From e6bd5af6a8e306a1cdef63402a77a980a04ad6e1 Mon Sep 17 00:00:00 2001 From: Grafting Rayman <156515434+GraftingRayman@users.noreply.github.com> Date: Fri, 17 Jan 2025 11:06:44 +0000 Subject: Add files via upload --- r_facelib/detection/retinaface/retinaface_net.py | 196 +++++++++++++++++++++++ 1 file changed, 196 insertions(+) create mode 100644 r_facelib/detection/retinaface/retinaface_net.py (limited to 'r_facelib/detection/retinaface/retinaface_net.py') diff --git a/r_facelib/detection/retinaface/retinaface_net.py b/r_facelib/detection/retinaface/retinaface_net.py new file mode 100644 index 0000000..c52535e --- /dev/null +++ b/r_facelib/detection/retinaface/retinaface_net.py @@ -0,0 +1,196 @@ +import torch +import torch.nn as nn +import torch.nn.functional as F + + +def conv_bn(inp, oup, stride=1, leaky=0): + return nn.Sequential( + nn.Conv2d(inp, oup, 3, stride, 1, bias=False), nn.BatchNorm2d(oup), + nn.LeakyReLU(negative_slope=leaky, inplace=True)) + + +def conv_bn_no_relu(inp, oup, stride): + return nn.Sequential( + nn.Conv2d(inp, oup, 3, stride, 1, bias=False), + nn.BatchNorm2d(oup), + ) + + +def conv_bn1X1(inp, oup, stride, leaky=0): + return nn.Sequential( + nn.Conv2d(inp, oup, 1, stride, padding=0, bias=False), nn.BatchNorm2d(oup), + nn.LeakyReLU(negative_slope=leaky, inplace=True)) + + +def conv_dw(inp, oup, stride, leaky=0.1): + return nn.Sequential( + nn.Conv2d(inp, inp, 3, stride, 1, groups=inp, bias=False), + nn.BatchNorm2d(inp), + nn.LeakyReLU(negative_slope=leaky, inplace=True), + nn.Conv2d(inp, oup, 1, 1, 0, bias=False), + nn.BatchNorm2d(oup), + nn.LeakyReLU(negative_slope=leaky, inplace=True), + ) + + +class SSH(nn.Module): + + def __init__(self, in_channel, out_channel): + super(SSH, self).__init__() + assert out_channel % 4 == 0 + leaky = 0 + if (out_channel <= 64): + leaky = 0.1 + self.conv3X3 = conv_bn_no_relu(in_channel, out_channel // 2, stride=1) + + self.conv5X5_1 = conv_bn(in_channel, out_channel // 4, stride=1, leaky=leaky) + self.conv5X5_2 = conv_bn_no_relu(out_channel // 4, out_channel // 4, stride=1) + + self.conv7X7_2 = conv_bn(out_channel // 4, out_channel // 4, stride=1, leaky=leaky) + self.conv7x7_3 = conv_bn_no_relu(out_channel // 4, out_channel // 4, stride=1) + + def forward(self, input): + conv3X3 = self.conv3X3(input) + + conv5X5_1 = self.conv5X5_1(input) + conv5X5 = self.conv5X5_2(conv5X5_1) + + conv7X7_2 = self.conv7X7_2(conv5X5_1) + conv7X7 = self.conv7x7_3(conv7X7_2) + + out = torch.cat([conv3X3, conv5X5, conv7X7], dim=1) + out = F.relu(out) + return out + + +class FPN(nn.Module): + + def __init__(self, in_channels_list, out_channels): + super(FPN, self).__init__() + leaky = 0 + if (out_channels <= 64): + leaky = 0.1 + self.output1 = conv_bn1X1(in_channels_list[0], out_channels, stride=1, leaky=leaky) + self.output2 = conv_bn1X1(in_channels_list[1], out_channels, stride=1, leaky=leaky) + self.output3 = conv_bn1X1(in_channels_list[2], out_channels, stride=1, leaky=leaky) + + self.merge1 = conv_bn(out_channels, out_channels, leaky=leaky) + self.merge2 = conv_bn(out_channels, out_channels, leaky=leaky) + + def forward(self, input): + # names = list(input.keys()) + # input = list(input.values()) + + output1 = self.output1(input[0]) + output2 = self.output2(input[1]) + output3 = self.output3(input[2]) + + up3 = F.interpolate(output3, size=[output2.size(2), output2.size(3)], mode='nearest') + output2 = output2 + up3 + output2 = self.merge2(output2) + + up2 = F.interpolate(output2, size=[output1.size(2), output1.size(3)], mode='nearest') + output1 = output1 + up2 + output1 = self.merge1(output1) + + out = [output1, output2, output3] + return out + + +class MobileNetV1(nn.Module): + + def __init__(self): + super(MobileNetV1, self).__init__() + self.stage1 = nn.Sequential( + conv_bn(3, 8, 2, leaky=0.1), # 3 + conv_dw(8, 16, 1), # 7 + conv_dw(16, 32, 2), # 11 + conv_dw(32, 32, 1), # 19 + conv_dw(32, 64, 2), # 27 + conv_dw(64, 64, 1), # 43 + ) + self.stage2 = nn.Sequential( + conv_dw(64, 128, 2), # 43 + 16 = 59 + conv_dw(128, 128, 1), # 59 + 32 = 91 + conv_dw(128, 128, 1), # 91 + 32 = 123 + conv_dw(128, 128, 1), # 123 + 32 = 155 + conv_dw(128, 128, 1), # 155 + 32 = 187 + conv_dw(128, 128, 1), # 187 + 32 = 219 + ) + self.stage3 = nn.Sequential( + conv_dw(128, 256, 2), # 219 +3 2 = 241 + conv_dw(256, 256, 1), # 241 + 64 = 301 + ) + self.avg = nn.AdaptiveAvgPool2d((1, 1)) + self.fc = nn.Linear(256, 1000) + + def forward(self, x): + x = self.stage1(x) + x = self.stage2(x) + x = self.stage3(x) + x = self.avg(x) + # x = self.model(x) + x = x.view(-1, 256) + x = self.fc(x) + return x + + +class ClassHead(nn.Module): + + def __init__(self, inchannels=512, num_anchors=3): + super(ClassHead, self).__init__() + self.num_anchors = num_anchors + self.conv1x1 = nn.Conv2d(inchannels, self.num_anchors * 2, kernel_size=(1, 1), stride=1, padding=0) + + def forward(self, x): + out = self.conv1x1(x) + out = out.permute(0, 2, 3, 1).contiguous() + + return out.view(out.shape[0], -1, 2) + + +class BboxHead(nn.Module): + + def __init__(self, inchannels=512, num_anchors=3): + super(BboxHead, self).__init__() + self.conv1x1 = nn.Conv2d(inchannels, num_anchors * 4, kernel_size=(1, 1), stride=1, padding=0) + + def forward(self, x): + out = self.conv1x1(x) + out = out.permute(0, 2, 3, 1).contiguous() + + return out.view(out.shape[0], -1, 4) + + +class LandmarkHead(nn.Module): + + def __init__(self, inchannels=512, num_anchors=3): + super(LandmarkHead, self).__init__() + self.conv1x1 = nn.Conv2d(inchannels, num_anchors * 10, kernel_size=(1, 1), stride=1, padding=0) + + def forward(self, x): + out = self.conv1x1(x) + out = out.permute(0, 2, 3, 1).contiguous() + + return out.view(out.shape[0], -1, 10) + + +def make_class_head(fpn_num=3, inchannels=64, anchor_num=2): + classhead = nn.ModuleList() + for i in range(fpn_num): + classhead.append(ClassHead(inchannels, anchor_num)) + return classhead + + +def make_bbox_head(fpn_num=3, inchannels=64, anchor_num=2): + bboxhead = nn.ModuleList() + for i in range(fpn_num): + bboxhead.append(BboxHead(inchannels, anchor_num)) + return bboxhead + + +def make_landmark_head(fpn_num=3, inchannels=64, anchor_num=2): + landmarkhead = nn.ModuleList() + for i in range(fpn_num): + landmarkhead.append(LandmarkHead(inchannels, anchor_num)) + return landmarkhead -- cgit v1.2.3