👷 [Add] more pre-commit, yaml-check & nbsripout

.gitignore

@@ -145,4 +145,4 @@ runs
 node_modules/
 
 # Not ignore image for demo
-!demo/images/inference/*
+!demo/images/inference/*

.pre-commit-config.yaml

@@ -6,9 +6,21 @@ repos:
         language_version: python3  # Specify the Python version
         exclude: '.*\.yaml$'  # Regex pattern to exclude all YAML files
         args: ["--line-length", "120"]  # Set max line length to 100 characters
-        
+
   - repo: https://github.com/pre-commit/mirrors-isort
     rev: v5.10.1  # Use the appropriate version or "stable" for the latest stable release
     hooks:
       - id: isort
         args: ["--profile", "black"]
+
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v3.4.0
+    hooks:
+    - id: trailing-whitespace
+    - id: end-of-file-fixer
+    - id: check-yaml
+
+  - repo: https://github.com/kynan/nbstripout
+    rev: 0.5.0
+    hooks:
+    - id: nbstripout

README.md

@@ -3,7 +3,7 @@
 ![WIP](https://img.shields.io/badge/status-WIP-orange)
 > [!IMPORTANT]
 > This project is currently a Work In Progress and may undergo significant changes. It is not recommended for use in production environments until further notice. Please check back regularly for updates.
-> 
+>
 > Use of this code is at your own risk and discretion. It is advisable to consult with the project owner before deploying or integrating into any critical systems.
 
