最新推送

zjsh_code/obb_main/train/obb_data.yaml

@@ -0,0 +1,18 @@
+# Ultralytics YOLO 🚀, AGPL-3.0 license
+# DOTA8 dataset 8 images from split DOTAv1 dataset by Ultralytics
+# Documentation: https://docs.ultralytics.com/datasets/obb/dota8/
+# Example usage: yolo train model=yolov8n-obb.pt data=dota8.yaml
+# parent
+# ├── ultralytics
+# └── datasets
+#     └── dota8  ← downloads here (1MB)
+
+# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
+path: ./dataset
+train: train  # 数据集路径下的train.txt
+val: val  # 数据集路径下的val.txt
+test: test  # 数据集路径下的test.txt
+
+nc: 1
+names: ['clamp']
+

zjsh_code/obb_main/train/train_obb_zengqiang.py

@@ -0,0 +1,42 @@
+from ultralytics import YOLO
+
+if __name__ == '__main__':
+    # ✅ 推荐：加载官方预训练模型 或 自己的 best.pt
+    model = YOLO(r'yolo11-obb.yaml')  #
+
+    results = model.train(
+        data='obb_data.yaml',
+        epochs=500,                    # 减少 epochs，配合早停
+        patience=0,                   # 50 轮无提升则停止
+        imgsz=640,
+        batch=4,
+        workers=10,
+        device='0',
+        project='runs/train',
+        name='exp_obb5',               # 建议递增实验编号
+        exist_ok=False,
+
+        # 优化器
+        optimizer='AdamW',
+        lr0=0.0005,                    # 更稳定的学习率
+        weight_decay=0.01,
+        momentum=0.937,
+
+        # 数据增强（OBB 关键）
+        degrees=5.0,                  # 随机旋转 ±10°
+        translate=0.1,                 # 平移
+        scale=0.5,                     # 缩放比例
+        shear=1.0,                     # 剪切
+        flipud=0.0,                    # 不推荐上下翻转（角度易错）
+        fliplr=0.5,                    # ✅ 水平翻转，OBB 支持良好
+        hsv_h=0.015,                   # 色调扰动
+        hsv_s=0.7,                     # 饱和度
+        hsv_v=0.4,                     # 明度
+
+        # 其他
+        close_mosaic=50,               # 最后10轮关闭 Mosaic 增强，提升稳定性
+        val=True,                      # 每轮验证
+
+        #
+        amp=False,
+    )

zjsh_code/obb_main/train/yolo11-obb.yaml

@@ -0,0 +1,47 @@
+# Ultralytics YOLO 🚀, AGPL-3.0 license
+# YOLO11 Oriented Bounding Boxes (OBB) model with P3-P5 outputs. For Usage examples see https://docs.ultralytics.com/tasks/obb
+
+# Parameters
+nc: 1 # number of classes
+scales: # model compound scaling constants, i.e. 'model=yolo11n-obb.yaml' will call yolo11-obb.yaml with scale 'n'
+  # [depth, width, max_channels]
+  n: [0.50, 0.25, 1024] # summary: 344 layers, 2695747 parameters, 2695731 gradients, 6.9 GFLOPs
+  s: [0.50, 0.50, 1024] # summary: 344 layers, 9744931 parameters, 9744915 gradients, 22.7 GFLOPs
+  m: [0.50, 1.00, 512] # summary: 434 layers, 20963523 parameters, 20963507 gradients, 72.2 GFLOPs
+  l: [1.00, 1.00, 512] # summary: 656 layers, 26220995 parameters, 26220979 gradients, 91.3 GFLOPs
+  x: [1.00, 1.50, 512] # summary: 656 layers, 58875331 parameters, 58875315 gradients, 204.3 GFLOPs
+
+# YOLO11n backbone
+backbone:
+  # [from, repeats, module, args]
+  - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
+  - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
+  - [-1, 2, C3k2, [256, False, 0.25]]
+  - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
+  - [-1, 2, C3k2, [512, False, 0.25]]
+  - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
+  - [-1, 2, C3k2, [512, True]]
+  - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
+  - [-1, 2, C3k2, [1024, True]]
+  - [-1, 1, SPPF, [1024, 5]] # 9
+  - [-1, 2, C2PSA, [1024]] # 10
+
+# YOLO11n head
+head:
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 6], 1, Concat, [1]] # cat backbone P4
+  - [-1, 2, C3k2, [512, False]] # 13
+
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
+  - [-1, 2, C3k2, [256, False]] # 16 (P3/8-small)
+
+  - [-1, 1, Conv, [256, 3, 2]]
+  - [[-1, 13], 1, Concat, [1]] # cat head P4
+  - [-1, 2, C3k2, [512, False]] # 19 (P4/16-medium)
+
+  - [-1, 1, Conv, [512, 3, 2]]
+  - [[-1, 10], 1, Concat, [1]] # cat head P5
+  - [-1, 2, C3k2, [1024, True]] # 22 (P5/32-large)
+
+  - [[16, 19, 22], 1, OBB, [nc, 1]] # Detect(P3, P4, P5)