Add AlexNet and LeNet5

mmcls/models/backbones/__init__.py

@@ -1,3 +1,5 @@
+from .alexnet import AlexNet
+from .lenet import LeNet5
 from .mobilenet_v2 import MobileNetV2
 from .mobilenet_v3 import MobileNetv3
 from .regnet import RegNet
@@ -9,6 +11,7 @@ from .shufflenet_v1 import ShuffleNetV1
 from .shufflenet_v2 import ShuffleNetV2
 
 __all__ = [
-    'RegNet', 'ResNet', 'ResNeXt', 'ResNetV1d', 'ResNetV1d', 'SEResNet',
-    'SEResNeXt', 'ShuffleNetV1', 'ShuffleNetV2', 'MobileNetV2', 'MobileNetv3'
+    'LeNet5', 'AlexNet', 'RegNet', 'ResNet', 'ResNeXt', 'ResNetV1d',
+    'ResNetV1d', 'SEResNet', 'SEResNeXt', 'ShuffleNetV1', 'ShuffleNetV2',
+    'MobileNetV2', 'MobileNetv3'
 ]

mmcls/models/backbones/alexnet.py

@@ -0,0 +1,55 @@
+import torch.nn as nn
+
+from ..builder import BACKBONES
+from .base_backbone import BaseBackbone
+
+
+@BACKBONES.register_module()
+class AlexNet(BaseBackbone):
+    """`AlexNet <https://en.wikipedia.org/wiki/AlexNet>`_ backbone.
+
+    The input for AlexNet is a 256x256 RGB image.
+
+    Args:
+        num_classes (int): number of classes for classification.
+            The default value is -1, which uses the backbone as
+            a feature extractor without the top classifier.
+    """
+
+    def __init__(self, num_classes=-1):
+        super(AlexNet, self).__init__()
+        self.num_classes = num_classes
+        self.features = nn.Sequential(
+            nn.Conv2d(3, 64, kernel_size=11, stride=4, padding=2),
+            nn.ReLU(inplace=True),
+            nn.MaxPool2d(kernel_size=3, stride=2),
+            nn.Conv2d(64, 192, kernel_size=5, padding=2),
+            nn.ReLU(inplace=True),
+            nn.MaxPool2d(kernel_size=3, stride=2),
+            nn.Conv2d(192, 384, kernel_size=3, padding=1),
+            nn.ReLU(inplace=True),
+            nn.Conv2d(384, 256, kernel_size=3, padding=1),
+            nn.ReLU(inplace=True),
+            nn.Conv2d(256, 256, kernel_size=3, padding=1),
+            nn.ReLU(inplace=True),
+            nn.MaxPool2d(kernel_size=3, stride=2),
+        )
+        if self.num_classes > 0:
+            self.classifier = nn.Sequential(
+                nn.Dropout(),
+                nn.Linear(256 * 6 * 6, 4096),
+                nn.ReLU(inplace=True),
+                nn.Dropout(),
+                nn.Linear(4096, 4096),
+                nn.ReLU(inplace=True),
+                nn.Linear(4096, num_classes),
+            )
+
+    def forward(self, x):
+
+        x = self.features(x)
+        if self.num_classes > 0:
+            x = x.view(x.size(0), 256 * 6 * 6)
+            x = self.classifier(x)
+
+        return x

mmcls/models/backbones/lenet.py

@@ -0,0 +1,41 @@
+import torch.nn as nn
+
+from ..builder import BACKBONES
+from .base_backbone import BaseBackbone
+
+
+@BACKBONES.register_module()
+class LeNet5(BaseBackbone):
+    """`LeNet5 <https://en.wikipedia.org/wiki/LeNet>`_ backbone.
+
+    The input for LeNet-5 is a 32×32 grayscale image.
+
+    Args:
+        num_classes (int): number of classes for classification.
+            The default value is -1, which uses the backbone as
+            a feature extractor without the top classifier.
+    """
+
+    def __init__(self, num_classes=-1):
+        super(LeNet5, self).__init__()
+        self.num_classes = num_classes
+        self.features = nn.Sequential(
+            nn.Conv2d(1, 6, kernel_size=5, stride=1), nn.Tanh(),
+            nn.AvgPool2d(kernel_size=2),
+            nn.Conv2d(6, 16, kernel_size=5, stride=1), nn.Tanh(),
+            nn.AvgPool2d(kernel_size=2),
+            nn.Conv2d(16, 120, kernel_size=5, stride=1), nn.Tanh())
+        if self.num_classes > 0:
+            self.classifier = nn.Sequential(
+                nn.Linear(120, 84),
+                nn.Tanh(),
+                nn.Linear(84, num_classes),
+            )
+
+    def forward(self, x):
+
+        x = self.features(x)
+        if self.num_classes > 0:
+            x = self.classifier(x.squeeze())
+
+        return x