commit 0074f28b2f370a8ed246910747b07ab12fa321b1 Author: Robofish <1683502971@qq.com> Date: Sun Apr 27 18:36:09 2025 +0800 init diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..14eabec --- /dev/null +++ b/.gitignore @@ -0,0 +1,2 @@ +/datasets +/weights \ No newline at end of file diff --git a/README.MD b/README.MD new file mode 100644 index 0000000..740913a --- /dev/null +++ b/README.MD @@ -0,0 +1,141 @@ +# 训练自己的YOLOv8模型 + +## 准备数据集 + +### 安装 LabelImg + +在命令提示符中输入以下命令： + +```bash +pip install labelimg -i https://pypi.tuna.tsinghua.edu.cn/simple +``` + +等待安装完成 + +![示例图片](docs/img/1.png) + +运行 + +```bash +labelimg +``` + +启动之后界面长这样 + +![示例图片](docs/img/2.png) +![示例图片](docs/img/3.png) +设置自动保存 +![示例图片](docs/img/4.png) +![示例图片](docs/img/5.png) + +labelimg的常用快捷键（熟练使用快捷键，提高效率） + +| 快捷键 | 功能 | +| :--- | :----: | +| W | 画框（创建或编辑标签框） | +| D |切换到下一张图片 | +| A |切换到上一张图片 | +| CTRL+Q | 退出LabelImg | +| CTRL+S |保存当前图片的标签 | +| Delete | 删除当前选中的标签框 | + +### 开始标注 + +- 点击Open Dir 选择原图片所在文件夹 + +- 点击Change Save Dir 选择存储位置 + +- 使用快捷键，开始标注，左侧将格式设置成yolo + +![示例图片](docs/img/6.png) + +### 将标注好的数据集按照指定路径放置 + +![示例图片](docs/img/13.png) + +## 训练YOLOv8模型 + +- 由于本地安装cuda较为麻烦，这里不做介绍，本文将使用腾讯云算力平台 + +### 登录并进入腾讯云高性能应用服务 HAI + +![示例图片](docs/img/7.png) + +### 创建实例 + +- 可选用预装了cuda的Pytorch，算力方案越贵，训练速度越快，普通1.2元/时的也够用了。 + +![示例图片](docs/img/8.png) + +- 创建实例之后，选择CloudStudio进入后台 + +![示例图片](docs/img/9.png) + +- 在终端安装yolo环境，克隆训练程序，上传数据集 + +- 使用国内服务器时候可使用清华源加速 + +```bash +pip install ultralytics -i https://pypi.tuna.tsinghua.edu.cn/simple +``` + +- 使用国外服务器时候可直接 + +```bash +pip install ultralytics +``` + +- 安装libGL.so.1 库 + +```bash +sudo apt-get update +sudo apt-get install libgl1-mesa-glx +``` + +- 环境安装完成后，克隆此训练代码 + +```bash +git clone http://gitea.qutcmrt.top/Robofish/YOLOv8.git +``` + +- 上传刚刚准备好的数据集datasets + +![示例图片](docs/img/14.png) + +- 修改yolo.yaml的内容，直接复制绝对路径。 + +![示例图片](docs/img/15.png) + +### 开始训练 + +```bash +yolo train data=yolo.yaml model=yolov8n.pt epochs=300 imgsz=640 batch=8 workers=0 device=0 +``` + +- 其中 data=YOLO.yaml 修改为实际yaml路径，model=yolov8n.pt修改为模型路径（按照教程走不用修改） +- 如果使用cpu训练，修改device='cpu',如果想使用多卡训练，device='\0,1,2,xxx\' + +![示例图片](docs/img/10.png) + +### 结束训练 + +- 训练完成的模型将位于 ' runs\detect\train\weights ' + +![示例图片](docs/img/11.png) + +- 右键下载，即可将训练好的模型下载到本地。 + +## 测试模型 + +- 在安装了ultralytics的电脑中，运行scripts文件夹中的track_test.py,修改模型和摄像头。 + +## 常见问题 + +### LabelImg无法标注，闪退 + +- 路径不能有中文 +- 请使用python3.9（推荐使用anconda） + +### 使用yolov8n 但是下载的是yolo11n + +- 删除文件夹里的yolov8n.pt即可。（其实可以直接用11了，速度更快，效果更好） diff --git a/docs/img/1.png b/docs/img/1.png new file mode 100644 index 0000000..de5c829 Binary files /dev/null and b/docs/img/1.png differ diff --git a/docs/img/10.png b/docs/img/10.png new file mode 100644 index 0000000..0653fab Binary files /dev/null and b/docs/img/10.png differ diff --git a/docs/img/11.png b/docs/img/11.png new file mode 100644 index 0000000..2a27d0b Binary files /dev/null and b/docs/img/11.png differ diff --git a/docs/img/12.png b/docs/img/12.png