Skip to content

Commit 50dccb2

Browse files
ChilicyyChilicyy
committed
fix url
1 parent 6b83533 commit 50dccb2

File tree

2 files changed

+12
-12
lines changed

2 files changed

+12
-12
lines changed

‎README.md‎

Lines changed: 6 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -19,10 +19,10 @@ New Feature
1919
## Performance on WIDERFACE
2020
| Model | Size | Easy | Medium | Hard | 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) |
2121
| :----------------------------------------------------------- | ---- | :--- | ------ | ---- | --------------------------------------- | ---------------------------------------- | -------------------- | ------------------- |
22-
| [**YOLOv6-N**](https://github.com/meituan/YOLOv6/releases/download/0.3.0/yolov6n_face.pt) | 640 | 95.0 | 92.4 | 80.4 | 797 | 1313 | 4.63 | 11.35 |
23-
| [**YOLOv6-S**](https://github.com/meituan/YOLOv6/releases/download/0.3.0/yolov6s_face.pt) | 640 | 96.2 | 94.7 | 85.1 | 339 | 484 | 12.41 | 32.45 |
24-
| [**YOLOv6-M**](https://github.com/meituan/YOLOv6/releases/download/0.3.0/yolov6m_face.pt) | 640 | 97.0 | 95.3 | 86.3 | 188 | 240 | 24.85 | 70.59 |
25-
| [**YOLOv6-L**](https://github.com/meituan/YOLOv6/releases/download/0.3.0/yolov6l_face.pt) | 640 | 97.2 | 95.9 | 87.5 | 102 | 121 | 56.77 | 159.24 |
22+
| [**YOLOv6-N**](https://github.com/meituan/YOLOv6/releases/download/0.3.1/yolov6n_face.pt) | 640 | 95.0 | 92.4 | 80.4 | 797 | 1313 | 4.63 | 11.35 |
23+
| [**YOLOv6-S**](https://github.com/meituan/YOLOv6/releases/download/0.3.1/yolov6s_face.pt) | 640 | 96.2 | 94.7 | 85.1 | 339 | 484 | 12.41 | 32.45 |
24+
| [**YOLOv6-M**](https://github.com/meituan/YOLOv6/releases/download/0.3.1/yolov6m_face.pt) | 640 | 97.0 | 95.3 | 86.3 | 188 | 240 | 24.85 | 70.59 |
25+
| [**YOLOv6-L**](https://github.com/meituan/YOLOv6/releases/download/0.3.1/yolov6l_face.pt) | 640 | 97.2 | 95.9 | 87.5 | 102 | 121 | 56.77 | 159.24 |
2626

2727
#### Table Notes
2828

@@ -63,7 +63,7 @@ python -m torch.distributed.launch --nproc_per_node 8 tools/train.py --batch 64
6363
```
6464
- fuse_ab: Anchor Aided Training Mode
6565
- conf: select config file to specify network/optimizer/hyperparameters. We recommend to apply yolov6n/s/m/l_finetune.py when training on WIDER FACE or your custom dataset.
66-
- data: prepare dataset and specify dataset paths in data.yaml ( [WIDERFACE](http://shuoyang1213.me/WIDERFACE/), [YOLO format widerface labels](https://github.com/meituan/YOLOv6/releases/download/0.3.0/widerface_yololabels.zip) )
66+
- data: prepare dataset and specify dataset paths in data.yaml ( [WIDERFACE](http://shuoyang1213.me/WIDERFACE/), [YOLO format widerface labels](https://github.com/meituan/YOLOv6/releases/download/0.3.1/widerface_yololabels.zip) )
6767
- make sure your dataset structure as follows:
6868
```
6969
├── widerface
@@ -81,7 +81,7 @@ python -m torch.distributed.launch --nproc_per_node 8 tools/train.py --batch 64
8181
<details open>
8282
<summary>Inference</summary>
8383

84-
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.
84+
First, download a pretrained model from the YOLOv6 [release](https://github.com/meituan/YOLOv6/releases/tag/0.3.1) or use your trained model to do inference.
8585

8686
Second, run inference with `tools/infer.py`
8787

‎README_cn.md‎

Lines changed: 6 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -18,10 +18,10 @@
1818
## WIDERFACE 模型指标
1919
| Model | Size | Easy | Medium | Hard | 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) |
2020
| :----------------------------------------------------------- | ---- | :--- | ------ | ---- | --------------------------------------- | ---------------------------------------- | -------------------- | ------------------- |
21-
| [**YOLOv6-N**](https://github.com/meituan/YOLOv6/releases/download/0.3.0/yolov6n_face.pt) | 640 | 95.0 | 92.4 | 80.4 | 797 | 1313 | 4.63 | 11.35 |
22-
| [**YOLOv6-S**](https://github.com/meituan/YOLOv6/releases/download/0.3.0/yolov6s_face.pt) | 640 | 96.2 | 94.7 | 85.1 | 339 | 484 | 12.41 | 32.45 |
23-
| [**YOLOv6-M**](https://github.com/meituan/YOLOv6/releases/download/0.3.0/yolov6m_face.pt) | 640 | 97.0 | 95.3 | 86.3 | 188 | 240 | 24.85 | 70.59 |
24-
| [**YOLOv6-L**](https://github.com/meituan/YOLOv6/releases/download/0.3.0/yolov6l_face.pt) | 640 | 97.2 | 95.9 | 87.5 | 102 | 121 | 56.77 | 159.24 |
21+
| [**YOLOv6-N**](https://github.com/meituan/YOLOv6/releases/download/0.3.1/yolov6n_face.pt) | 640 | 95.0 | 92.4 | 80.4 | 797 | 1313 | 4.63 | 11.35 |
22+
| [**YOLOv6-S**](https://github.com/meituan/YOLOv6/releases/download/0.3.1/yolov6s_face.pt) | 640 | 96.2 | 94.7 | 85.1 | 339 | 484 | 12.41 | 32.45 |
23+
| [**YOLOv6-M**](https://github.com/meituan/YOLOv6/releases/download/0.3.1/yolov6m_face.pt) | 640 | 97.0 | 95.3 | 86.3 | 188 | 240 | 24.85 | 70.59 |
24+
| [**YOLOv6-L**](https://github.com/meituan/YOLOv6/releases/download/0.3.1/yolov6l_face.pt) | 640 | 97.2 | 95.9 | 87.5 | 102 | 121 | 56.77 | 159.24 |
2525

2626
#### 表格备注
2727

@@ -62,7 +62,7 @@ python -m torch.distributed.launch --nproc_per_node 8 tools/train.py --batch 64
6262
```
6363
- fuse_ab: 使用联合锚点训练模式
6464
- 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
65-
- data: 数据集配置文件，以 WIDERFACE 数据集为例，您可以在 [WIDERFACE](http://shuoyang1213.me/WIDERFACE/) 下载数据, 在这里下载[YOLO 格式标签](https://github.com/meituan/YOLOv6/releases/download/0.3.0/widerface_yololabels.zip)
65+
- data: 数据集配置文件，以 WIDERFACE 数据集为例，您可以在 [WIDERFACE](http://shuoyang1213.me/WIDERFACE/) 下载数据, 在这里下载[YOLO 格式标签](https://github.com/meituan/YOLOv6/releases/download/0.3.1/widerface_yololabels.zip)
6666
- 确保您的数据集按照下面这种格式来组织；
6767
```
6868
├── widerface
@@ -80,7 +80,7 @@ python -m torch.distributed.launch --nproc_per_node 8 tools/train.py --batch 64
8080
<details open>
8181
<summary>推理</summary>
8282

83-
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；
83+
首先，从[release 页面](https://github.com/meituan/YOLOv6/releases/tag/0.3.1) 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；
8484

8585
然后，通过 `tools/infer.py` 文件进行推理。
8686

0 commit comments

Comments
 (0)