 Welcome to the official implementation of YOLOv7 and YOLOv9. This repository will contains the complete codebase, pre-trained models, and detailed instructions for training and deploying YOLOv9.
@@ -80,11 +80,11 @@ Contributions to the YOLOv9 project are welcome! See [CONTRIBUTING](docs/CONTRIB
 ## Citations
 ```
 @misc{wang2024yolov9,
-      title={YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information}, 
+      title={YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information},
       author={Chien-Yao Wang and I-Hau Yeh and Hong-Yuan Mark Liao},
       year={2024},
       eprint={2402.13616},
       archivePrefix={arXiv},
       primaryClass={cs.CV}
 }
-```
+```

docs/CONTRIBUTING.md

@@ -40,5 +40,3 @@ Once you submit a PR, maintainers will review your work, suggest changes if nece
 Your contributions are greatly appreciated and vital to the project's success!
 
 Please feel free to contact [[email protected]](mailto:[email protected])!
-
-

docs/HOWTO.md

@@ -7,7 +7,7 @@ To facilitate easy customization of the YOLO model, we've structured the codebas
 You can change the model architecture simply by modifying the YAML configuration file. Here's how:
 
 1. **Modify Architecture in Config:**
-   
+
    Navigate to your model's configuration file (typically formate like `yolo/config/model/v9-c.yaml`).
    - Adjust the architecture settings under the `architecture` section. Ensure that every module you reference exists in `module.py`, or refer to the next section on how to add new modules.
 
@@ -40,7 +40,7 @@ To add or modify a block in the model:
 1. **Create a New Module:**
 
    Define a new class in `module.py` that inherits from `nn.Module`.
-   
+
    The constructor should accept `in_channels` as a parameter. Make sure to calculate `out_channels` based on your model's requirements or configure it through the YAML file using `args`.
 
     ```python
@@ -49,7 +49,7 @@ To add or modify a block in the model:
             super().__init__()
             self.module = # conv, bool, ...
         def forward(self, x):
-            return self.module(x) 
+            return self.module(x)
     ```
 
 2. **Reference in Config:**
@@ -145,4 +145,4 @@ Custom transformations should be designed to accept an image and its bounding bo
     - **loss**
         - `class` BoxLoss: a Custom Loss for bounding box
         - `class` YOLOLoss: a implementation of yolov9 loss
-        - `class` DualLoss: a implementation of yolov9 loss with auxiliary detection head
+        - `class` DualLoss: a implementation of yolov9 loss with auxiliary detection head

pyproject.toml

@@ -31,4 +31,4 @@ requires = [
 ]
 
 [project.scripts]
-yolo = "yolo.lazy:main"
+yolo = "yolo.lazy:main"

requirements.txt

@@ -12,4 +12,4 @@ rich
 torch
 torchvision
 tqdm
-wandb
+wandb

yolo/config/config.yaml

@@ -10,4 +10,3 @@ defaults:
   - dataset: coco
   - model: v9-c
   - general
- 

yolo/config/dataset/coco.yaml

@@ -8,7 +8,7 @@ auto_download:
     train2017:
       file_name: train2017
       file_num: 118287
-    val2017: 
+    val2017:
       file_name: val2017
       file_num: 5000
     test2017:
@@ -17,4 +17,4 @@ auto_download:
   annotations:
     base_url: http://images.cocodataset.org/annotations/
     annotations:
-      file_name: annotations_trainval2017
+      file_name: annotations_trainval2017

yolo/config/dataset/dev.yaml

@@ -2,4 +2,4 @@ path: data/dev
 train: train
 validation: test
 
-auto_download: 
+auto_download:

yolo/config/general.yaml

@@ -12,4 +12,4 @@ lucky_number: 10
 use_wandb: False
 use_TensorBoard: False
 
-weight: weights/v9-c.pt
+weight: weights/v9-c.pt

yolo/config/model/v7-base.yaml

@@ -4,243 +4,243 @@ anchor:
 
 model:
   backbone:
-  - Conv: 
+  - Conv:
       args: {out_channels: 32, kernel_size: 3}
-  - Conv: 
+  - Conv:
       args: {out_channels: 64, kernel_size: 3, stride: 2}
-  - Conv: 
+  - Conv:
       args: {out_channels: 64, kernel_size: 3}
-  - Conv: 
+  - Conv:
       args: {out_channels: 128, kernel_size: 3, stride: 2}
-  - Conv: 
+  - Conv:
       args: {out_channels: 64, kernel_size: 1}
-  - Conv: 
+  - Conv:
       args: {out_channels: 64, kernel_size: 1}
       source: -2
-  - Conv: 
+  - Conv:
       args: {out_channels: 64, kernel_size: 3}
-  - Conv: 
+  - Conv:
       args: {out_channels: 64, kernel_size: 3}
-  - Conv: 
+  - Conv:
       args: {out_channels: 64, kernel_size: 3}
-  - Conv: 
+  - Conv:
       args: {out_channels: 64, kernel_size: 3}
-  - Concat: 
+  - Concat:
       source: [-1, -3, -5, -6]
-  - Conv: 
+  - Conv:
       args: {out_channels: 256, kernel_size: 1}
-  - Pool: 
+  - Pool:
       args: {padding: 0}
-  - Conv: 
+  - Conv:
       args: {out_channels: 128, kernel_size: 1}
-  - Conv: 
+  - Conv:
