20250312

我现在可以用yolov5x6.pt模型了，下面是我的训练命令python train.py --weights yolov5x6.pt --img 1536 --data data_x6_0.9.yaml --batch-size 6 --device 0 --epochs 200 --cfg models/hub/yolov5m6.yaml，
我的data_x6_0.9.yaml为
# data.yaml
train: ../NEU-DET/train/images
val: ../NEU-DET/valid/images
task: classification
nc: 6
names: ['crazing', 'inclusion', 'patches', 'pitted_surface', 'rolled-in_scale', 'scratches']

# ------------------------- 核心优化参数 -------------------------
loss:
type: FocalLoss # 替换交叉熵，专注困难样本
class_weights: [15.0, 0.3, 1.0, 1.0, 1.0, 8.0] # 极端补偿 crazing/scratches
gamma: 2.0 # FocalLoss 参数，抑制易分类样本
alpha: 0.8 # 平衡正负样本

augment:
# --------------- 基础增强 ---------------
mosaic: 0.3 # 降低噪声干扰
mixup: 0.7 # 提升混合比例增强多样性
copy_paste: 0.0 # 禁用（对小样本无效）

# --------------- 几何增强 ---------------
random_rotate: 35 # 最大旋转角度提升至35°
random_scale: 0.15 # 强制放大图像至1.15倍
perspective: 0.0005 # 透视变换模拟视角变化

# --------------- 色彩增强 ---------------
hsv_h: 0.3 # 色调扰动提升至30%
hsv_s: 0.8 # 饱和度扰动提升至80%
hsv_v: 0.5 # 亮度扰动提升至50%

# --------------- 小目标专项增强 ---------------
small_object_min_area: 32 # 定义小目标（面积<32像素）
small_object_aug_ratio: 0.6 # 对小目标复制增强概率60%
cutout: 0.5 # 随机遮挡比例50%
grid_mask: 0.4 # 网格遮挡比例40%

# ------------------------- 训练参数 -------------------------
params:
img_size: 1536 # 提升分辨率至1536x1536
batch_size: 6 # 适配更高分辨率
optimizer:
name: AdamW # 使用AdamW优化器
lr0: 0.001 # 初始学习率
lrf: 0.02 # 最终学习率（OneCycle策略）
momentum: 0.9 # 动量参数
weight_decay: 0.05 # 权重衰减

# --------------- 高级调度 ---------------
cos_lr: True # 启用余弦退火
warmup_epochs: 10 # 学习率预热10轮
patience: 30 # 早停轮次

yolov5m6.yaml为
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license

# Parameters
nc: 6 # number of classes
depth_multiple: 1.33 # model depth multiple
width_multiple: 1.25 # layer channel multiple
anchors:
- [19, 27, 44, 40, 38, 94] # P3/8
- [96, 68, 86, 152, 180, 137] # P4/16
- [140, 301, 303, 264, 238, 542] # P5/32
- [436, 615, 739, 380, 925, 792] # P6/64

# YOLOv5 v6.0 backbone
backbone:
# [from, number, module, args]
[
[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
[-1, 3, C3, [128]],
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
[-1, 6, C3, [256]],
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
[-1, 9, C3, [512]],
[-1, 1, Conv, [768, 3, 2]], # 7-P5/32
[-1, 3, C3, [768]],
[-1, 1, Conv, [1024, 3, 2]], # 9-P6/64
[-1, 3, C3, [1024]],
[-1, 1, SPPF, [1024, 5]], # 11
]

# YOLOv5 v6.0 head
head: [
[-1, 1, Conv, [768, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, "nearest"]],
[[-1, 8], 1, Concat, [1]], # cat backbone P5
[-1, 3, C3, [768, False]], # 15

[-1, 1, Conv, [512, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, "nearest"]],
[[-1, 6], 1, Concat, [1]], # cat backbone P4
[-1, 3, C3, [512, False]], # 19

[-1, 1, Conv, [256, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, "nearest"]],
[[-1, 4], 1, Concat, [1]], # cat backbone P3
[-1, 3, C3, [256, False]], # 23 (P3/8-small)

[-1, 1, Conv, [256, 3, 2]],
[[-1, 20], 1, Concat, [1]], # cat head P4
[-1, 3, C3, [512, False]], # 26 (P4/16-medium)

[-1, 1, Conv, [512, 3, 2]],
[[-1, 16], 1, Concat, [1]], # cat head P5
[-1, 3, C3, [768, False]], # 29 (P5/32-large)

[-1, 1, Conv, [768, 3, 2]],
[[-1, 12], 1, Concat, [1]], # cat head P6
[-1, 3, C3, [1024, False]], # 32 (P6/64-xlarge)

[[23, 26, 29, 32], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5, P6)
]

最终的结果为

我如果想使用yolov5x6.pt这个模型使我的训练结果所有的mAP50都达到0.9以上，我该如何调整我的训练命令和data_x6_0.9.yaml