feat(worker): 接口1 四庭七眼测量真实实现（替换 Mock）

worker 侧从 Mock 替换为真实算法：
- face_analysis 包：detector(MediaPipe 478点) / pose(solvePnP 姿态) /
  calibration(虹膜直径法) / hair_segmenter+bisenet_model(方案B 头发分割) /
  measure(方案A兜底+B/A决策+七眼+换算) / annotation(numpy渐变线+中文标注)
- app.py：/api/v1/face/measure 接真实实现，返回 annotated_image_base64
  （不落盘不拼URL，落盘由网关做）；加 X-Internal-Token 鉴权、/health 就绪态、
  可配置分辨率门槛、异常兜底
- 部署：start.sh/run_worker.sh/hair-worker.service 监听 8187；worker_config 示例
- 测试 tests/：Tier1合成真值<1e-6 + Tier2缩放不变 + Tier3叠加 + 错误码集成 +
  数值回归，pytest 24 项全绿
- 文档补实测基线表 + RTX5090/torch 说明

注：worker 为 RTX 5090(sm_120)，pinned torch 2.2.2(cu121) 只到 sm_90，
BiSeNet 已自动回退 CPU（方案B 正常）；要用 GPU 需换 torch cu128(≥2.7)。

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

face_analysis/bisenet_model.py

@@ -0,0 +1,215 @@
+"""BiSeNet (face-parsing.PyTorch) 网络结构，vendored。
+
+源自 zllrunning/face-parsing.PyTorch，结构与权重 `79999_iter.pth`（CelebAMask-HQ
+19 类）严格对应，仅修改 resnet18 骨干加载为「优先本地权重」以适配内网离线。
+hair 类别索引 = 17。
+"""
+import os
+
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+import torch.utils.model_zoo as modelzoo
+
+resnet18_url = "https://download.pytorch.org/models/resnet18-5c106cde.pth"
+_LOCAL_RESNET18 = os.path.join(os.path.dirname(__file__), "weights", "resnet18-5c106cde.pth")
+
+
+def conv3x3(in_planes, out_planes, stride=1):
+    return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride, padding=1, bias=False)
+
+
+class BasicBlock(nn.Module):
+    def __init__(self, in_chan, out_chan, stride=1):
+        super(BasicBlock, self).__init__()
+        self.conv1 = conv3x3(in_chan, out_chan, stride)
+        self.bn1 = nn.BatchNorm2d(out_chan)
+        self.conv2 = conv3x3(out_chan, out_chan)
+        self.bn2 = nn.BatchNorm2d(out_chan)
+        self.relu = nn.ReLU(inplace=True)
+        self.downsample = None
+        if in_chan != out_chan or stride != 1:
+            self.downsample = nn.Sequential(
+                nn.Conv2d(in_chan, out_chan, kernel_size=1, stride=stride, bias=False),
+                nn.BatchNorm2d(out_chan),
+            )
+
+    def forward(self, x):
+        residual = self.conv1(x)
+        residual = F.relu(self.bn1(residual))
+        residual = self.conv2(residual)
+        residual = self.bn2(residual)
+        shortcut = x
+        if self.downsample is not None:
+            shortcut = self.downsample(x)
+        out = shortcut + residual
+        out = self.relu(out)
+        return out
+
+
+def create_layer_basic(in_chan, out_chan, bnum, stride=1):
+    layers = [BasicBlock(in_chan, out_chan, stride=stride)]
+    for _ in range(bnum - 1):
+        layers.append(BasicBlock(out_chan, out_chan, stride=1))
+    return nn.Sequential(*layers)
+
+
+class Resnet18(nn.Module):
+    def __init__(self):
+        super(Resnet18, self).__init__()
+        self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3, bias=False)
+        self.bn1 = nn.BatchNorm2d(64)
+        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
+        self.layer1 = create_layer_basic(64, 64, bnum=2, stride=1)
+        self.layer2 = create_layer_basic(64, 128, bnum=2, stride=2)
+        self.layer3 = create_layer_basic(128, 256, bnum=2, stride=2)
+        self.layer4 = create_layer_basic(256, 512, bnum=2, stride=2)
+        self.init_weight()
+
+    def forward(self, x):
+        x = self.conv1(x)
+        x = F.relu(self.bn1(x))
+        x = self.maxpool(x)
+        x = self.layer1(x)
+        feat8 = self.layer2(x)    # 1/8
+        feat16 = self.layer3(feat8)   # 1/16
+        feat32 = self.layer4(feat16)  # 1/32
+        return feat8, feat16, feat32
+
+    def init_weight(self):
+        # 优先本地骨干权重（内网离线），缺失才回退 torch model_zoo（会查缓存）。
+        if os.path.isfile(_LOCAL_RESNET18):
+            state_dict = torch.load(_LOCAL_RESNET18, map_location="cpu")
+        else:
+            state_dict = modelzoo.load_url(resnet18_url)
+        self_state_dict = self.state_dict()
+        for k, v in state_dict.items():
+            if "fc" in k:
+                continue
+            self_state_dict.update({k: v})
+        self.load_state_dict(self_state_dict)
+
+
+class ConvBNReLU(nn.Module):
+    def __init__(self, in_chan, out_chan, ks=3, stride=1, padding=1):
+        super(ConvBNReLU, self).__init__()
+        self.conv = nn.Conv2d(in_chan, out_chan, kernel_size=ks, stride=stride,
+                              padding=padding, bias=False)
+        self.bn = nn.BatchNorm2d(out_chan)
+
+    def forward(self, x):
+        x = self.conv(x)
+        x = F.relu(self.bn(x))