       args: {out_channels: 128, kernel_size: 1}
       source: -3
-  - Conv: 
+  - Conv:
       args: {out_channels: 128, kernel_size: 3, stride: 2}
-  - Concat: 
+  - Concat:
       source: [-1, -3]
-  - Conv: 
+  - Conv:
       args: {out_channels: 128, kernel_size: 1}
-  - Conv: 
+  - Conv:
       args: {out_channels: 128, kernel_size: 1}
       source: -2
-  - Conv: 
+  - Conv:
       args: {out_channels: 128, kernel_size: 3}
-  - Conv: 
+  - Conv:
       args: {out_channels: 128, kernel_size: 3}
-  - Conv: 
+  - Conv:
       args: {out_channels: 128, kernel_size: 3}
-  - Conv: 
+  - Conv:
       args: {out_channels: 128, kernel_size: 3}
-  - Concat: 
+  - Concat:
       source: [-1, -3, -5, -6]
       tags: 8x
-  - Conv: 
+  - Conv:
       args: {out_channels: 512, kernel_size: 1}
-  - Pool: 
+  - Pool:
       args: {padding: 0}
-  - Conv: 
+  - Conv:
       args: {out_channels: 256, kernel_size: 1}
-  - Conv: 
+  - Conv:
       args: {out_channels: 256, kernel_size: 1}
       source: -3
-  - Conv: 
+  - Conv:
       args: {out_channels: 256, kernel_size: 3, stride: 2}
-  - Concat: 
+  - Concat:
       source: [-1, -3]
-  - Conv: 
+  - Conv:
       args: {out_channels: 256, kernel_size: 1}
-  - Conv: 
+  - Conv:
       args: {out_channels: 256, kernel_size: 1}
       source: -2
-  - Conv: 
+  - Conv:
       args: {out_channels: 256, kernel_size: 3}
-  - Conv: 
+  - Conv:
       args: {out_channels: 256, kernel_size: 3}
-  - Conv: 
+  - Conv:
       args: {out_channels: 256, kernel_size: 3}
-  - Conv: 
+  - Conv:
       args: {out_channels: 256, kernel_size: 3}
-  - Concat: 
+  - Concat:
       source: [-1, -3, -5, -6]
-  - Conv: 
+  - Conv:
       args: {out_channels: 1024, kernel_size: 1}
       tags: 16x
-  - Pool: 
+  - Pool:
       args: {padding: 0}
-  - Conv: 
+  - Conv:
       args: {out_channels: 512, kernel_size: 1}
-  - Conv: 
+  - Conv:
       args: {out_channels: 512, kernel_size: 1}
       source: -3
-  - Conv: 
+  - Conv:
       args: {out_channels: 512, kernel_size: 3, stride: 2}
-  - Concat: 
+  - Concat:
       source: [-1, -3]
-  - Conv: 
+  - Conv:
       args: {out_channels: 256, kernel_size: 1}
-  - Conv: 
+  - Conv:
       args: {out_channels: 256, kernel_size: 1}
       source: -2
-  - Conv: 
+  - Conv:
       args: {out_channels: 256, kernel_size: 3}
-  - Conv: 
+  - Conv:
       args: {out_channels: 256, kernel_size: 3}
-  - Conv: 
+  - Conv:
       args: {out_channels: 256, kernel_size: 3}
-  - Conv: 
+  - Conv:
       args: {out_channels: 256, kernel_size: 3}
-  - Concat: 
+  - Concat:
       source: [-1, -3, -5, -6]
-  - Conv: 
+  - Conv:
       args: {out_channels: 1024, kernel_size: 1}
       tags: 32x
   head:
-  - SPPCSPConv: 
+  - SPPCSPConv:
       args: {out_channels: 512}
-  - Conv: 
+  - Conv:
       args: {out_channels: 256, kernel_size: 1}
-  - UpSample: 
+  - UpSample:
       args: {scale_factor: 2}
-  - Conv: 
+  - Conv:
       args: {out_channels: 256, kernel_size: 1}
       source: 16x
-  - Concat: 
+  - Concat:
       source: [-1, -2]
-  - Conv: 
+  - Conv:
       args: {out_channels: 256, kernel_size: 1}
-  - Conv: 
+  - Conv:
       args: {out_channels: 256, kernel_size: 1}
       source: -2
-  - Conv: 
+  - Conv:
       args: {out_channels: 128, kernel_size: 3}
-  - Conv: 
+  - Conv:
       args: {out_channels: 128, kernel_size: 3}
-  - Conv: 
+  - Conv:
       args: {out_channels: 128, kernel_size: 3}
-  - Conv: 
+  - Conv:
       args: {out_channels: 128, kernel_size: 3}
-  - Concat: 
+  - Concat:
       source: [-1, -2, -3, -4, -5, -6]
-  - Conv: 
+  - Conv:
       args: {out_channels: 256, kernel_size: 1}
-  - Conv: 
+  - Conv:
       args: {out_channels: 128, kernel_size: 1}
-  - UpSample: 
+  - UpSample:
       args: {scale_factor: 2}
-  - Conv: 
+  - Conv:
       args: {out_channels: 128, kernel_size: 1}
       source: 8x
-  - Concat: 
+  - Concat:
       source: [-1, -2]
-  - Conv: 
+  - Conv:
       args: {out_channels: 128, kernel_size: 1}
-  - Conv: 
+  - Conv:
       args: {out_channels: 128, kernel_size: 1}
       source: -2
-  - Conv: 
+  - Conv:
       args: {out_channels: 64, kernel_size: 3}
-  - Conv: 
+  - Conv:
       args: {out_channels: 64, kernel_size: 3}
-  - Conv: 
+  - Conv:
       args: {out_channels: 64, kernel_size: 3}
-  - Conv: 
+  - Conv:
       args: {out_channels: 64, kernel_size: 3}
-  - Concat: 
+  - Concat:
       source: [-1, -2, -3, -4, -5, -6]
-  - Conv: 
+  - Conv:
       args: {out_channels: 128, kernel_size: 1}
-  - Pool: 
+  - Pool:
       args: {padding: 0}
-  - Conv: 
+  - Conv:
       args: {out_channels: 128, kernel_size: 1}
-  - Conv: 
+  - Conv:
       args: {out_channels: 128, kernel_size: 1}
       source: -3
-  - Conv: 
+  - Conv:
       args: {out_channels: 128, kernel_size: 3, stride: 2}
