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/necks/__init__.py

@@ -0,0 +1,3 @@
+from models.necks.upsample import UpsampleNeck
+
+__all__ = ["UpsampleNeck"]

models/necks/upsample.py

@@ -0,0 +1,33 @@
+"""上采样 neck：把骨架的低分辨率特征恢复到定位所需的 stride。"""
+
+from __future__ import annotations
+
+import torch
+from torch import nn
+from torch.nn import functional as F
+
+from models.layers import ConvBNAct
+from models.registry import NECKS
+
+
+@NECKS.register("upsample")
+class UpsampleNeck(nn.Module):
+    """`num_upsamples` 次 2 倍上采样，每次接一个 3x3 卷积平滑。
+
+    使用 nearest + conv 而非转置卷积：避免棋盘伪影，且在推理引擎上更快。
+    """
+
+    def __init__(self, in_channels: int, channels: int = 64, num_upsamples: int = 2) -> None:
+        super().__init__()
+        self.lateral = ConvBNAct(in_channels, channels, kernel_size=1)
+        self.blocks = nn.ModuleList(
+            [ConvBNAct(channels, channels, kernel_size=3) for _ in range(num_upsamples)]
+        )
+        self.out_channels = channels
+        self.scale_factor = 2**num_upsamples
+
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
+        x = self.lateral(x)
+        for block in self.blocks:
+            x = block(F.interpolate(x, scale_factor=2.0, mode="nearest"))
+        return x