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/defect_net.py

@@ -0,0 +1,83 @@
+"""缺陷分类 + 定位主模型。"""
+
+from __future__ import annotations
+
+from collections.abc import Mapping
+from typing import Any
+
+import torch
+from torch import nn
+
+from models.heads.center_head import CenterHead
+from models.heads.classification import ClassificationHead
+from models.registry import BACKBONES, MODELS, NECKS
+from utils.labels import LABEL_MODES, MULTILABEL, check_label_mode
+
+__all__ = ["DefectNet", "classification_outputs", "LABEL_MODES"]
+
+
+def classification_outputs(num_classes: int, label_mode: str) -> int:
+    """分类头的输出维度；multiclass 需要额外一维表示 "无缺陷"。"""
+    check_label_mode(label_mode)
+    return num_classes if label_mode == MULTILABEL else num_classes + 1
+
+
+@MODELS.register("defect_net")
+class DefectNet(nn.Module):
+    """backbone -> neck -> {分类头, 中心点定位头}。
+
+    Args:
+        num_classes: 缺陷类别数（不含背景）。
+        backbone: backbone 注册表的配置，如 `{"name": "tiny_conv", ...}`。
+        neck: neck 配置，`None` 表示直接在骨架特征上出图。
+        head: CenterHead 的额外参数。
+        with_classification: 是否输出图像级分类 logits。
+        label_mode: 图像级标签形式，由 yaml 配置决定。
+            "multilabel" —— 多类：一张图可同时含多种缺陷，逐类 sigmoid + BCE；
+            "multiclass" —— 单类：一张图只归一个类别（含 "无缺陷"），softmax + CE。
+            仅影响分类头与分类损失；定位头始终按 num_classes 个类别输出 heatmap。
+    """
+
+    def __init__(
+        self,
+        num_classes: int,
+        backbone: Mapping[str, Any] | None = None,
+        neck: Mapping[str, Any] | None = None,
+        head: Mapping[str, Any] | None = None,
+        with_classification: bool = True,
+        classification: Mapping[str, Any] | None = None,
+        label_mode: str = "multilabel",
+    ) -> None:
+        super().__init__()
+        self.num_classes = num_classes
+        self.label_mode = check_label_mode(label_mode)
+
+        self.backbone = BACKBONES.build(dict(backbone or {"name": "tiny_conv"}))
+        stride = self.backbone.out_stride
+        channels = self.backbone.out_channels
+
+        if neck:
+            self.neck: nn.Module = NECKS.build(dict(neck), in_channels=channels)
+            channels = self.neck.out_channels
+            stride = stride // self.neck.scale_factor
+        else:
+            self.neck = nn.Identity()
+
+        self.out_stride = stride
+        self.center_head = CenterHead(channels, num_classes, **dict(head or {}))
+        self.cls_head = (
+            ClassificationHead(
+                channels,
+                classification_outputs(num_classes, label_mode),
+                **dict(classification or {}),
+            )
+            if with_classification
+            else None
+        )
+
+    def forward(self, images: torch.Tensor) -> dict[str, torch.Tensor]:
+        feat = self.neck(self.backbone(images))
+        outputs = self.center_head(feat)
+        if self.cls_head is not None:
+            outputs["logits"] = self.cls_head(feat)
+        return outputs