-  - Concat: 
+  - Concat:
       source: [-1, -3, 63]
-  - Conv: 
+  - Conv:
       args: {out_channels: 256, kernel_size: 1}
-  - Conv: 
+  - Conv:
       args: {out_channels: 256, kernel_size: 1}
       source: -2
-  - Conv: 
+  - Conv:
       args: {out_channels: 128, kernel_size: 3}
-  - Conv: 
+  - Conv:
       args: {out_channels: 128, kernel_size: 3}
-  - Conv: 
+  - Conv:
       args: {out_channels: 128, kernel_size: 3}
-  - Conv: 
+  - Conv:
       args: {out_channels: 128, kernel_size: 3}
-  - Concat: 
+  - Concat:
       source: [-1, -2, -3, -4, -5, -6]
-  - Conv: 
+  - Conv:
       args: {out_channels: 256, kernel_size: 1}
-  - Pool: 
+  - Pool:
       args: {padding: 0}
-  - Conv: 
+  - Conv:
       args: {out_channels: 256, kernel_size: 1}
-  - Conv: 
+  - Conv:
       args: {out_channels: 256, kernel_size: 1}
       source: -3
-  - Conv: 
+  - Conv:
       args: {out_channels: 256, kernel_size: 3, stride: 2}
-  - Concat: 
+  - Concat:
       source: [-1, -3, 51]
-  - Conv: 
+  - Conv:
       args: {out_channels: 512, kernel_size: 1}
-  - Conv: 
+  - Conv:
       args: {out_channels: 512, kernel_size: 1}
       source: -2
-  - Conv: 
+  - Conv:
       args: {out_channels: 256, kernel_size: 3}
-  - Conv: 
+  - Conv:
       args: {out_channels: 256, kernel_size: 3}
-  - Conv: 
+  - Conv:
       args: {out_channels: 256, kernel_size: 3}
-  - Conv: 
+  - Conv:
       args: {out_channels: 256, kernel_size: 3}
-  - Concat: 
+  - Concat:
       source: [-1, -2, -3, -4, -5, -6]
-  - Conv: 
+  - Conv:
       args: {out_channels: 512, kernel_size: 1}
-  - RepConv: 
+  - RepConv:
       args: {out_channels: 256}
       source: 75
-  - RepConv: 
+  - RepConv:
       args: {out_channels: 512}
       source: 88
-  - RepConv: 
+  - RepConv:
       args: {out_channels: 1024}
       source: 101
-  - IDetect: 
+  - IDetect:
       args:
         anchors:
             - [12,16, 19,36, 40,28]  # P3/8
             - [36,75, 76,55, 72,146]  # P4/16
             - [142,110, 192,243, 459,401]  # P5/32
       source: [102, 103, 104]
-      output: True
+      output: True

yolo/config/model/v9-c.yaml

@@ -13,7 +13,7 @@ model:
         args: {out_channels: 128, kernel_size: 3, stride: 2}
     - RepNCSPELAN:
         args: {out_channels: 256, part_channels: 128}
-    
+
     - ADown:
         args: {out_channels: 256}
     - RepNCSPELAN:
@@ -25,13 +25,13 @@ model:
     - RepNCSPELAN:
         args: {out_channels: 512, part_channels: 512}
         tags: B4
-    
+
     - ADown:
         args: {out_channels: 512}
     - RepNCSPELAN:
         args: {out_channels: 512, part_channels: 512}
         tags: B5
-  
+
   neck:
     - SPPELAN:
         args: {out_channels: 512}
@@ -49,12 +49,12 @@ model:
         args: {scale_factor: 2, mode: nearest}
     - Concat:
         source: [-1, B3]
-    
+
   head:
     - RepNCSPELAN:
         args: {out_channels: 256, part_channels: 256}
         tags: P3
-    
+
     - ADown:
         args: {out_channels: 256}
     - Concat:
@@ -70,7 +70,7 @@ model:
     - RepNCSPELAN:
         args: {out_channels: 512, part_channels: 512}
         tags: P5
-  
+
   auxiliary:
     - CBLinear:
         source: B3
@@ -84,7 +84,7 @@ model:
         source: B5
         args: {out_channels: [256, 512, 512]}
         tags: R5
-    
+
     - Conv:
         args: {out_channels: 64, kernel_size: 3, stride: 2}
         source: 0
@@ -122,4 +122,4 @@ model:
 
     - MultiheadDetection:
         source: [A3, A4, A5, P3, P4, P5]
-        output: True
+        output: True

yolo/config/task/inference.yaml

@@ -7,4 +7,4 @@ data:
   data_augment: {}
 nms:
   min_confidence: 0.5
-  min_iou: 0.5
+  min_iou: 0.5

yolo/config/task/train.yaml

@@ -6,7 +6,7 @@ defaults:
 epoch: 500
 
 data:
-  batch_size: 16 
+  batch_size: 16
   image_size: ${image_size}
   cpu_num: ${cpu_num}
   shuffle: True
@@ -26,7 +26,7 @@ optimizer:
 loss:
   objective:
     BCELoss: 0.5
-    BoxLoss: 7.5  
+    BoxLoss: 7.5
     DFLoss: 1.5
   aux:
     0.25

yolo/config/task/validation.yaml

@@ -9,4 +9,4 @@ data:
   data_augment: {}
 nms:
   min_confidence: 0.001
-  min_iou: 0.7
+  min_iou: 0.7

yolo/utils/logging_utils.py

@@ -1,9 +1,9 @@
 """
-Module for initializing logging tools used in machine learning and data processing. 
-Supports integration with Weights & Biases (wandb), Loguru, TensorBoard, and other 
+Module for initializing logging tools used in machine learning and data processing.
+Supports integration with Weights & Biases (wandb), Loguru, TensorBoard, and other
 logging frameworks as needed.
 
-This setup ensures consistent logging across various platforms, facilitating 
+This setup ensures consistent logging across various platforms, facilitating
 effective monitoring and debugging.
 
 Example: