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>
11 lines
236 B
Python
11 lines
236 B
Python
"""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"]
|