Shaun ZhouandClaude Opus 5
3a36aad6c3
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>
34 lines
1.1 KiB
Python
34 lines
1.1 KiB
Python
"""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
|