def __init__(self, in_planes, planes, stride=1, group_norm=0): super(PreActBottleneck, self).__init__() self.bn1 = norm2d(in_planes, group_norm) self.conv1 = nn.Conv2d(in_planes, planes, kernel_size=1, bias=False) self.bn2 = norm2d(planes, group_norm) self.gate1 = GateLayer(planes, planes, [1, -1, 1, 1]) self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride, padding=1, bias=False) self.bn3 = norm2d(planes, group_norm) self.gate2 = GateLayer(planes, planes, [1, -1, 1, 1]) self.conv3 = nn.Conv2d(planes, self.expansion * planes, kernel_size=1, bias=False) self.gate3 = GateLayer(self.expansion * planes, self.expansion * planes, [1, -1, 1, 1]) 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)) self.gate_shortcut = GateLayer(self.expansion * planes, self.expansion * planes, [1, -1, 1, 1])
def __init__(self, inplanes, planes, stride=1, downsample=None, gate=None): super(BasicBlock, self).__init__() self.conv1 = conv3x3(inplanes, planes, stride) self.bn1 = nn.BatchNorm2d(planes) self.relu = nn.ReLU(inplace=True) self.gate1 = GateLayer(planes, planes, [1, -1, 1, 1]) self.conv2 = conv3x3(planes, planes) self.bn2 = nn.BatchNorm2d(planes) self.gate2 = GateLayer(planes, planes, [1, -1, 1, 1]) self.downsample = downsample self.stride = stride self.gate = gate
def flatten_model(old_net): """Removes nested modules. Only works for VGG.""" from collections import OrderedDict module_list, counter, inserted_view = [], 0, False gate_counter = 0 print("printing network") print(" Hard codded network in vgg_bn.py") for m_indx, module in enumerate(old_net.modules()): if not isinstance(module, (nn.Sequential, VGG)): print(m_indx, module) if isinstance(module, nn.Linear) and not inserted_view: module_list.append(('flatten', LinView())) inserted_view = True # features.0 # classifier prefix = "features" if m_indx > 30: prefix = "classifier" if m_indx == 32: counter = 0 # prefix = "" module_list.append((prefix + str(counter), module)) if isinstance(module, nn.BatchNorm2d): planes = module.num_features gate = GateLayer(planes, planes, [1, -1, 1, 1]) module_list.append(('gate%d' % (gate_counter), gate)) print("gate ", counter, planes) gate_counter += 1 if isinstance(module, nn.BatchNorm1d): planes = module.num_features gate = GateLayer(planes, planes, [1, -1]) module_list.append(('gate%d' % (gate_counter), gate)) print("gate ", counter, planes) gate_counter += 1 counter += 1 new_net = nn.Sequential(OrderedDict(module_list)) return new_net
def __init__(self, dataset="CIFAR10"): super(LeNet, self).__init__() if dataset == "CIFAR10": nunits_input = 3 nuintis_fc = 32 * 5 * 5 elif dataset == "MNIST": nunits_input = 1 nuintis_fc = 32 * 4 * 4 self.conv1 = nn.Conv2d(nunits_input, 16, 5) self.gate1 = GateLayer(16, 16, [1, -1, 1, 1]) self.conv2 = nn.Conv2d(16, 32, 5) self.gate2 = GateLayer(32, 32, [1, -1, 1, 1]) self.fc1 = nn.Linear(nuintis_fc, 120) self.gate3 = GateLayer(120, 120, [1, -1]) self.fc2 = nn.Linear(120, 84) self.gate4 = GateLayer(84, 84, [1, -1]) self.fc3 = nn.Linear(84, 10)
def __init__(self, inplanes, planes, stride=1, downsample=None, gate=None): super(Bottleneck, self).__init__() self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, bias=False) self.bn1 = nn.BatchNorm2d(planes) self.gate1 = GateLayer(planes,planes,[1, -1, 1, 1]) self.relu1 = nn.ReLU(inplace=True) self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride, padding=1, bias=False) self.bn2 = nn.BatchNorm2d(planes) self.gate2 = GateLayer(planes,planes,[1, -1, 1, 1]) self.relu2 = nn.ReLU(inplace=True) self.conv3 = nn.Conv2d(planes, planes * self.expansion, kernel_size=1, bias=False) self.bn3 = nn.BatchNorm2d(planes * self.expansion) self.relu3 = nn.ReLU(inplace=True) self.downsample = downsample self.stride = stride self.gate = gate
def __init__(self, num_input_features, num_output_features, gate_types): super(_Transition, self).__init__() self.add_module('norm', nn.BatchNorm2d(num_input_features)) self.add_module('relu', nn.ReLU(inplace=True)) if 'input' in gate_types: self.add_module( 'gate): (input', GateLayer(num_input_features, num_input_features, [1, -1, 1, 1])) self.add_module( 'conv', nn.Conv2d(num_input_features, num_output_features, kernel_size=1, stride=1, bias=False)) self.add_module('pool', nn.AvgPool2d(kernel_size=2, stride=2)) if 'output_conv' in gate_types: self.add_module( 'gate): (output_conv', GateLayer(num_output_features, num_output_features, [1, -1, 1, 1]))
def __init__(self, num_input_features, growth_rate, bn_size, drop_rate, gate_types): super(_DenseLayer, self).__init__() self.add_module('norm1', nn.BatchNorm2d(num_input_features)), self.add_module('relu1', nn.ReLU(inplace=True)), if 'input' in gate_types: self.add_module( 'gate1): (input', GateLayer(num_input_features, num_input_features, [1, -1, 1, 1])) self.add_module( 'conv1', nn.Conv2d(num_input_features, bn_size * growth_rate, kernel_size=1, stride=1, bias=False)), self.add_module('norm2', nn.BatchNorm2d(bn_size * growth_rate)), if 'output_bn' in gate_types: self.add_module( 'gate2): (output_bn', GateLayer(bn_size * growth_rate, bn_size * growth_rate, [1, -1, 1, 1])) self.add_module('relu2', nn.ReLU(inplace=True)), self.add_module( 'conv2', nn.Conv2d(bn_size * growth_rate, growth_rate, kernel_size=3, stride=1, padding=1, bias=False)), if 'output_conv' in gate_types: self.add_module('gate3): (output_conv', GateLayer(growth_rate, growth_rate, [1, -1, 1, 1])) self.drop_rate = drop_rate
