feat: MindNLP兼容Ultralytics库

src/mindnlp/ultralytics/__init__.py

@@ -0,0 +1,3 @@
+from .models.model import YOLO
+
+__all__ = ["YOLO"]

src/mindnlp/ultralytics/cfg/datasets/coco128-seg.yaml

@@ -0,0 +1,101 @@
+# Ultralytics  AGPL-3.0 License - https://ultralytics.com/license
+
+# COCO128-seg dataset https://www.kaggle.com/datasets/ultralytics/coco128 (first 128 images from COCO train2017) by Ultralytics
+# Documentation: https://docs.ultralytics.com/datasets/segment/coco/
+# Example usage: yolo train data=coco128-seg.yaml
+# parent
+# ├── ultralytics
+# └── datasets
+#     └── coco128-seg ← downloads here (7 MB)
+
+# 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: ./datasets/coco128-seg # dataset root dir
+train: images/train2017 # train images (relative to 'path') 128 images
+val: images/train2017 # val images (relative to 'path') 128 images
+test: # test images (optional)
+
+# Classes
+names:
+  0: person
+  1: bicycle
+  2: car
+  3: motorcycle
+  4: airplane
+  5: bus
+  6: train
+  7: truck
+  8: boat
+  9: traffic light
+  10: fire hydrant
+  11: stop sign
+  12: parking meter
+  13: bench
+  14: bird
+  15: cat
+  16: dog
+  17: horse
+  18: sheep
+  19: cow
+  20: elephant
+  21: bear
+  22: zebra
+  23: giraffe
+  24: backpack
+  25: umbrella
+  26: handbag
+  27: tie
+  28: suitcase
+  29: frisbee
+  30: skis
+  31: snowboard
+  32: sports ball
+  33: kite
+  34: baseball bat
+  35: baseball glove
+  36: skateboard
+  37: surfboard
+  38: tennis racket
+  39: bottle
+  40: wine glass
+  41: cup
+  42: fork
+  43: knife
+  44: spoon
+  45: bowl
+  46: banana
+  47: apple
+  48: sandwich
+  49: orange
+  50: broccoli
+  51: carrot
+  52: hot dog
+  53: pizza
+  54: donut
+  55: cake
+  56: chair
+  57: couch
+  58: potted plant
+  59: bed
+  60: dining table
+  61: toilet
+  62: tv
+  63: laptop
+  64: mouse
+  65: remote
+  66: keyboard
+  67: cell phone
+  68: microwave
+  69: oven
+  70: toaster
+  71: sink
+  72: refrigerator
+  73: book
+  74: clock
+  75: vase
+  76: scissors
+  77: teddy bear
+  78: hair drier
+  79: toothbrush
+
+# Download script/URL (optional)
+download: https://github.com/ultralytics/assets/releases/download/v0.0.0/coco128-seg.zip

src/mindnlp/ultralytics/cfg/datasets/coco128.yaml

@@ -0,0 +1,101 @@
+# Ultralytics  AGPL-3.0 License - https://ultralytics.com/license
+
+# COCO128 dataset https://www.kaggle.com/datasets/ultralytics/coco128 (first 128 images from COCO train2017) by Ultralytics
+# Documentation: https://docs.ultralytics.com/datasets/detect/coco/
+# Example usage: yolo train data=coco128.yaml
+# parent
+# ├── ultralytics
+# └── datasets
+#     └── coco128 ← downloads here (7 MB)
+
+# 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: ./datasets/coco128 # dataset root dir
+train: images/train2017 # train images (relative to 'path') 128 images
+val: images/train2017 # val images (relative to 'path') 128 images
+test: # test images (optional)
+
+# Classes
+names:
+  0: person
+  1: bicycle
+  2: car
+  3: motorcycle
+  4: airplane
+  5: bus
+  6: train
+  7: truck
+  8: boat
+  9: traffic light
+  10: fire hydrant
+  11: stop sign
+  12: parking meter
+  13: bench
+  14: bird
+  15: cat
+  16: dog
+  17: horse
+  18: sheep
+  19: cow
+  20: elephant
+  21: bear
+  22: zebra
+  23: giraffe
+  24: backpack
+  25: umbrella
+  26: handbag
+  27: tie
+  28: suitcase
+  29: frisbee
+  30: skis
+  31: snowboard
+  32: sports ball
+  33: kite
+  34: baseball bat
+  35: baseball glove
+  36: skateboard
+  37: surfboard
+  38: tennis racket
+  39: bottle
+  40: wine glass
+  41: cup
+  42: fork
+  43: knife
+  44: spoon
+  45: bowl
+  46: banana
+  47: apple
+  48: sandwich
+  49: orange
+  50: broccoli
+  51: carrot
+  52: hot dog
+  53: pizza
+  54: donut
+  55: cake
+  56: chair
+  57: couch
+  58: potted plant
+  59: bed
+  60: dining table
+  61: toilet
+  62: tv
+  63: laptop
+  64: mouse
+  65: remote
+  66: keyboard
+  67: cell phone
+  68: microwave
+  69: oven
+  70: toaster
+  71: sink
+  72: refrigerator
+  73: book
+  74: clock
+  75: vase
+  76: scissors
+  77: teddy bear
+  78: hair drier
+  79: toothbrush
+
+# Download script/URL (optional)
+download: https://github.com/ultralytics/assets/releases/download/v0.0.0/coco128.zip

src/mindnlp/ultralytics/cfg/datasets/coco8-pose.yaml

@@ -0,0 +1,47 @@
+# Ultralytics  AGPL-3.0 License - https://ultralytics.com/license
+
+# COCO8-pose dataset (first 8 images from COCO train2017) by Ultralytics
+# Documentation: https://docs.ultralytics.com/datasets/pose/coco8-pose/
+# Example usage: yolo train data=coco8-pose.yaml
+# parent
+# ├── ultralytics
+# └── datasets
+#     └── coco8-pose ← downloads here (1 MB)
+
+# 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: ./datasets/coco8-pose # dataset root dir
+train: images/train # train images (relative to 'path') 4 images
+val: images/val # val images (relative to 'path') 4 images
+test: # test images (optional)
+
+# Keypoints
+kpt_shape: [17, 3] # number of keypoints, number of dims (2 for x,y or 3 for x,y,visible)
+flip_idx: [0, 2, 1, 4, 3, 6, 5, 8, 7, 10, 9, 12, 11, 14, 13, 16, 15]
+
+# Classes
+names:
+  0: person
+
+# Keypoint names per class
+kpt_names:
+  0:
+    - nose
+    - left_eye
+    - right_eye
+    - left_ear
+    - right_ear
+    - left_shoulder
+    - right_shoulder
+    - left_elbow
+    - right_elbow
+    - left_wrist
+    - right_wrist
+    - left_hip
+    - right_hip
+    - left_knee
+    - right_knee
+    - left_ankle
+    - right_ankle
+
+# Download script/URL (optional)
+download: https://github.com/ultralytics/assets/releases/download/v0.0.0/coco8-pose.zip

src/mindnlp/ultralytics/cfg/datasets/imagenette2-160.yaml

@@ -0,0 +1,28 @@
+# Ultralytics  AGPL-3.0 License - https://ultralytics.com/license
+# Imagenette2-160 Dataset by fast.ai
+# Example usage: python train.py --data imagenette2-160.yaml
+
+# 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: ./datasets/imagenette2-160 # 你的数据集根目录 (根据你的截图和运行路径调整)
+train: train # 训练集相对路径 (会与 path 拼接)
+val: val     # 验证集相对路径 (会与 path 拼接)
+test:        # 测试集 (Imagenette 没有单独的 test，可以留空)
+
+# Classes
+nc: 10 # 类别数量
+names:
+  0: tench            # 丁鱼
+  1: English springer # 英国斯宾格犬
+  2: cassette player  # 录音机
+  3: chain saw        # 链锯
+  4: church           # 教堂
+  5: French horn      # 圆号
+  6: garbage truck    # 垃圾车
+  7: gas pump         # 加油泵
+  8: golf ball        # 高尔夫球
+  9: parachute        # 降落伞
+
+# Download script/URL (optional)
+download: |
+  wget https://s3.amazonaws.com/fast-ai-imageclas/imagenette2-160.tgz
+  tar -xzvf imagenette2-160.tgz

