def __init__(self, block, layers, num_classes=10, zero_init_residual=False): super(MyResNet, self).__init__() self.inplanes = 64 self.conv1 = nn.Conv2d(1, 64, kernel_size=7, stride=2, padding=3, bias=False) self.bn1 = nn.BatchNorm2d(64) self.relu = nn.ReLU(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) self.layer3 = self._make_layer(block, 256, layers[2], stride=2) self.layer4 = self._make_layer(block, 512, layers[3], stride=2) self.avgpool = nn.AdaptiveAvgPool2d((1, 1)) for m in self.modules(): if isinstance(m, nn.Conv2d): nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu') elif isinstance(m, nn.BatchNorm2d): nn.init.constant_(m.weight, 1) nn.init.constant_(m.bias, 0) # Zero-initialize the last BN in each residual branch, # so that the residual branch starts with zeros, and each residual block behaves like an identity. # This improves the model by 0.2~0.3% according to https://arxiv.org/abs/1706.02677 if zero_init_residual: for m in self.modules(): if isinstance(m, Bottleneck): nn.init.constant_(m.bn3.weight, 0) elif isinstance(m, BasicBlock): nn.init.constant_(m.bn2.weight, 0) self.classifier = nn.Sequential( nn.Dropout(p=0.5), nn.Linear(512 * block.expansion, 256), nn.BatchNorm1d(256), nn.ReLU(inplace=True), nn.Dropout(p=0.5), nn.Linear(256, num_classes), )
def __init__(self, num_classes=10): super(VGG, self).__init__() self.l1 = self.two_conv_pool(1, 64, 64) self.l2 = self.two_conv_pool(64, 128, 128) self.l3 = self.three_conv_pool(128, 256, 256, 256) self.l4 = self.three_conv_pool(256, 256, 256, 256) self.classifier = nn.Sequential( nn.Dropout(p=0.5), nn.Linear(256, 512), nn.BatchNorm1d(512), nn.ReLU(inplace=True), nn.Dropout(p=0.5), nn.Linear(512, num_classes), )
def head_layer(self): cin = self.channels #* 2 return nn.Sequential( nn.AdaptiveAvgPool2d(1), #AdaptiveConcatPool2d(1), #nn.Dropout2d(0.5), Flatten(), init_default(nn.Linear(cin, self.classes), nn.init.kaiming_normal_))
def __init__(self, num_classes=10): super(ConvNet, self).__init__() self.layer1 = nn.Sequential( nn.Conv2d(1, 16, kernel_size=5, stride=1, padding=2), nn.BatchNorm2d(16), nn.ReLU(), nn.MaxPool2d(kernel_size=2, stride=2)) self.layer2 = nn.Sequential( nn.Conv2d(16, 32, kernel_size=5, stride=1, padding=2), nn.BatchNorm2d(32), nn.ReLU(), nn.MaxPool2d(kernel_size=2, stride=2)) self.fc = nn.Linear(7 * 7 * 32, num_classes)