release code

Dassl.ProGrad.pytorch/dassl/modeling/backbone/preact_resnet18.py

@@ -0,0 +1,135 @@
+import torch.nn as nn
+import torch.nn.functional as F
+
+from .build import BACKBONE_REGISTRY
+from .backbone import Backbone
+
+
+class PreActBlock(nn.Module):
+    expansion = 1
+
+    def __init__(self, in_planes, planes, stride=1):
+        super().__init__()
+        self.bn1 = nn.BatchNorm2d(in_planes)
+        self.conv1 = nn.Conv2d(
+            in_planes,
+            planes,
+            kernel_size=3,
+            stride=stride,
+            padding=1,
+            bias=False
+        )
+        self.bn2 = nn.BatchNorm2d(planes)
+        self.conv2 = nn.Conv2d(
+            planes, planes, kernel_size=3, stride=1, padding=1, bias=False
+        )
+
+        if stride != 1 or in_planes != self.expansion * planes:
+            self.shortcut = nn.Sequential(
+                nn.Conv2d(
+                    in_planes,
+                    self.expansion * planes,
+                    kernel_size=1,
+                    stride=stride,
+                    bias=False,
+                )
+            )
+
+    def forward(self, x):
+        out = F.relu(self.bn1(x))
+        shortcut = self.shortcut(out) if hasattr(self, "shortcut") else x
+        out = self.conv1(out)
+        out = self.conv2(F.relu(self.bn2(out)))
+        out += shortcut
+        return out
+
+
+class PreActBottleneck(nn.Module):
+    expansion = 4
+
+    def __init__(self, in_planes, planes, stride=1):
+        super().__init__()
+        self.bn1 = nn.BatchNorm2d(in_planes)
+        self.conv1 = nn.Conv2d(in_planes, planes, kernel_size=1, bias=False)
+        self.bn2 = nn.BatchNorm2d(planes)
+        self.conv2 = nn.Conv2d(
+            planes,
+            planes,
+            kernel_size=3,
+            stride=stride,
+            padding=1,
+            bias=False
+        )
+        self.bn3 = nn.BatchNorm2d(planes)
+        self.conv3 = nn.Conv2d(
+            planes, self.expansion * planes, kernel_size=1, bias=False
+        )
+
+        if stride != 1 or in_planes != self.expansion * planes:
+            self.shortcut = nn.Sequential(
+                nn.Conv2d(
+                    in_planes,
+                    self.expansion * planes,
+                    kernel_size=1,
+                    stride=stride,
+                    bias=False,
+                )
+            )
+
+    def forward(self, x):
+        out = F.relu(self.bn1(x))
+        shortcut = self.shortcut(out) if hasattr(self, "shortcut") else x
+        out = self.conv1(out)
+        out = self.conv2(F.relu(self.bn2(out)))
+        out = self.conv3(F.relu(self.bn3(out)))
+        out += shortcut
+        return out
+
+
+class PreActResNet(Backbone):
+
+    def __init__(self, block, num_blocks):
+        super().__init__()
+        self.in_planes = 64
+
+        self.conv1 = nn.Conv2d(
+            3, 64, kernel_size=3, stride=1, padding=1, bias=False
+        )
+        self.layer1 = self._make_layer(block, 64, num_blocks[0], stride=1)
+        self.layer2 = self._make_layer(block, 128, num_blocks[1], stride=2)
+        self.layer3 = self._make_layer(block, 256, num_blocks[2], stride=2)
+        self.layer4 = self._make_layer(block, 512, num_blocks[3], stride=2)
+
+        self._out_features = 512 * block.expansion
+
+    def _make_layer(self, block, planes, num_blocks, stride):
+        strides = [stride] + [1] * (num_blocks-1)
+        layers = []
+        for stride in strides:
+            layers.append(block(self.in_planes, planes, stride))
+            self.in_planes = planes * block.expansion
+        return nn.Sequential(*layers)
+
+    def forward(self, x):
+        out = self.conv1(x)
+        out = self.layer1(out)
+        out = self.layer2(out)
+        out = self.layer3(out)
+        out = self.layer4(out)
+        out = F.avg_pool2d(out, 4)
+        out = out.view(out.size(0), -1)
+        return out
+
+
+"""
+Preact-ResNet18 was used for the CIFAR10 and
+SVHN datasets (both are SSL tasks) in
+
+- Wang et al. Semi-Supervised Learning by
+Augmented Distribution Alignment. ICCV 2019.
+"""
+
+
+@BACKBONE_REGISTRY.register()
+def preact_resnet18(**kwargs):
+    return PreActResNet(PreActBlock, [2, 2, 2, 2])