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
This commit is contained in:
xsl
@@ -0,0 +1,311 @@
|
||||
import torch.nn as nn
|
||||
import torch.utils.model_zoo as model_zoo
|
||||
import torch
|
||||
import os
|
||||
import numpy as np
|
||||
import cv2
|
||||
from utils import landmark_processor, utils_3ddfa, params_3ddfa
|
||||
|
||||
__all__ = ['ResNet', 'resnet18', 'resnet34', 'resnet50', 'resnet101',
|
||||
'resnet152']
|
||||
|
||||
|
||||
model_urls = {
|
||||
'resnet18': 'https://download.pytorch.org/models/resnet18-5c106cde.pth',
|
||||
'resnet34': 'https://download.pytorch.org/models/resnet34-333f7ec4.pth',
|
||||
'resnet50': 'https://download.pytorch.org/models/resnet50-19c8e357.pth',
|
||||
'resnet101': 'https://download.pytorch.org/models/resnet101-5d3b4d8f.pth',
|
||||
'resnet152': 'https://download.pytorch.org/models/resnet152-b121ed2d.pth',
|
||||
}
|
||||
|
||||
|
||||
def conv3x3(in_planes, out_planes, stride=1):
|
||||
"""3x3 convolution with padding"""
|
||||
return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride,
|
||||
padding=1, bias=False)
|
||||
|
||||
|
||||
def conv1x1(in_planes, out_planes, stride=1):
|
||||
"""1x1 convolution"""
|
||||
return nn.Conv2d(in_planes, out_planes, kernel_size=1, stride=stride, bias=False)
|
||||
|
||||
|
||||
class BasicBlock(nn.Module):
|
||||
expansion = 1
|
||||
|
||||
def __init__(self, inplanes, planes, stride=1, downsample=None):
|
||||
super(BasicBlock, self).__init__()
|
||||
self.conv1 = conv3x3(inplanes, planes, stride)
|
||||
self.bn1 = nn.BatchNorm2d(planes)
|
||||
self.relu = nn.ReLU(inplace=True)
|
||||
self.conv2 = conv3x3(planes, planes)
|
||||
self.bn2 = nn.BatchNorm2d(planes)
|
||||
self.downsample = downsample
|
||||
self.stride = stride
|
||||
|
||||
def forward(self, x):
|
||||
identity = x
|
||||
|
||||
out = self.conv1(x)
|
||||
out = self.bn1(out)
|
||||
out = self.relu(out)
|
||||
|
||||
out = self.conv2(out)
|
||||
out = self.bn2(out)
|
||||
|
||||
if self.downsample is not None:
|
||||
identity = self.downsample(x)
|
||||
|
||||
out += identity
|
||||
out = self.relu(out)
|
||||
|
||||
return out
|
||||
|
||||
|
||||
class Bottleneck(nn.Module):
|
||||
expansion = 4
|
||||
|
||||
def __init__(self, inplanes, planes, stride=1, downsample=None):
|
||||
super(Bottleneck, self).__init__()
|
||||
self.conv1 = conv1x1(inplanes, planes)
|
||||
self.bn1 = nn.BatchNorm2d(planes)
|
||||
self.conv2 = conv3x3(planes, planes, stride)
|
||||
self.bn2 = nn.BatchNorm2d(planes)
|
||||
self.conv3 = conv1x1(planes, planes * self.expansion)
|
||||
self.bn3 = nn.BatchNorm2d(planes * self.expansion)
|
||||
self.relu = nn.ReLU(inplace=True)
|
||||
self.downsample = downsample
|
||||
self.stride = stride
|
||||
|
||||
def forward(self, x):
|
||||
identity = x
|
||||
|
||||
out = self.conv1(x)
|
||||
out = self.bn1(out)
|
||||
out = self.relu(out)
|
||||
|
||||
out = self.conv2(out)
|
||||
out = self.bn2(out)
|
||||
out = self.relu(out)
|
||||
|
||||
out = self.conv3(out)
|
||||
out = self.bn3(out)
|
||||
|
||||
if self.downsample is not None:
|
||||
identity = self.downsample(x)
|
||||
|
||||
out += identity
|
||||
out = self.relu(out)
|
||||
|
||||
return out
|
||||
|
||||
|
||||
class ResNet(nn.Module):
|
||||
|
||||
def __init__(self, block, layers, num_classes=1000, no_branch=False, no_activate=False, zero_init_residual=False):
|
||||
super(ResNet, self).__init__()
|
||||
self.inplanes = 64
|
||||
self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3, bias=False)
|
||||
self.bn1 = nn.BatchNorm2d(64)
|
||||
self.relu = nn.ReLU(inplace=True)
|
||||
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
|
||||
self.layer1 = self._make_layer(block, 64, layers[0])
|
||||
self.layer2 = self._make_layer(block, 128, layers[1], stride=2)