src/mindnlp/ultralytics/cfg/hyp.yaml

@@ -0,0 +1,60 @@
+# ==========================================
+# YOLO11 统一超参数配置 (适用于 Classify, Detect, Segment, Pose)
+# ==========================================
+
+# 1. 优化器与学习率 (Optimizer & LR)
+
+optimizer: 'SGD'      # 优化器选择 
+lr0: 0.01             # 初始学习率（微调pose任务,使用coco8-pose数据集时,推荐使用0.001）
+lrf: 0.01             # 最终学习率比例 (lr0 * lrf = 0.0001)
+momentum: 0.937       # 动量 (SGD momentum / Adam beta1)
+weight_decay: 0.0005  # 权重衰减系数 (L2 正则化)
+warmup_epochs: 3.0    # 预热轮数 (前几个 Epoch 学习率从低爬升)
+warmup_momentum: 0.8  # 预热阶段的初始动量
+warmup_bias_lr: 0.1   # 预热阶段偏置项(bias)的学习率
+
+
+# 2. 任务损失权重 (Loss Weights)
+# 说明：各个任务会自动读取自己需要的权重，无关的会被忽略
+
+box: 7.5              # 边界框回归损失 (GIoU/CIoU)
+cls: 0.5              # 类别分类损失 (BCE / CE)
+dfl: 1.5              # 分布焦点损失 (DFL)
+pose: 12.0            # 姿态估计：关键点坐标损失
+kobj: 1.0             # 姿态估计：关键点可见度损失
+seg: 2.5              # 实例分割：掩码 BCE 损失
+label_smoothing: 0.0  # 标签平滑系数 (防止过拟合，通常为0)
+
+
+# 3. 基础数据增强 (Data Augmentation)
+
+hsv_h: 0.015          # 图像 HSV 色调增强比例
+hsv_s: 0.7            # 图像 HSV 饱和度增强比例
+hsv_v: 0.4            # 图像 HSV 明度增强比例
+degrees: 0.0          # 图像旋转角度 (+/- deg)
+translate: 0.1        # 图像平移比例 (+/- fraction)
+scale: 0.5            # 图像缩放比例 (+/- gain)
+shear: 0.0            # 图像剪切角度 (+/- deg)
+perspective: 0.0      # 透视变换系数 (0-0.001)
+flipud: 0.0           # 图像上下翻转概率 
+fliplr: 0.5           # 图像左右翻转概率 (分类和检测常用)
+
+
+# 4. 高级图像拼接增强 (Mosaic & MixUp)
+# 注意：分类任务通常不使用马赛克增强，代码里需做判断
+
+mosaic: 1.0           # 马赛克数据增强概率 (检测/分割/姿态 核心)
+mixup: 0.0            # MixUp 增强概率
+copy_paste: 0.0       # Copy-Paste 分割增强概率
+
+
+# 5. 验证与推理超参数 (Val & Inference Settings)
+# 注意：在验证(Val)计算 mAP 时，系统会自动将 conf 降为 0.001；
+# 下面填写的 conf 主要供常规推理(Predict)或最终展示使用。
+
+conf: 0.25            # 目标置信度阈值 (预测时使用 0.25，验证算 mAP 时代码内部会强转为 0.001)
+iou: 0.6              # NMS (非极大值抑制) 的 IoU 阈值
+max_det: 300          # 每张图像最多保留的预测框数量
+half: False           # 是否使用 FP16 半精度推理 (Ascend/GPU 推荐开启以提速)
+dnn: False            # 是否使用 OpenCV DNN 进行 ONNX 推理
+plots: True           # 是否在验证期间保存画好框的结果图和各种评估图表

src/mindnlp/ultralytics/cfg/models/11/yolo11-cls.yaml

@@ -0,0 +1,33 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# Ultralytics YOLO11-cls image classification model
+# Model docs: https://docs.ultralytics.com/models/yolo11
+# Task docs: https://docs.ultralytics.com/tasks/classify
+
+# Parameters
+nc: 1000 # number of classes
+scales: # model compound scaling constants, i.e. 'model=yolo11n-cls.yaml' will call yolo11-cls.yaml with scale 'n'
+  # [depth, width, max_channels]
+  n: [0.50, 0.25, 1024] # summary: 86 layers, 1633584 parameters, 1633584 gradients, 0.5 GFLOPs
+  s: [0.50, 0.50, 1024] # summary: 86 layers, 5545488 parameters, 5545488 gradients, 1.6 GFLOPs
+  m: [0.50, 1.00, 512] # summary: 106 layers, 10455696 parameters, 10455696 gradients, 5.0 GFLOPs
+  l: [1.00, 1.00, 512] # summary: 176 layers, 12937104 parameters, 12937104 gradients, 6.2 GFLOPs
+  x: [1.00, 1.50, 512] # summary: 176 layers, 28458544 parameters, 28458544 gradients, 13.7 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, 2, C2PSA, [1024]] # 9
+
+# YOLO11n head
+head:
+  - [-1, 1, Classify, [nc]] # Classify