def __init__(self, block, layers, num_classes=1000, **kwargs): self.inplanes = 64 super(ResNet_whiten_3n, self).__init__() self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3, bias=False) self.bn1 = my.Norm(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.AvgPool2d(7, stride=1) if kwargs.setdefault('last', False): self.last_bn = my.Norm(512 * block.expansion, dim=2) else: self.last_bn = None drop_ratio = kwargs.setdefault('dropout', 0) self.dropout = nn.Dropout(p=drop_ratio) if drop_ratio > 0 else None self.fc = nn.Linear(512 * block.expansion, num_classes) for m in self.modules(): if isinstance(m, nn.Conv2d): n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels m.weight.data.normal_(0, math.sqrt(2. / n)) elif isinstance(m, nn.BatchNorm2d): m.weight.data.fill_(1) m.bias.data.zero_()
def __init__(self, inplanes, planes, stride=1, downsample=None, groups=1, base_width=64, dilation=1, norm_layer=None): super(Bottleneck, self).__init__() if norm_layer is None: norm_layer = nn.BatchNorm2d width = int(planes * (base_width / 64.)) * groups # Both self.conv2 and self.downsample layers downsample the input when stride != 1 self.conv1 = conv1x1(inplanes, width) #self.bn1 = norm_layer(width) self.bn1 = my.Norm(width) self.conv2 = conv3x3(width, width, stride, groups, dilation) #self.bn2 = norm_layer(width) self.bn2 = my.Norm(width) self.conv3 = conv1x1(width, planes * self.expansion) #self.bn3 = norm_layer(planes * self.expansion) self.bn3 = my.Norm(planes * self.expansion) self.relu = nn.ReLU(inplace=True) self.downsample = downsample self.stride = stride
def __init__(self, inplanes, planes, stride=1, downsample=None, groups=1, base_width=64, dilation=1, norm_layer=None): super(BasicBlock, self).__init__() if norm_layer is None: norm_layer = nn.BatchNorm2d if groups != 1 or base_width != 64: raise ValueError( 'BasicBlock only supports groups=1 and base_width=64') if dilation > 1: raise NotImplementedError( "Dilation > 1 not supported in BasicBlock") # Both self.conv1 and self.downsample layers downsample the input when stride != 1 self.conv1 = conv3x3(inplanes, planes, stride) #self.bn1 = norm_layer(planes) self.bn1 = my.Norm(planes) self.relu = nn.ReLU(inplace=True) self.conv2 = conv3x3(planes, planes) #self.bn2 = norm_layer(planes) self.bn2 = my.Norm(planes) self.downsample = downsample self.stride = stride
def __init__(self, block, layers, num_classes=1000, zero_init_residual=False, groups=1, width_per_group=64, replace_stride_with_dilation=None, norm_layer=None,**kwargs): super(ResNext, self).__init__() if norm_layer is None: norm_layer = nn.BatchNorm2d self._norm_layer = norm_layer self.inplanes = 64 self.dilation = 1 if replace_stride_with_dilation is None: # each element in the tuple indicates if we should replace # the 2x2 stride with a dilated convolution instead replace_stride_with_dilation = [False, False, False] if len(replace_stride_with_dilation) != 3: raise ValueError("replace_stride_with_dilation should be None " "or a 3-element tuple, got {}".format(replace_stride_with_dilation)) self.groups = groups self.base_width = width_per_group self.conv1 = nn.Conv2d(3, self.inplanes, kernel_size=7, stride=2, padding=3, bias=False) #self.bn1 = norm_layer(self.inplanes) self.bn1 = my.Norm(self.inplanes) 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, dilate=replace_stride_with_dilation[0]) self.layer3 = self._make_layer(block, 256, layers[2], stride=2, dilate=replace_stride_with_dilation[1]) self.layer4 = self._make_layer(block, 512, layers[3], stride=2, dilate=replace_stride_with_dilation[2]) self.avgpool = nn.AdaptiveAvgPool2d((1, 1)) if kwargs.setdefault('last', False): self.last_bn = my.Norm(512 * block.expansion, dim=2) else: self.last_bn = None drop_ratio=kwargs.setdefault('dropout', 0) self.dropout = nn.Dropout(p=drop_ratio) if drop_ratio > 0 else None 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.GroupNorm)): 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)
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.bn1 = my.Norm(planes) self.relu = nn.ReLU(inplace=True) self.conv2 = conv3x3(planes, planes) self.bn2 = my.Norm(planes) self.downsample = downsample self.stride = stride
def __init__(self, depth=4, width=100, **kwargs): super(MLP, self).__init__() layers = [ ext.View(28 * 28), nn.Linear(28 * 28, width), ext.Norm(width), nn.ReLU(True) ] for index in range(depth - 1): layers.append(nn.Linear(width, width)) layers.append(ext.Norm(width)) layers.append(nn.ReLU(True)) layers.append(nn.Linear(width, 10)) self.net = nn.Sequential(*layers)
def __init__(self, inplanes, planes, stride=1, downsample=None): super(BasicBlock, self).__init__() #self.conv1 = conv3x3(inplanes, planes, stride) self.conv1 = my.NormConv(inplanes, planes, 3, stride, padding=1, bias=False) #self.bn1 = nn.BatchNorm2d(planes) self.bn1 = my.Norm(planes) self.relu = nn.ReLU(inplace=True) #self.conv2 = conv3x3(planes, planes) #self.conv2 = Conv2d_ONI(planes, planes, 3, stride=1, padding=1, bias=False, T=7) self.conv2 = my.NormConv(planes, planes, 3, stride=1, padding=1, bias=False) #self.bn2 = nn.BatchNorm2d(planes) self.bn2 = my.Norm(planes) self.downsample = downsample self.stride = stride
def __init__(self, depth=28, widen_factor=1, num_classes=10, dropout=0.0): super(WideResNet, self).__init__() nChannels = [ 16, 16 * widen_factor, 32 * widen_factor, 64 * widen_factor ] assert ((depth - 4) % 6 == 0) n = (depth - 4) / 6 block = BasicBlock # 1st conv before any network block self.conv1 = nn.Conv2d(3, nChannels[0], 3, 1, 1, bias=False) # 1st block self.block1 = self._make_layer(n, block, nChannels[0], nChannels[1], 1, dropout) # 2nd block self.block2 = self._make_layer(n, block, nChannels[1], nChannels[2], 2, dropout) # 3rd block self.block3 = self._make_layer(n, block, nChannels[2], nChannels[3], 2, dropout) # global average pooling and classifier self.bn = my.Norm(nChannels[3]) self.relu = nn.ReLU(inplace=True) self.pool = nn.AvgPool2d(8, 1) self.fc = nn.Linear(nChannels[3], num_classes) self.nChannels = nChannels[3] for m in self.modules(): if isinstance(m, nn.Conv2d): n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels m.weight.data.normal_(0, math.sqrt(2. / n)) elif isinstance(m, nn.BatchNorm2d): m.weight.data.fill_(1) m.bias.data.zero_() elif isinstance(m, nn.Linear): m.bias.data.zero_()
def _make_layer(self, block, planes, blocks, stride=1, dilate=False): norm_layer = self._norm_layer downsample = None previous_dilation = self.dilation if dilate: self.dilation *= stride stride = 1 if stride != 1 or self.inplanes != planes * block.expansion: downsample = nn.Sequential( conv1x1(self.inplanes, planes * block.expansion, stride), my.Norm(planes * block.expansion), ) layers = [] layers.append( block(self.inplanes, planes, stride, downsample, self.groups, self.base_width, previous_dilation, norm_layer)) self.inplanes = planes * block.expansion for _ in range(1, blocks): layers.append( block(self.inplanes, planes, groups=self.groups, base_width=self.base_width, dilation=self.dilation, norm_layer=norm_layer)) return nn.Sequential(*layers)
def __init__(self, inplanes, planes, stride=1, downsample=None): super(Bottleneck, self).__init__() self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, bias=False) self.bn1 = my.Norm(planes) self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride, padding=1, bias=False) self.bn2 = my.Norm(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.downsample = downsample self.stride = stride
def __init__(self, in_channels, out_channels, stride, drop_ratio=0.0): super(BasicBlock, self).__init__() self.bn1 = my.Norm(in_channels) self.relu1 = nn.ReLU(inplace=True) self.conv1 = nn.Conv2d(in_channels, out_channels, 3, stride, 1, bias=False) self.bn2 = my.Norm(out_channels) self.relu2 = nn.ReLU(inplace=True) self.dropout = nn.Dropout2d(p=drop_ratio) if drop_ratio > 0 else None self.conv2 = nn.Conv2d(out_channels, out_channels, 3, 1, 1, bias=False) if in_channels != out_channels: self.shortcut = nn.Conv2d(in_channels, out_channels, 1, stride, 0, bias=False) else: self.shortcut = None
def _make_layer(self, block, planes, blocks, stride=1): downsample = None if stride != 1 or self.inplanes != planes * block.expansion: downsample = nn.Sequential( #nn.Conv2d(self.inplanes, planes * block.expansion, kernel_size=1, stride=stride, bias=False), my.NormConv(self.inplanes, planes * block.expansion, kernel_size=1, stride=stride, bias=False, ONIRow_Fix=True), #nn.BatchNorm2d(planes * block.expansion), ) my.Norm(planes * block.expansion), ) layers = [] layers.append(block(self.inplanes, planes, stride, downsample)) self.inplanes = planes * block.expansion for i in range(1, blocks): layers.append(block(self.inplanes, planes)) return nn.Sequential(*layers)
def make_layers(cfg, batch_norm=True): layers = [] in_channels = 3 for v in cfg: if v == 'M': layers += [nn.MaxPool2d(kernel_size=2, stride=2)] else: conv2d = nn.Conv2d(in_channels, v, kernel_size=3, padding=1, bias=False) if batch_norm: layers += [conv2d, my.Norm(v), nn.ReLU(inplace=True)] else: layers += [conv2d, nn.ReLU(inplace=True)] in_channels = v return nn.Sequential(*layers)
def __init__(self, block, layers, num_classes=1000, **kwargs): self.inplanes = 64 super(ResNetDebug, self).__init__() #self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3, bias=False) self.conv1 = my.NormConv(3, 64, kernel_size=7, stride=2, padding=3, bias=False) self.bn1 = my.Norm(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.AvgPool2d(7, stride=1) self.fc = nn.Linear(512 * block.expansion, num_classes) for m in self.modules(): if isinstance(m, nn.Conv2d): n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels m.weight.data.normal_(0, math.sqrt(2. / n)) elif isinstance(m, nn.BatchNorm2d): m.weight.data.fill_(1) m.bias.data.zero_()