use pre-commit to remove blanks.

.pre-commit-config.yaml

@@ -1,7 +1,10 @@
+# See https://pre-commit.com for more information
+# See https://pre-commit.com/hooks.html for more hooks
 repos:
-  - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.3.0
+-   repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v3.2.0
     hooks:
-      - id: check-yaml
-      - id: end-of-file-fixer
-      - id: trailing-whitespace
+    -   id: trailing-whitespace
+    -   id: end-of-file-fixer
+    -   id: check-yaml
+    -   id: check-added-large-files

README.md

@@ -31,7 +31,7 @@ Implementation of paper:
 - [2023.01.06] Release P6 models and enhance the performance of P5 models. ⭐️ [Benchmark](#Benchmark)
 - [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. 
+- [2022.09.05] 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
@@ -49,7 +49,7 @@ Implementation of paper:
 <details>
 <summary>Table Notes</summary>
 
-- All checkpoints are trained with self-distillation except for YOLOv6-N6/S6 models trained to 300 epochs without distillation.  
+- 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.
@@ -96,7 +96,7 @@ Implementation of paper:
 <details>
 <summary>Table Notes</summary>
 
-- From the perspective of model size and input image ratio, we have built a series of models on the mobile terminal to facilitate flexible applications in different scenarios. 
+- From the perspective of model size and input image ratio, we have built a series of models on the mobile terminal to facilitate flexible applications in different scenarios.
 - All checkpoints are trained with 400 epochs without distillation.
 - Results of the mAP and speed are evaluated on [COCO val2017](https://cocodataset.org/#download) dataset, and the input resolution is the Size in the table.
 - Speed is tested on MNN 2.3.0 AArch64 with 2 threads by arm82 acceleration. The inference warm-up is performed 10 times, and the cycle is performed 100 times.
@@ -180,7 +180,7 @@ 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. 
+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
 ```
@@ -246,7 +246,7 @@ python tools/infer.py --weights yolov6s6.pt --img 1280 1280 --webcam --webcam-ad
 <details open>
 <summary> Tutorials</summary>
 
-*  [User Guide(zh_CN)](https://yolov6-docs.readthedocs.io/zh_CN/latest/) 
+*  [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)
@@ -266,7 +266,7 @@ python tools/infer.py --weights yolov6s6.pt --img 1280 1280 --webcam --webcam-ad
 
  * [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)
 
- * [Interactive demo](https://yolov6.dagshubusercontent.com/) on [DagsHub](https://dagshub.com) with [Streamlit](https://github.com/streamlit/streamlit) 
+ * [Interactive demo](https://yolov6.dagshubusercontent.com/) on [DagsHub](https://dagshub.com) with [Streamlit](https://github.com/streamlit/streamlit)
 
  * 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>
 

README_cn.md

@@ -6,7 +6,7 @@
 
 ## YOLOv6
 
-官方论文: 
+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)
 
@@ -22,7 +22,7 @@
 - [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)
 - [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  
+- [2022.09.05] 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
@@ -41,7 +41,7 @@
 <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；  
+- 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；
@@ -238,7 +238,7 @@ python tools/infer.py --weights yolov6s6.pt --img 1280 1280 --webcam --webcam-ad
 <details open>
 <summary> 教程 </summary>
 
-*  [用户手册（中文版）](https://yolov6-docs.readthedocs.io/zh_CN/latest/) 
+*  [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)
@@ -263,4 +263,4 @@ python tools/infer.py --weights yolov6s6.pt --img 1280 1280 --webcam --webcam-ad
 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>
+</p>

configs/base/README.md

@@ -23,4 +23,4 @@ Advantage:
 | [**YOLOv6-L-base**](https://github.com/meituan/YOLOv6/releases/download/0.3.0/yolov6l_base.pt) | 640 | 51.1<sup>distill  | 116   | 157  | 196  | 288  | 59.61 | 150.89 |
 
 - Speed is tested with TensorRT 8.2.4.2 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).
+- 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).

configs/base/yolov6l_base.py

@@ -2,7 +2,7 @@
 model = dict(
     type='YOLOv6l_base',
     pretrained=None,
-    depth_multiple=1.0,  
+    depth_multiple=1.0,
     width_multiple=1.0,
     backbone=dict(
         type='CSPBepBackbone',
@@ -23,8 +23,8 @@
         num_layers=3,
         begin_indices=24,
         anchors=3,
-        anchors_init=[[10,13, 19,19, 33,23], 
-                      [30,61, 59,59, 59,119], 
+        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],
@@ -48,12 +48,12 @@
     weight_decay=0.0005,
     warmup_epochs=3.0,
     warmup_momentum=0.8,
-    warmup_bias_lr=0.1       
+    warmup_bias_lr=0.1
 )
- 
+
 data_aug = dict(
-    hsv_h=0.015,  
-    hsv_s=0.7, 
+    hsv_h=0.015,
+    hsv_s=0.7,
     hsv_v=0.4,
     degrees=0.0,
     translate=0.1,
@@ -64,4 +64,4 @@
     mosaic=1.0,
     mixup=0.1,
 )
-training_mode = "conv_relu" 
+training_mode = "conv_relu"

configs/base/yolov6l_base_finetune.py

@@ -60,4 +60,4 @@
     mosaic=1.0,
     mixup=0.243,
 )
-training_mode = "conv_relu" 
+training_mode = "conv_relu"

