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>
This commit is contained in:
Shaun Zhou
2026-09-02 17:54:55 +08:00
co-authored by Claude Opus 5
parent f4eff8beee
commit 3a36aad6c3
14 changed files with 504 additions and 0 deletions
+10
View File
@@ -0,0 +1,10 @@
"""模型组件注册表。"""
from utils.registry import Registry
BACKBONES = Registry("backbones")
NECKS = Registry("necks")
HEADS = Registry("heads")
MODELS = Registry("models")
__all__ = ["BACKBONES", "NECKS", "HEADS", "MODELS"]