N-seg**](https://github.com/meituan/YOLOv6/releases/download/0.4.1/yolov6n_seg.pt) | 640 | 35.3 | 31.2 | 645 | -| [**YOLOv6-S-seg**](https://github.com/meituan/YOLOv6/releases/download/0.4.1/yolov6s_seg.pt) | 640 | 44.0 | 38.0 | 292 | -| [**YOLOv6-M-seg**](https://github.com/meituan/YOLOv6/releases/download/0.4.1/yolov6m_seg.pt) | 640 | 48.2 | 41.3 | 148 | -| [**YOLOv6-L-seg**](https://github.com/meituan/YOLOv6/releases/download/0.4.1/yolov6l_seg.pt) | 640 | 51.1 | 43.7 | 93 | -| [**YOLOv6-X-seg**](https://github.com/meituan/YOLOv6/releases/download/0.4.1/yolov6x_seg.pt) | 640 | 52.2 | 44.8 | 47 | -| | | | | | -| [**YOLOv6-N-solo**](https://github.com/meituan/YOLOv6/releases/download/0.4.1/yolov6n_solo.pt) | 640 | 35.7 | 31.3 | 506 | -| [**YOLOv6-S-solo**](https://github.com/meituan/YOLOv6/releases/download/0.4.1/yolov6s_solo.pt) | 640 | 44.2 | 39.0 | 243 | -| [**YOLOv6-M-solo**](https://github.com/meituan/YOLOv6/releases/download/0.4.1/yolov6m_solo.pt) | 640 | 48.3 | 42.2 | 120 | -| [**YOLOv6-L-solo**](https://github.com/meituan/YOLOv6/releases/download/0.4.1/yolov6l_solo.pt) | 640 | 50.9 | 44.4 | 75 | -| [**YOLOv6-X-solo**](https://github.com/meituan/YOLOv6/releases/download/0.4.1/yolov6x_solo.pt) | 640 | 52.2 | 45.0 | 41 | +| Model | Size | mAPbox
50-95 | mAPmask
50-95 | SpeedT4
trt fp16 b1
(fps) | Params
(M) | FLOPs
(G) | +| :----------------------------------------------------------- | ---- | :-------------------- | ---------------------- | --------------------------------------- | -------------------- | ------------------- | +| [**YOLOv6-N**](https://github.com/meituan/YOLOv6/releases/download/0.4.1/yolov6n_seg.pt) | 640 | 35.3 | 31.2 | 645 | 4.9 | 7.0 | +| [**YOLOv6-S**](https://github.com/meituan/YOLOv6/releases/download/0.4.1/yolov6s_seg.pt) | 640 | 44.0 | 38.0 | 292 | 19.6 | 27.7 | +| [**YOLOv6-M**](https://github.com/meituan/YOLOv6/releases/download/0.4.1/yolov6m_seg.pt) | 640 | 48.2 | 41.3 | 148 | 37.1 | 54.3 | +| [**YOLOv6-L**](https://github.com/meituan/YOLOv6/releases/download/0.4.1/yolov6l_seg.pt) | 640 | 51.1 | 43.7 | 93 | 63.6 | 95.5 | +| [**YOLOv6-X**](https://github.com/meituan/YOLOv6/releases/download/0.4.1/yolov6x_seg.pt) | 640 | 52.2 | 44.8 | 47 | 119.1 | 175.5 | #### Table Notes -- YOLOv6-x-seg models apply YOLACT segment head, and YOLOv6-x-solo models apply SOLO segment head. - All checkpoints are trained from scratch on COCO for 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. - Speed is tested with TensorRT 8.5 on T4 without post-processing. @@ -45,7 +40,7 @@ New Feature ```shell git clone https://github.com/meituan/YOLOv6 cd YOLOv6 -git checkout yolov6-segss +git checkout yolov6-seg pip install -r requirements.txt ``` @@ -66,7 +61,7 @@ python -m torch.distributed.launch --nproc_per_node 8 tools/train.py --batch 64 ``` - fuse_ab: Not supported in current version - 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) ) +- 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/0.4.1/coco2017labels-segments.zip) ) - make sure your dataset structure as follows: ``` ├── coco @@ -83,7 +78,6 @@ python -m torch.distributed.launch --nproc_per_node 8 tools/train.py --batch 64 │ ├── README.txt ``` -YOLOv6 supports different input resolution modes. For details, see [How to Set the Input Size](./docs/About_training_size.md). @@ -96,6 +90,7 @@ Reproduce mAP on COCO val2017 dataset with 640×640 resolution ```shell python tools/eval.py --data data/coco.yaml --batch 32 --weights yolov6s.pt --task val ``` + @@ -114,6 +109,8 @@ If you want to inference on local camera or web camera, you can run: python tools/infer.py --weights yolov6s.pt --webcam --webcam-addr 0 ``` `webcam-addr` can be local camera number id or rtsp address. +Maybe you want to eval a solo-head model, remember to add the *--issolo* parameter. +
