feat(models): 纯卷积缺陷分类定位模型

面向实时设备部署，全程只用 convolution，不含 attention / transformer。

- backbones: 自研 tiny_conv（深度可分离，默认）与 torchvision 封装（resnet/mobilenet/shufflenet）
- necks: nearest 上采样 + 3x3 卷积，把特征恢复到 stride 4，兼顾小缺陷定位与速度
- heads: anchor-free 中心点定位头（heatmap + wh + offset）与图像级分类头；
  分类头输出维度随 label_mode 切换（多类多热 / 单类互斥含背景位）
- postprocess: 3x3 max-pool 峰值抑制替代 NMS 循环，无循环、可导出 TensorRT / OpenVINO

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

models/heads/__init__.py

@@ -0,0 +1,4 @@
+from models.heads.center_head import CenterHead
+from models.heads.classification import ClassificationHead
+
+__all__ = ["CenterHead", "ClassificationHead"]

models/heads/center_head.py

@@ -0,0 +1,51 @@
+"""Anchor-free 中心点定位头（CenterNet 风格，纯卷积）。
+
+输出:
+    heatmap: (B, num_classes, H, W)  各类别缺陷中心的置信度（logits）
+    wh:      (B, 2, H, W)            中心点处的框宽高（特征图尺度）
+    offset:  (B, 2, H, W)            下采样量化误差补偿
+"""
+
+from __future__ import annotations
+
+import math
+
+import torch
+from torch import nn
+
+from models.layers import ConvBNAct
+from models.registry import HEADS
+
+
+def _branch(in_channels: int, hidden: int, out_channels: int) -> nn.Sequential:
+    return nn.Sequential(
+        ConvBNAct(in_channels, hidden, kernel_size=3),
+        nn.Conv2d(hidden, out_channels, kernel_size=1),
+    )
+
+
+@HEADS.register("center")
+class CenterHead(nn.Module):
+    def __init__(
+        self,
+        in_channels: int,
+        num_classes: int,
+        hidden_channels: int = 64,
+        prior_prob: float = 0.01,
+    ) -> None:
+        super().__init__()
+        self.num_classes = num_classes
+        self.heatmap = _branch(in_channels, hidden_channels, num_classes)
+        self.wh = _branch(in_channels, hidden_channels, 2)
+        self.offset = _branch(in_channels, hidden_channels, 2)
+
+        # heatmap 正样本极稀疏，用先验概率初始化最后一层 bias，稳定早期训练。
+        bias = -math.log((1 - prior_prob) / prior_prob)
+        nn.init.constant_(self.heatmap[-1].bias, bias)
+
+    def forward(self, feat: torch.Tensor) -> dict[str, torch.Tensor]:
+        return {
+            "heatmap": self.heatmap(feat),
+            "wh": self.wh(feat),
+            "offset": self.offset(feat),
+        }

models/heads/classification.py

@@ -0,0 +1,27 @@
+"""图像级缺陷分类头。
+
+输出维度由 `label_mode` 决定，见 `models.defect_net.DefectNet`：
+    multilabel: num_classes      —— 每一维独立 sigmoid，全 0 表示 OK 片
+    multiclass: num_classes + 1  —— softmax 互斥，最后一维为 "无缺陷"
+"""
+
+from __future__ import annotations
+
+import torch
+from torch import nn
+
+from models.registry import HEADS
+
+
+@HEADS.register("classification")
+class ClassificationHead(nn.Module):
+    def __init__(self, in_channels: int, num_outputs: int, dropout: float = 0.0) -> None:
+        super().__init__()
+        self.pool = nn.AdaptiveAvgPool2d(1)
+        self.drop = nn.Dropout(dropout) if dropout > 0 else nn.Identity()
+        self.fc = nn.Linear(in_channels, num_outputs)
+        self.num_outputs = num_outputs
+
+    def forward(self, feat: torch.Tensor) -> torch.Tensor:
+        x = self.pool(feat).flatten(1)
+        return self.fc(self.drop(x))