replace ReLU with Swish

resnet.py

@@ -1,21 +1,13 @@
 import torch.nn as nn
 import math
-import torch.utils.model_zoo as model_zoo
+
+from swish import Swish
 
 
 __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,
@@ -29,7 +21,7 @@ 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.act = Swish(inplace=True)
         self.conv2 = conv3x3(planes, planes)
         self.bn2 = nn.BatchNorm2d(planes)
         self.downsample = downsample
@@ -40,7 +32,7 @@ def forward(self, x):
 
         out = self.conv1(x)
         out = self.bn1(out)
-        out = self.relu(out)
+        out = self.act(out)
 
         out = self.conv2(out)
         out = self.bn2(out)
@@ -49,7 +41,7 @@ def forward(self, x):
             residual = self.downsample(x)
 
         out += residual
-        out = self.relu(out)
+        out = self.act(out)
 
         return out
 
@@ -66,7 +58,7 @@ def __init__(self, inplanes, planes, stride=1, downsample=None):
         self.bn2 = nn.BatchNorm2d(planes)
         self.conv3 = nn.Conv2d(planes, planes * 4, kernel_size=1, bias=False)
         self.bn3 = nn.BatchNorm2d(planes * 4)
-        self.relu = nn.ReLU(inplace=True)
+        self.act = Swish(inplace=True)
         self.downsample = downsample
         self.stride = stride
 
@@ -75,11 +67,11 @@ def forward(self, x):
 
         out = self.conv1(x)
         out = self.bn1(out)
-        out = self.relu(out)
+        out = self.act(out)
 
         out = self.conv2(out)
         out = self.bn2(out)
-        out = self.relu(out)
+        out = self.act(out)
 
         out = self.conv3(out)
         out = self.bn3(out)
@@ -88,7 +80,7 @@ def forward(self, x):
             residual = self.downsample(x)
 
         out += residual
-        out = self.relu(out)
+        out = self.act(out)
 
         return out
 
@@ -101,7 +93,7 @@ def __init__(self, block, layers, num_classes=1000):
         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.act = Swish(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)
@@ -138,7 +130,7 @@ def _make_layer(self, block, planes, blocks, stride=1):
     def forward(self, x):
         x = self.conv1(x)
         x = self.bn1(x)
-        x = self.relu(x)
+        x = self.act(x)
         x = self.maxpool(x)
 
         x = self.layer1(x)
@@ -161,7 +153,7 @@ def resnet18(pretrained=False, **kwargs):
     """
     model = ResNet(BasicBlock, [2, 2, 2, 2], **kwargs)
     if pretrained:
-        model.load_state_dict(model_zoo.load_url(model_urls['resnet18']))
+        raise NotImplementedError()
     return model
 
 
@@ -173,7 +165,7 @@ def resnet34(pretrained=False, **kwargs):
     """
     model = ResNet(BasicBlock, [3, 4, 6, 3], **kwargs)
     if pretrained:
-        model.load_state_dict(model_zoo.load_url(model_urls['resnet34']))
+        raise NotImplementedError()
     return model
 
 
@@ -185,7 +177,7 @@ def resnet50(pretrained=False, **kwargs):
     """
     model = ResNet(Bottleneck, [3, 4, 6, 3], **kwargs)
     if pretrained:
-        model.load_state_dict(model_zoo.load_url(model_urls['resnet50']))
+        raise NotImplementedError()
     return model
 
 
@@ -197,7 +189,7 @@ def resnet101(pretrained=False, **kwargs):
     """
     model = ResNet(Bottleneck, [3, 4, 23, 3], **kwargs)
     if pretrained:
-        model.load_state_dict(model_zoo.load_url(model_urls['resnet101']))
+        raise NotImplementedError()
     return model
 
 
@@ -209,5 +201,5 @@ def resnet152(pretrained=False, **kwargs):
     """
     model = ResNet(Bottleneck, [3, 8, 36, 3], **kwargs)
     if pretrained:
-        model.load_state_dict(model_zoo.load_url(model_urls['resnet152']))
+        raise NotImplementedError()
     return model

swish.py

@@ -0,0 +1,16 @@
+import torch.nn as nn
+import torch.nn.functional as F
+
+class Swish(nn.Module):
+
+    def __init__(self, inplace=False):
+        super().__init__()
+
+        self.inplace = True
+
+    def forward(self, x):
+        if self.inplace:
+            x.mul_(F.sigmoid(x))
+            return x
+        else:
+            return x * F.sigmoid(x)