|
||||
self.layer3 = self._make_layer(block, 256, layers[2], stride=2)
|
||||
self.layer4 = self._make_layer(block, 512, layers[3], stride=2)
|
||||
self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
|
||||
if no_activate:
|
||||
if no_branch:
|
||||
self.fc = nn.Sequential(*[nn.Linear(512 * block.expansion, num_classes)])
|
||||
else:
|
||||
self.fc_key = nn.Sequential(*[nn.Linear(256 * block.expansion, 45 * 2)])
|
||||
self.fc_ctrl = nn.Sequential(*[nn.Linear(256 * block.expansion, 48 * 2)])
|
||||
else:
|
||||
if no_branch:
|
||||
self.fc = nn.Sequential(*[nn.Linear(512 * block.expansion, num_classes), nn.Tanh()])
|
||||
else:
|
||||
self.fc_key = nn.Sequential(*[nn.Linear(256 * block.expansion, 45 * 2), nn.Tanh()])
|
||||
self.fc_ctrl = nn.Sequential(*[nn.Linear(256 * block.expansion, 48 * 2), nn.Tanh()])
|
||||
self.no_branch = no_branch
|
||||
|
||||
for m in self.modules():
|
||||
if isinstance(m, nn.Conv2d):
|
||||
nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
|
||||
elif isinstance(m, nn.BatchNorm2d):
|
||||
nn.init.constant_(m.weight, 1)
|
||||
nn.init.constant_(m.bias, 0)
|
||||
|
||||
# Zero-initialize the last BN in each residual branch,
|
||||
# so that the residual branch starts with zeros, and each residual block behaves like an identity.
|
||||
# This improves the model by 0.2~0.3% according to https://arxiv.org/abs/1706.02677
|
||||
if zero_init_residual:
|
||||
for m in self.modules():
|
||||
if isinstance(m, Bottleneck):
|
||||
nn.init.constant_(m.bn3.weight, 0)
|
||||
elif isinstance(m, BasicBlock):
|
||||
nn.init.constant_(m.bn2.weight, 0)
|
||||
|
||||
def _make_layer(self, block, planes, blocks, stride=1):
|
||||
downsample = None
|
||||
if stride != 1 or self.inplanes != planes * block.expansion:
|
||||
downsample = nn.Sequential(
|
||||
conv1x1(self.inplanes, planes * block.expansion, stride),
|
||||
nn.BatchNorm2d(planes * block.expansion),
|
||||
)
|
||||
|
||||
layers = []
|
||||
layers.append(block(self.inplanes, planes, stride, downsample))
|
||||
self.inplanes = planes * block.expansion
|
||||
for _ in range(1, blocks):
|
||||
layers.append(block(self.inplanes, planes))
|
||||
|
||||
return nn.Sequential(*layers)
|
||||
|
||||
def forward(self, x):
|
||||
x = self.conv1(x)
|
||||
x = self.bn1(x)
|
||||
x = self.relu(x)
|
||||
x = self.maxpool(x)
|
||||
|
||||
x = self.layer1(x)
|
||||
x = self.layer2(x)
|
||||
x = self.layer3(x)
|
||||
x = self.layer4(x)
|
||||
|
||||
if self.no_branch:
|
||||
key = self.avgpool(x)
|
||||
key = key.view(-1, 512)
|
||||
key = self.fc(key)
|
||||
return key
|
||||
else:
|
||||
key, ctrl = torch.chunk(x, 2, dim=1)
|
||||
|
||||
key = self.avgpool(key)
|
||||
key = key.view(key.size(0), -1)
|
||||
key = self.fc_key(key)
|
||||
|
||||
ctrl = self.avgpool(ctrl)
|
||||
ctrl = ctrl.view(ctrl.size(0), -1)
|
||||
ctrl = self.fc_ctrl(ctrl)
|
||||
|
||||
return key, ctrl
|
||||
|
||||
def resnet18(pretrained=False, **kwargs):
|
||||
"""Constructs a ResNet-18 model.
|
||||
|
||||
Args:
|
||||
pretrained (bool): If True, returns a model pre-trained on ImageNet
|
||||
"""
|
||||
model = ResNet(BasicBlock, [2, 2, 2, 2], **kwargs)
|
||||
if pretrained:
|
||||
model.load_state_dict(model_zoo.load_url(model_urls['resnet18']), strict=False)
|
||||
return model
|
||||
|
||||
|
||||
def resnet34(pretrained=False, **kwargs):
|
||||
"""Constructs a ResNet-34 model.
|
||||
|
||||
Args:
|
||||
pretrained (bool): If True, returns a model pre-trained on ImageNet
|
||||
"""
|
||||
model = ResNet(BasicBlock, [3, 4, 6, 3], **kwargs)
|
||||
if pretrained:
|
||||
model.load_state_dict(model_zoo.load_url(model_urls['resnet34']))
|
||||
return model
|
||||
|
||||
|
||||
def resnet50(pretrained=False, **kwargs):
|
||||
"""Constructs a ResNet-50 model.