def __init__(self, block, layers, num_classes=1000, skip_gate = True): self.inplanes = 64 super(ResNet, self).__init__() 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.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1) gate = skip_gate self.gate = gate if gate: # self.gate_skip1 = GateLayer(64,64,[1, -1, 1, 1]) self.gate_skip64 = GateLayer(64*4,64*4,[1, -1, 1, 1]) self.gate_skip128 = GateLayer(128*4,128*4,[1, -1, 1, 1]) self.gate_skip256 = GateLayer(256*4,256*4,[1, -1, 1, 1]) self.gate_skip512 = GateLayer(512*4,512*4,[1, -1, 1, 1]) if block == BasicBlock: self.gate_skip64 = GateLayer(64, 64, [1, -1, 1, 1]) self.gate_skip128 = GateLayer(128, 128, [1, -1, 1, 1]) self.gate_skip256 = GateLayer(256, 256, [1, -1, 1, 1]) self.gate_skip512 = GateLayer(512, 512, [1, -1, 1, 1]) else: self.gate_skip64 = None self.gate_skip128 = None self.gate_skip256 = None self.gate_skip512 = None self.layer1 = self._make_layer(block, 64, layers[0], gate = self.gate_skip64) self.layer2 = self._make_layer(block, 128, layers[1], stride=2, gate=self.gate_skip128) self.layer3 = self._make_layer(block, 256, layers[2], stride=2, gate=self.gate_skip256) self.layer4 = self._make_layer(block, 512, layers[3], stride=2, gate=self.gate_skip512) self.avgpool = nn.AvgPool2d(7, stride=1) self.fc = nn.Linear(512 * block.expansion, num_classes) 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)
def __init__( self, growth_rate=32, block_config=(6, 12, 24, 16), num_init_features=64, bn_size=4, drop_rate=0, num_classes=1000, gate_types=['input', 'output_bn', 'output_conv', 'bottom', 'top']): super(DenseNet, self).__init__() # First convolution self.features = nn.Sequential( OrderedDict([ ('conv0', nn.Conv2d(3, num_init_features, kernel_size=7, stride=2, padding=3, bias=False)), ('norm0', nn.BatchNorm2d(num_init_features)), ('relu0', nn.ReLU(inplace=True)), ('pool0', nn.MaxPool2d(kernel_size=3, stride=2, padding=1)), ])) if 'bottom' in gate_types: self.features.add_module( 'gate0): (bottom', GateLayer(num_init_features, num_init_features, [1, -1, 1, 1])) # Each denseblock num_features = num_init_features for i, num_layers in enumerate(block_config): block = _DenseBlock(num_layers=num_layers, num_input_features=num_features, bn_size=bn_size, growth_rate=growth_rate, drop_rate=drop_rate, gate_types=gate_types) self.features.add_module('denseblock%d' % (i + 1), block) num_features = num_features + num_layers * growth_rate if i != len(block_config) - 1: trans = _Transition(num_input_features=num_features, num_output_features=num_features // 2, gate_types=gate_types) self.features.add_module('transition%d' % (i + 1), trans) num_features = num_features // 2 # Final batch norm self.features.add_module('norm5', nn.BatchNorm2d(num_features)) if 'top' in gate_types: self.features.add_module( 'gate5): (top', GateLayer(num_features, num_features, [1, -1, 1, 1])) # Linear layer self.classifier = nn.Linear(num_features, num_classes) # Official init from torch repo. for m in self.modules(): if isinstance(m, nn.Conv2d): nn.init.kaiming_normal_(m.weight) elif isinstance(m, nn.BatchNorm2d): nn.init.constant_(m.weight, 1) nn.init.constant_(m.bias, 0) elif isinstance(m, nn.Linear): nn.init.constant_(m.bias, 0)
def __init__(self, block, num_blocks, num_classes=10, group_norm=0, dataset="CIFAR10"): super(PreActResNet, self).__init__() self.in_planes = 64 self.dataset = dataset if dataset == "CIFAR10": self.conv1 = nn.Conv2d(3, 64, kernel_size=3, stride=1, padding=1, bias=False) num_classes = 10 elif dataset == "Imagenet": 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.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1) num_classes = 1000 self.gate_in = GateLayer(64, 64, [1, -1, 1, 1]) self.layer1 = self._make_layer(block, 64, num_blocks[0], stride=1, group_norm=group_norm) self.layer2 = self._make_layer(block, 128, num_blocks[1], stride=2, group_norm=group_norm) self.layer3 = self._make_layer(block, 256, num_blocks[2], stride=2, group_norm=group_norm) self.layer4 = self._make_layer(block, 512, num_blocks[3], stride=2, group_norm=group_norm) if dataset == "CIFAR10": self.avgpool = nn.AvgPool2d(4, stride=1) self.linear = nn.Linear(512 * block.expansion, num_classes) elif dataset == "Imagenet": self.avgpool = nn.AvgPool2d(7, stride=1) self.fc = nn.Linear(512 * block.expansion, num_classes) for m in self.modules(): if isinstance(m, nn.Conv2d): nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu') if isinstance(m, nn.BatchNorm2d): m.bias.data.zero_()