初始化：换发型/换发色/训练发型服务

包含：
- hair_service_sd: 主服务（换发型/换发色/生发，端口8801）
- photo_service: LoRA调度+训练（端口32678）
- hair_grow_service: 调试测试页（端口8888，含4个测试页）
- 批量训练脚本（batch_train_hairstyles.py）
- 发际线mask自动识别（hairline_mask.py，4种方案）
- 手绘mask换发型（hair_swap_manual.py）
- 文档：README.md + LARGE_FILES.md + docs/

大文件（模型权重200G、训练数据123G）已排除，见 LARGE_FILES.md
OSS/COS密钥已脱敏为环境变量，原文件备份在本地

project/hair_service_sd/seg/networks/jpu.py

@@ -0,0 +1,68 @@
+"""Joint Pyramid Upsampling"""
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+__all__ = ['JPU']
+
+
+class SeparableConv2d(nn.Module):
+    def __init__(self, inplanes, planes, kernel_size=3, stride=1, padding=1,
+                 dilation=1, bias=False, norm_layer=nn.BatchNorm2d):
+        super(SeparableConv2d, self).__init__()
+        self.conv = nn.Conv2d(inplanes, inplanes, kernel_size, stride, padding, dilation, groups=inplanes, bias=bias)
+        self.bn = norm_layer(inplanes)
+        self.pointwise = nn.Conv2d(inplanes, planes, 1, bias=bias)
+
+    def forward(self, x):
+        x = self.conv(x)
+        x = self.bn(x)
+        x = self.pointwise(x)
+        return x
+
+
+# copy from: https://github.com/wuhuikai/FastFCN/blob/master/encoding/nn/customize.py
+class JPU(nn.Module):
+    def __init__(self, in_channels, width=512, norm_layer=nn.BatchNorm2d, **kwargs):
+        super(JPU, self).__init__()
+
+        self.conv5 = nn.Sequential(
+            nn.Conv2d(in_channels[-1], width, 3, padding=1, bias=False),
+            norm_layer(width),
+            nn.ReLU(True))
+        self.conv4 = nn.Sequential(
+            nn.Conv2d(in_channels[-2], width, 3, padding=1, bias=False),
+            norm_layer(width),
+            nn.ReLU(True))
+        self.conv3 = nn.Sequential(
+            nn.Conv2d(in_channels[-3], width, 3, padding=1, bias=False),
+            norm_layer(width),
+            nn.ReLU(True))
+
+        self.dilation1 = nn.Sequential(
+            SeparableConv2d(3 * width, width, 3, padding=1, dilation=1, bias=False),
+            norm_layer(width),
+            nn.ReLU(True))
+        self.dilation2 = nn.Sequential(
+            SeparableConv2d(3 * width, width, 3, padding=2, dilation=2, bias=False),
+            norm_layer(width),
+            nn.ReLU(True))
+        self.dilation3 = nn.Sequential(
+            SeparableConv2d(3 * width, width, 3, padding=4, dilation=4, bias=False),
+            norm_layer(width),
+            nn.ReLU(True))
+        self.dilation4 = nn.Sequential(
+            SeparableConv2d(3 * width, width, 3, padding=8, dilation=8, bias=False),
+            norm_layer(width),
+            nn.ReLU(True))
+
+    def forward(self, *inputs):
+        feats = [self.conv5(inputs[-1]), self.conv4(inputs[-2]), self.conv3(inputs[-3])]
+        size = feats[-1].size()[2:]
+        feats[-2] = F.interpolate(feats[-2], size, mode='bilinear', align_corners=True)
+        feats[-3] = F.interpolate(feats[-3], size, mode='bilinear', align_corners=True)
+        feat = torch.cat(feats, dim=1)
+        feat = torch.cat([self.dilation1(feat), self.dilation2(feat), self.dilation3(feat), self.dilation4(feat)],
+                         dim=1)
+
+        return inputs[0], inputs[1], inputs[2], feat