first commit

ssd/layers/__init__.py

@@ -0,0 +1,25 @@
+import torch
+import torch.nn as nn
+import torch.nn.init as init
+from .separable_conv import SeparableConv2d
+
+__all__ = ['L2Norm', 'SeparableConv2d']
+
+
+class L2Norm(nn.Module):
+    def __init__(self, n_channels, scale):
+        super(L2Norm, self).__init__()
+        self.n_channels = n_channels
+        self.gamma = scale or None
+        self.eps = 1e-10
+        self.weight = nn.Parameter(torch.Tensor(self.n_channels))
+        self.reset_parameters()
+
+    def reset_parameters(self):
+        init.constant_(self.weight, self.gamma)
+
+    def forward(self, x):
+        norm = x.pow(2).sum(dim=1, keepdim=True).sqrt() + self.eps
+        x = torch.div(x, norm)
+        out = self.weight.unsqueeze(0).unsqueeze(2).unsqueeze(3).expand_as(x) * x
+        return out

ssd/layers/separable_conv.py

@@ -0,0 +1,17 @@
+from torch import nn
+
+
+class SeparableConv2d(nn.Module):
+    def __init__(self, in_channels, out_channels, kernel_size=1, stride=1, padding=0, onnx_compatible=False):
+        super().__init__()
+        ReLU = nn.ReLU if onnx_compatible else nn.ReLU6
+        self.conv = nn.Sequential(
+            nn.Conv2d(in_channels=in_channels, out_channels=in_channels, kernel_size=kernel_size,
+                      groups=in_channels, stride=stride, padding=padding),
+            nn.BatchNorm2d(in_channels),
+            ReLU(),
+            nn.Conv2d(in_channels=in_channels, out_channels=out_channels, kernel_size=1),
+        )
+
+    def forward(self, x):
+        return self.conv(x)