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/postprocess.py

@@ -0,0 +1,68 @@
+"""推理后处理：从 heatmap 解码出缺陷框。"""
+
+from __future__ import annotations
+
+import torch
+from torch.nn import functional as F
+
+
+def heatmap_nms(heatmap: torch.Tensor, kernel: int = 3) -> torch.Tensor:
+    """用 max-pool 做峰值抑制，替代 NMS（无循环，可导出）。"""
+    pooled = F.max_pool2d(heatmap, kernel, stride=1, padding=kernel // 2)
+    return heatmap * (pooled == heatmap).float()
+
+
+@torch.no_grad()
+def decode_heatmap(
+    heatmap: torch.Tensor,
+    wh: torch.Tensor,
+    offset: torch.Tensor,
+    stride: int,
+    topk: int = 50,
+    score_threshold: float = 0.3,
+) -> list[dict[str, torch.Tensor]]:
+    """解码为原图坐标下的检测结果。
+
+    Args:
+        heatmap: (B, C, H, W) logits。
+        wh / offset: (B, 2, H, W)，单位为特征图像素。
+        stride: 特征图相对原图的下采样倍数。
+
+    Returns:
+        每张图一个 dict：`boxes` (N, 4) xyxy、`scores` (N,)、`labels` (N,)。
+    """
+    scores_map = heatmap_nms(heatmap.sigmoid())
+    batch, _num_classes, height, width = scores_map.shape
+
+    flat = scores_map.view(batch, -1)
+    topk = min(topk, flat.shape[1])
+    topk_scores, topk_idx = flat.topk(topk, dim=1)
+
+    labels = torch.div(topk_idx, height * width, rounding_mode="floor")
+    pixel_idx = topk_idx % (height * width)
+    ys = torch.div(pixel_idx, width, rounding_mode="floor").float()
+    xs = (pixel_idx % width).float()
+
+    wh_flat = wh.view(batch, 2, -1)
+    offset_flat = offset.view(batch, 2, -1)
+    gather_idx = pixel_idx.unsqueeze(1).expand(-1, 2, -1)
+    pred_wh = wh_flat.gather(2, gather_idx)
+    pred_offset = offset_flat.gather(2, gather_idx)
+
+    cx = (xs + pred_offset[:, 0]) * stride
+    cy = (ys + pred_offset[:, 1]) * stride
+    half_w = pred_wh[:, 0].clamp(min=0) * stride / 2
+    half_h = pred_wh[:, 1].clamp(min=0) * stride / 2
+    boxes = torch.stack([cx - half_w, cy - half_h, cx + half_w, cy + half_h], dim=-1)
+
+    results = []
+    for i in range(batch):
+        keep = topk_scores[i] >= score_threshold
+        results.append(
+            {
+                "boxes": boxes[i][keep],
+                "scores": topk_scores[i][keep],
+                "labels": labels[i][keep],
+            }
+        )
+    return results