configs/base/yolov6m_base.py

@@ -2,7 +2,7 @@
 model = dict(
     type='YOLOv6m_base',
     pretrained=None,
-    depth_multiple=0.80,  
+    depth_multiple=0.80,
     width_multiple=0.75,
     backbone=dict(
         type='CSPBepBackbone',
@@ -23,8 +23,8 @@
         num_layers=3,
         begin_indices=24,
         anchors=3,
-        anchors_init=[[10,13, 19,19, 33,23], 
-                      [30,61, 59,59, 59,119], 
+        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],
@@ -48,12 +48,12 @@
     weight_decay=0.0005,
     warmup_epochs=3.0,
     warmup_momentum=0.8,
-    warmup_bias_lr=0.1       
+    warmup_bias_lr=0.1
 )
- 
+
 data_aug = dict(
-    hsv_h=0.015,  
-    hsv_s=0.7, 
+    hsv_h=0.015,
+    hsv_s=0.7,
     hsv_v=0.4,
     degrees=0.0,
     translate=0.1,
@@ -64,4 +64,4 @@
     mosaic=1.0,
     mixup=0.1,
 )
-training_mode = "conv_relu" 
+training_mode = "conv_relu"

configs/base/yolov6m_base_finetune.py

@@ -2,7 +2,7 @@
 model = dict(
     type='YOLOv6m_base',
     pretrained=None,
-    depth_multiple=0.80,  
+    depth_multiple=0.80,
     width_multiple=0.75,
     backbone=dict(
         type='CSPBepBackbone',
@@ -23,8 +23,8 @@
         num_layers=3,
         begin_indices=24,
         anchors=3,
-        anchors_init=[[10,13, 19,19, 33,23], 
-                      [30,61, 59,59, 59,119], 
+        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],

configs/base/yolov6n_base.py

@@ -21,15 +21,15 @@
         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], 
+        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, # set to True if you want to further train with distillation 
+        use_dfl=True, # set to True if you want to further train with distillation
         reg_max=16, # set to 16 if you want to further train with distillation
         distill_weight={
             'class': 1.0,
@@ -63,4 +63,4 @@
     mosaic=1.0,
     mixup=0.0,
 )
-training_mode = "conv_relu"
+training_mode = "conv_relu"

configs/base/yolov6n_base_finetune.py

@@ -21,15 +21,15 @@
         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], 
+        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 
+        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,

configs/base/yolov6s_base.py

@@ -24,14 +24,14 @@
         num_layers=3,
         begin_indices=24,
         anchors=3,
-        anchors_init=[[10,13, 19,19, 33,23], 
-                      [30,61, 59,59, 59,119], 
+        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, # set to True if you want to further train with distillation 
+        use_dfl=True, # set to True if you want to further train with distillation
         reg_max=16, # set to 16 if you want to further train with distillation
         distill_weight={
             'class': 1.0,

configs/base/yolov6s_base_finetune.py

@@ -24,14 +24,14 @@
         num_layers=3,
         begin_indices=24,
         anchors=3,
-        anchors_init=[[10,13, 19,19, 33,23], 
-                      [30,61, 59,59, 59,119], 
+        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 
+        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,
@@ -65,4 +65,4 @@
     mosaic=1.0,
     mixup=0.243,
 )
-training_mode = "conv_relu" 
+training_mode = "conv_relu"

configs/mbla/README.md

@@ -25,4 +25,4 @@ Advantage:
 | [**YOLOv6-X-base**](https://github.com/meituan/YOLOv6/releases/download/0.4.0/yolov6x_base.pt) | 640      | 53.5<sup>distill         | 78                                    | 94                                     | 78.8                 | 199.0               |
 
 - Speed is tested with TensorRT 8.4.2.4 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).
+- 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).

configs/mbla/yolov6l_mbla.py

@@ -2,7 +2,7 @@
 model = dict(
     type='YOLOv6l_mbla',
     pretrained=None,
-    depth_multiple=0.5,  
+    depth_multiple=0.5,
     width_multiple=1.0,
     backbone=dict(
         type='CSPBepBackbone',
@@ -25,8 +25,8 @@
         num_layers=3,
         begin_indices=24,
         anchors=3,
-        anchors_init=[[10,13, 19,19, 33,23], 
-                      [30,61, 59,59, 59,119], 
+        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],
@@ -50,12 +50,12 @@
     weight_decay=0.0005,
     warmup_epochs=3.0,
     warmup_momentum=0.8,
-    warmup_bias_lr=0.1       
+    warmup_bias_lr=0.1
 )
- 
+
 data_aug = dict(
-    hsv_h=0.015,  
-    hsv_s=0.7, 
+    hsv_h=0.015,
+    hsv_s=0.7,
     hsv_v=0.4,
     degrees=0.0,
     translate=0.1,
@@ -67,4 +67,4 @@
     mixup=0.1,
 )
 
-training_mode = "conv_silu"
+training_mode = "conv_silu"

configs/mbla/yolov6l_mbla_finetune.py

@@ -2,7 +2,7 @@
 model = dict(
     type='YOLOv6l_mbla',
     pretrained=None,
-    depth_multiple=0.5,  
+    depth_multiple=0.5,
     width_multiple=1.0,
     backbone=dict(
         type='CSPBepBackbone',
@@ -25,8 +25,8 @@
         num_layers=3,
         begin_indices=24,
         anchors=3,
-        anchors_init=[[10,13, 19,19, 33,23], 
-                      [30,61, 59,59, 59,119], 
+        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],
@@ -67,4 +67,4 @@
     mixup=0.243,
 )
 
-training_mode = "conv_silu"
+training_mode = "conv_silu"