diff --git a/README_cn.md b/README_cn.md index b3a7e9c2..629d214a 100644 --- a/README_cn.md +++ b/README_cn.md @@ -8,26 +8,21 @@ 基于 [YOLOv6 v4.0 分支](https://github.com/meituan/YOLOv6/tree/main) 代码实现实例分割任务。 -新特性 -- 参考 YOLACT 和 SOLO 设计了两种不同的分割预测头 +

+ +
+

## MSCOCO 模型指标 -| Model | Size | mAPbox
50-95 | mAPmask
50-95 | SpeedT4
trt fp16 b1
(fps) | -| :----------------------------------------------------------- | ---- | :-------------------- | ---------------------- | --------------------------------------- | -| [**YOLOv6-N-seg**](https://github.com/meituan/YOLOv6/releases/download/0.4.1/yolov6n_seg.pt) | 640 | 35.3 | 31.2 | 645 | -| [**YOLOv6-S-seg**](https://github.com/meituan/YOLOv6/releases/download/0.4.1/yolov6s_seg.pt) | 640 | 44.0 | 38.0 | 292 | -| [**YOLOv6-M-seg**](https://github.com/meituan/YOLOv6/releases/download/0.4.1/yolov6m_seg.pt) | 640 | 48.2 | 41.3 | 148 | -| [**YOLOv6-L-seg**](https://github.com/meituan/YOLOv6/releases/download/0.4.1/yolov6l_seg.pt) | 640 | 51.1 | 43.7 | 93 | -| [**YOLOv6-X-seg**](https://github.com/meituan/YOLOv6/releases/download/0.4.1/yolov6x_seg.pt) | 640 | 52.2 | 44.8 | 47 | -| | | | | | -| [**YOLOv6-N-solo**](https://github.com/meituan/YOLOv6/releases/download/0.4.1/yolov6n_solo.pt) | 640 | 35.7 | 31.3 | 506 | -| [**YOLOv6-S-solo**](https://github.com/meituan/YOLOv6/releases/download/0.4.1/yolov6s_solo.pt) | 640 | 44.2 | 39.0 | 243 | -| [**YOLOv6-M-solo**](https://github.com/meituan/YOLOv6/releases/download/0.4.1/yolov6m_solo.pt) | 640 | 48.3 | 42.2 | 120 | -| [**YOLOv6-L-solo**](https://github.com/meituan/YOLOv6/releases/download/0.4.1/yolov6l_solo.pt) | 640 | 50.9 | 44.4 | 75 | -| [**YOLOv6-X-solo**](https://github.com/meituan/YOLOv6/releases/download/0.4.1/yolov6x_solo.pt) | 640 | 52.2 | 45.0 | 41 | - -#### Table Notes -- YOLOv6-x-seg 模型采用 YOLACT 分割头, YOLOv6-x-solo 模型采用 SOLO 分割头. +| Model | Size | mAPbox
50-95 | mAPmask
50-95 | SpeedT4
trt fp16 b1
(fps) | Params
(M) | FLOPs
(G) | +| :----------------------------------------------------------- | ---- | :-------------------- | ---------------------- | --------------------------------------- | -------------------- | ------------------- | +| [**YOLOv6-N**](https://github.com/meituan/YOLOv6/releases/download/0.4.1/yolov6n_seg.pt) | 640 | 35.3 | 31.2 | 645 | 4.9 | 7.0 | +| [**YOLOv6-S**](https://github.com/meituan/YOLOv6/releases/download/0.4.1/yolov6s_seg.pt) | 640 | 44.0 | 38.0 | 292 | 19.6 | 27.7 | +| [**YOLOv6-M**](https://github.com/meituan/YOLOv6/releases/download/0.4.1/yolov6m_seg.pt) | 640 | 48.2 | 41.3 | 148 | 37.1 | 54.3 | +| [**YOLOv6-L**](https://github.com/meituan/YOLOv6/releases/download/0.4.1/yolov6l_seg.pt) | 640 | 51.1 | 43.7 | 93 | 63.6 | 95.5 | +| [**YOLOv6-X**](https://github.com/meituan/YOLOv6/releases/download/0.4.1/yolov6x_seg.pt) | 640 | 52.2 | 44.8 | 47 | 119.1 | 175.5 | + +#### 表格笔记 - 所有权重都经过 300 个 epoch 的训练，并且没有使用蒸馏技术. - mAP 和速度指标是在 COCO val2017 数据集上评估的，输入分辨率为640x640. - 速度是在 T4 上测试的，TensorRT 版本为 8.5，且不包括后处理部分. @@ -35,7 +30,7 @@ -## Quick Start +## 快速开启
安装 @@ -43,7 +38,7 @@ ```shell git clone https://github.com/meituan/YOLOv6 cd YOLOv6 -git checkout yolov6-segss +git checkout yolov6-seg pip install -r requirements.txt ```
@@ -64,7 +59,7 @@ python -m torch.distributed.launch --nproc_per_node 8 tools/train.py --batch 64 ``` - fuse_ab: 当前版本暂不支持 - 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)； +- 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/0.4.1/coco2017labels-segments.zip)； - 确保您的数据集按照下面这种格式来组织； ``` ├── coco @@ -81,7 +76,6 @@ python -m torch.distributed.launch --nproc_per_node 8 tools/train.py --batch 64 │ ├── README.txt ``` -YOLOv6 支持不同的输入分辨率模式，详情请参见 [如何设置输入大小](./docs/About_training_size_cn.md).