|
||||
|
||||
Args:
|
||||
pretrained (bool): If True, returns a model pre-trained on ImageNet
|
||||
"""
|
||||
model = ResNet(Bottleneck, [3, 4, 6, 3], **kwargs)
|
||||
if pretrained:
|
||||
model.load_state_dict(model_zoo.load_url(model_urls['resnet50']))
|
||||
return model
|
||||
|
||||
|
||||
def resnet101(pretrained=False, **kwargs):
|
||||
"""Constructs a ResNet-101 model.
|
||||
|
||||
Args:
|
||||
pretrained (bool): If True, returns a model pre-trained on ImageNet
|
||||
"""
|
||||
model = ResNet(Bottleneck, [3, 4, 23, 3], **kwargs)
|
||||
if pretrained:
|
||||
model.load_state_dict(model_zoo.load_url(model_urls['resnet101']))
|
||||
return model
|
||||
|
||||
|
||||
def resnet152(pretrained=False, **kwargs):
|
||||
"""Constructs a ResNet-152 model.
|
||||
|
||||
Args:
|
||||
pretrained (bool): If True, returns a model pre-trained on ImageNet
|
||||
"""
|
||||
model = ResNet(Bottleneck, [3, 8, 36, 3], **kwargs)
|
||||
if pretrained:
|
||||
model.load_state_dict(model_zoo.load_url(model_urls['resnet152']))
|
||||
return model
|
||||
|
||||
|
||||
class Model_3DDFA(nn.Module):
|
||||
def __init__(self, gpu_id=None):
|
||||
super(Model_3DDFA, self).__init__()
|
||||
|
||||
self.face_alignment_net = resnet18(pretrained=False, num_classes=76, no_branch=True, no_activate=True)
|
||||
|
||||
model_path, _ = os.path.split(os.path.realpath(__file__))
|
||||
weights = torch.load(os.path.join(model_path, 'face_3ddfa.pth'), map_location=lambda storage, loc: storage)
|
||||
self.load_state_dict(weights)
|
||||
self.eval()
|
||||
self.device = torch.device('cuda:{}'.format(gpu_id) if gpu_id is not None else 'cpu')
|
||||
self.to(self.device)
|
||||
|
||||
def forward(self, imgs):
|
||||
pred_pose_shape_exp = self.face_alignment_net(imgs)
|
||||
return pred_pose_shape_exp
|
||||
|
||||
def forward_np(self, imgs):
|
||||
pred_pose_shape_exp = self.face_alignment_net(imgs)
|
||||
return pred_pose_shape_exp.detach().cpu().numpy()
|
||||
|
||||
def detect(self, images, landmarks):
|
||||
dst_size = 256
|
||||
with torch.no_grad():
|
||||
input_numpy = np.zeros((len(images), 3, dst_size, dst_size), dtype=np.float32)
|
||||
assert len(images) == len(landmarks)
|
||||
all_mat = []
|
||||
all_res = []
|
||||
all_height = []
|
||||
for ix, img in enumerate(images):
|
||||
landmark = landmarks[ix]
|
||||
|
||||
mat = landmark_processor.get_transform_mat_full_face(landmark, dst_size)
|
||||
|
||||
all_mat.append(mat)
|
||||
all_height.append(img.shape[0])
|
||||
|
||||
tmp = cv2.warpAffine(img, mat, (dst_size, dst_size))
|
||||
|
||||
input_numpy[ix, :, :, :] = tmp.transpose((2, 0, 1)).astype(np.float32) / 255
|
||||
|
||||
# cv2.imshow('3ddfa_', tmp)
|
||||
# cv2.waitKey()
|
||||
|
||||
in_tensor = torch.from_numpy(input_numpy)
|
||||
in_tensor = in_tensor.to(self.device)
|
||||
params = self.face_alignment_net(in_tensor)
|
||||
params = params.cpu().numpy()
|
||||
|
||||
for ix, param in enumerate(params):
|
||||
param[0] = param[0] / params_3ddfa.SCALE_F
|
||||
param[1:4] = param[1:4] / params_3ddfa.SCALE_ROTATE
|
||||
param[4:6] = param[4:6] / params_3ddfa.SCALE_OFFSET
|
||||
param[6:56] = (param[6:56] / params_3ddfa.SCALE_SHAPE)
|
||||
param[56:] = (param[56:] / params_3ddfa.SCALE_EXP)
|
||||
new_param = utils_3ddfa.transform_params(param, cv2.invertAffineTransform(all_mat[ix]), all_height[ix], dst_size)
|
||||
all_res.append(new_param)
|
||||
|
||||
return all_res
|
||||
Reference in New Issue
Block a user