new file mode 100644 index 0000000..8f39bf3 Binary files /dev/null and b/docs/img/12.png differ diff --git a/docs/img/13.png b/docs/img/13.png new file mode 100644 index 0000000..9767665 Binary files /dev/null and b/docs/img/13.png differ diff --git a/docs/img/14.png b/docs/img/14.png new file mode 100644 index 0000000..597c3fb Binary files /dev/null and b/docs/img/14.png differ diff --git a/docs/img/15.png b/docs/img/15.png new file mode 100644 index 0000000..6614997 Binary files /dev/null and b/docs/img/15.png differ diff --git a/docs/img/2.png b/docs/img/2.png new file mode 100644 index 0000000..08e7bc8 Binary files /dev/null and b/docs/img/2.png differ diff --git a/docs/img/3.png b/docs/img/3.png new file mode 100644 index 0000000..fddabd8 Binary files /dev/null and b/docs/img/3.png differ diff --git a/docs/img/4.png b/docs/img/4.png new file mode 100644 index 0000000..7525294 Binary files /dev/null and b/docs/img/4.png differ diff --git a/docs/img/5.png b/docs/img/5.png new file mode 100644 index 0000000..c203808 Binary files /dev/null and b/docs/img/5.png differ diff --git a/docs/img/6.png b/docs/img/6.png new file mode 100644 index 0000000..b0798f7 Binary files /dev/null and b/docs/img/6.png differ diff --git a/docs/img/7.png b/docs/img/7.png new file mode 100644 index 0000000..fa93056 Binary files /dev/null and b/docs/img/7.png differ diff --git a/docs/img/8.png b/docs/img/8.png new file mode 100644 index 0000000..88c5ab1 Binary files /dev/null and b/docs/img/8.png differ diff --git a/docs/img/9.png b/docs/img/9.png new file mode 100644 index 0000000..d980a35 Binary files /dev/null and b/docs/img/9.png differ diff --git a/scripts/1080p.py b/scripts/1080p.py new file mode 100644 index 0000000..549021c --- /dev/null +++ b/scripts/1080p.py @@ -0,0 +1,29 @@ +# 使用前需要安装Pillow pip install Pillow + +from PIL import Image +import os + +def resize_to_1080p(image_path): + try: + with Image.open(image_path) as img: + # 获取图像的原始尺寸 + original_width, original_height = img.size + target_size = (1920, 1080) + + # 等比例缩放图像 + img.thumbnail(target_size, Image.LANCZOS) + img.save(image_path) + print(f"图像已调整大小: {image_path}") + except Exception as e: + print(f"处理图像时发生错误: {e}") + +def process_folder(folder_path): + for root, _, files in os.walk(folder_path): + for file in files: + if file.lower().endswith(('.png', '.jpg', '.jpeg', '.bmp', '.gif')): + image_path = os.path.join(root, file) + resize_to_1080p(image_path) + +if __name__ == "__main__": + folder_path = r"E:\School\R\Robocon\垃圾桶\数据集" + process_folder(folder_path) \ No newline at end of file diff --git a/scripts/track_test.py b/scripts/track_test.py new file mode 100644 index 0000000..e3286d9 --- /dev/null +++ b/scripts/track_test.py @@ -0,0 +1,63 @@ +from collections import defaultdict + +import cv2 +import numpy as np + +from ultralytics import YOLO + +# Load the YOLO model +model = YOLO("yolo11n.pt") +# model = YOLO("yolov8n.pt") +# model = YOLO("your_yolo_model.pt") + +# Open