+        return x
+
+
+class BiSeNetOutput(nn.Module):
+    def __init__(self, in_chan, mid_chan, n_classes):
+        super(BiSeNetOutput, self).__init__()
+        self.conv = ConvBNReLU(in_chan, mid_chan, ks=3, stride=1, padding=1)
+        self.conv_out = nn.Conv2d(mid_chan, n_classes, kernel_size=1, bias=False)
+
+    def forward(self, x):
+        x = self.conv(x)
+        x = self.conv_out(x)
+        return x
+
+
+class AttentionRefinementModule(nn.Module):
+    def __init__(self, in_chan, out_chan):
+        super(AttentionRefinementModule, self).__init__()
+        self.conv = ConvBNReLU(in_chan, out_chan, ks=3, stride=1, padding=1)
+        self.conv_atten = nn.Conv2d(out_chan, out_chan, kernel_size=1, bias=False)
+        self.bn_atten = nn.BatchNorm2d(out_chan)
+        self.sigmoid_atten = nn.Sigmoid()
+
+    def forward(self, x):
+        feat = self.conv(x)
+        atten = F.avg_pool2d(feat, feat.size()[2:])
+        atten = self.conv_atten(atten)
+        atten = self.bn_atten(atten)
+        atten = self.sigmoid_atten(atten)
+        out = torch.mul(feat, atten)
+        return out
+
+
+class ContextPath(nn.Module):
+    def __init__(self):
+        super(ContextPath, self).__init__()
+        self.resnet = Resnet18()
+        self.arm16 = AttentionRefinementModule(256, 128)
+        self.arm32 = AttentionRefinementModule(512, 128)
+        self.conv_head32 = ConvBNReLU(128, 128, ks=3, stride=1, padding=1)
+        self.conv_head16 = ConvBNReLU(128, 128, ks=3, stride=1, padding=1)
+        self.conv_avg = ConvBNReLU(512, 128, ks=1, stride=1, padding=0)
+
+    def forward(self, x):
+        feat8, feat16, feat32 = self.resnet(x)
+        h8, w8 = feat8.size()[2:]
+        h16, w16 = feat16.size()[2:]
+        h32, w32 = feat32.size()[2:]
+
+        avg = F.avg_pool2d(feat32, feat32.size()[2:])
+        avg = self.conv_avg(avg)
+        avg_up = F.interpolate(avg, (h32, w32), mode="nearest")
+
+        feat32_arm = self.arm32(feat32)
+        feat32_sum = feat32_arm + avg_up
+        feat32_up = F.interpolate(feat32_sum, (h16, w16), mode="nearest")
+        feat32_up = self.conv_head32(feat32_up)
+
+        feat16_arm = self.arm16(feat16)
+        feat16_sum = feat16_arm + feat32_up
+        feat16_up = F.interpolate(feat16_sum, (h8, w8), mode="nearest")
+        feat16_up = self.conv_head16(feat16_up)
+
+        return feat8, feat16_up, feat32_up  # feat8 未用，保持与权重结构一致
+
+
+class FeatureFusionModule(nn.Module):
+    def __init__(self, in_chan, out_chan):
+        super(FeatureFusionModule, self).__init__()
+        self.convblk = ConvBNReLU(in_chan, out_chan, ks=1, stride=1, padding=0)
+        self.conv1 = nn.Conv2d(out_chan, out_chan // 4, kernel_size=1, stride=1,
+                               padding=0, bias=False)
+        self.conv2 = nn.Conv2d(out_chan // 4, out_chan, kernel_size=1, stride=1,
+                               padding=0, bias=False)
+        self.relu = nn.ReLU(inplace=True)
+        self.sigmoid = nn.Sigmoid()
+
+    def forward(self, fsp, fcp):
+        fcat = torch.cat([fsp, fcp], dim=1)
+        feat = self.convblk(fcat)
+        atten = F.avg_pool2d(feat, feat.size()[2:])
+        atten = self.conv1(atten)
+        atten = self.relu(atten)
+        atten = self.conv2(atten)
+        atten = self.sigmoid(atten)
+        feat_atten = torch.mul(feat, atten)
+        feat_out = feat_atten + feat
+        return feat_out
+
+
+class BiSeNet(nn.Module):
+    def __init__(self, n_classes):
+        super(BiSeNet, self).__init__()
+        # 该权重(79999_iter.pth)的变体无独立 SpatialPath：
+        # 直接用 ContextPath 的 resnet feat8（128ch）作为空间路径特征。
+        self.cp = ContextPath()
+        self.ffm = FeatureFusionModule(256, 256)
+        self.conv_out = BiSeNetOutput(256, 256, n_classes)
+        self.conv_out16 = BiSeNetOutput(128, 64, n_classes)
+        self.conv_out32 = BiSeNetOutput(128, 64, n_classes)
+
+    def forward(self, x):
+        h, w = x.size()[2:]
+        feat_res8, feat_cp8, feat_cp16 = self.cp(x)
+        feat_fuse = self.ffm(feat_res8, feat_cp8)
+
+        feat_out = self.conv_out(feat_fuse)
+        feat_out16 = self.conv_out16(feat_cp8)
+        feat_out32 = self.conv_out32(feat_cp16)
+        feat_out = F.interpolate(feat_out, (h, w), mode="bilinear", align_corners=True)
+        feat_out16 = F.interpolate(feat_out16, (h, w), mode="bilinear", align_corners=True)
+        feat_out32 = F.interpolate(feat_out32, (h, w), mode="bilinear", align_corners=True)
+        return feat_out, feat_out16, feat_out32