the video file +# video_path = "path/to/video.mp4" +cap = cv2.VideoCapture(0) + +# Store the track history +track_history = defaultdict(lambda: []) + +# Loop through the video frames +while cap.isOpened(): + # Read a frame from the video + success, frame = cap.read() + + if success: + results = model.track(frame, persist=True) + # print(results) + boxes = results[0].boxes.xywh.cpu() + track_ids = results[0].boxes.id + + if track_ids is not None: + track_ids = track_ids.int().cpu().tolist() + + # Visualize the results on the frame + annotated_frame = results[0].plot() + + # Plot the tracks + for box, track_id in zip(boxes, track_ids): + x, y, w, h = box + track = track_history[track_id] + track.append((float(x), float(y))) # x, y center point + if len(track) > 30: # retain 90 tracks for 90 frames + track.pop(0) + + # Draw the tracking lines + points = np.hstack(track).astype(np.int32).reshape((-1, 1, 2)) + cv2.polylines(annotated_frame, [points], isClosed=False, color=(230, 230, 230), thickness=10) + else: + annotated_frame = frame + + # Display the annotated frame + cv2.imshow("YOLO11 Tracking", annotated_frame) + + # Break the loop if 'q' is pressed + if cv2.waitKey(1) & 0xFF == ord("q"): + break + else: + # Break the loop if the end of the video is reached + break + +# Release the video capture object and close the display window +cap.release() +cv2.destroyAllWindows() \ No newline at end of file diff --git a/scripts/turn_img.py b/scripts/turn_img.py new file mode 100644 index 0000000..770c700 --- /dev/null +++ b/scripts/turn_img.py @@ -0,0 +1,29 @@ +# 使用前需要安装Pillow pip install Pillow + +from PIL import Image +import os + +def rotate_to_landscape(image_path): + try: + with Image.open(image_path) as img: + width, height = img.size + if height > width: + # 旋转图像使其变为横向 + rotated_img = img.rotate(90, expand=True) + rotated_img.save(image_path) + print(f"图像已旋转: {image_path}") + else: + print(f"图像已是横向: {image_path}") + except Exception as e: + print(f"处理图像时发生错误: {e}") + +def process_folder(folder_path): + for root, _, files in os.walk(folder_path): + for file in files: + if file.lower().endswith(('.png', '.jpg', '.jpeg', '.bmp', '.gif')): + image_path = os.path.join(root, file) + rotate_to_landscape(image_path) + +if __name__ == "__main__": + folder_path = "E:\School\R\Robocon\垃圾桶\数据集" + process_folder(folder_path) \ No newline at end of file diff --git a/yolo.yaml b/yolo.yaml new file mode 100644 index 0000000..7c71ef9 --- /dev/null +++ b/yolo.yaml @@ -0,0 +1,6 @@ +train: E:\School\R\Robocon\YOLOv8\datasets\images\train #训练集图片绝对路径 +val: E:\School\R\Robocon\YOLOv8\datasets\images\val #数据集绝对路径 +# number of classes +nc: 2 #类别数 +# class names +names: ['blue', 'red'] #类别名称 diff --git a/yolo11n.pt b/yolo11n.pt new file mode 100644 index 0000000..45b273b Binary files /dev/null and b/yolo11n.pt differ diff --git a/yolov8n.pt b/yolov8n.pt new file mode 100644 index 0000000..0db4ca4 Binary files /dev/null and b/yolov8n.pt differ